Identifying postoperative complications after inguinal hernia repair with a smartphone application: a comparative cohort study

PURPOSE

The Q1.6 Inguinal Hernia application continuously measures patient-reported outcomes (PROs) by sampling experiences through brief, digital and condition-specific questions, utilising micro-moments. This can overcome the limitations of current paper questionnaires and give real-time insight into patient recovery. This exploratory study compares data from the application with retrospective data from electronic medical records (EMRs) to provide information on its accuracy in detecting postoperative complications after inguinal hernia repair.

METHODS

Patients were asked to use the application in addition to their usual care. The application employs twitch crowdsourcing to gather PROs. Questions from validated and frequently used questionnaires were integrated. A retrospective assessment of EMRs was combined with an additional telephone interview. The primary endpoints were the sensitivity and specificity of the application in detecting chronic postoperative inguinal pain, recurrence and surgical-site infection (SSI).

RESULTS

A total of 215 patients were analysed. The sensitivity and specificity for detecting chronic postoperative inguinal pain were 100% (95% CI [47.8%, 100%]) and 93.7% (95% CI [88.3%, 97.1%]), respectively. For recurrence, the sensitivity was 77.8% (95% CI [40.0%, 97.2%]), and the specificity was 81.3% (95% CI [75.0%, 86.5%]). For SSI, the sensitivity and specificity were 75.0% (95% CI [19.4%, 99.4%]) and 89.8% (95% CI [84.8%, 93.6%]), respectively.

CONCLUSION

This study demonstrates satisfactory measurement capabilities of the Q1.6 Inguinal Hernia application for identifying postoperative complications following inguinal hernia repair. However, certain aspects require further improvement, such as addressing error-prone questions, enhancing long-term compliance, and validating (pain) measurements through prospective control data.

TRAIL REGISTRATION NUMBER

NL7813 (Dutch Trial Registry), 19 May 2019.

Effectiveness of telerehabilitation intervention to improve pain and physical function in people with patellofemoral pain syndrome: study protocol for a randomized controlled trial

BACKGROUND

Patellofemoral pain syndrome (PFPS) is a common musculoskeletal condition in young and active adults. Exercise therapy is an essential part of rehabilitation in people with PFPS (PwPFPS). Telerehabilitation is an innovative treatment approach that has been used in several musculoskeletal conditions. This study aims to investigate the non-inferiority of telerehabilitation through a smartphone application, the Vito App, compared to face-to-face physical therapy on reducing pain and improving physical function, quality of life, and psychological factors.

METHODS

This randomized controlled trial will include 60 PwPFPS. to a control group (face-to-face physical therapy) or an experimental group (telerehabilitation). The intervention for both groups consists of stretching, strengthening, balance, and functional exercises for 6 weeks and three sessions per week. The primary outcomes are pain intensity by visual analog scale (VAS), physical function by the Kujala questionnaire and functional tests including the bilateral squat, anteromedial lunge, and step down, and quality of life by the Knee Injury and Osteoarthritis Outcome Score (KOOS) questionnaire quality of life subscale. Secondary outcomes are psychological factors such as anxiety and depression assessed with the Hospital Anxiety and Depression Scale (HADS) questionnaire, kinesiophobia assessed with the Tampa scale, and pain catastrophizing assessed with the Pain Catastrophizing Scale (PCS). Assessments will be held in 3 phases: pre-test (before the intervention), post-test (after the 6 weeks of intervention), and follow-up (1 month after the end of the intervention).

DISCUSSION

We expect that both the control group and experimental group will show similar improvements in clinical and psychological outcome measures. If our hypothesis becomes true, PwPFPS can use telerehabilitation as a practical treatment approach. Telerehabilitation can also enhance accessibility to rehabilitation services for active adults and for people living in remote and rural areas.

TRIAL REGISTRATION

Iranian Registry of Clinical Trials (IRCT) IRCT20201112049361N1. Registered on 29 October 2022.

Mobile health applications for epilepsy in Indian app stores: A systematic review and content analysis using the mobile app rating scale

OBJECTIVE

The growing prevalence of smartphones may prompt individuals with epilepsy to pursue unfulfilled healthcare requirements through mobile health (mHealth) apps, but the content and quality of these mHealth apps are rarely analysed. Hence, this study aimed to identify and assess the quality of epilepsy apps for patients with epilepsy (PWE), their caregivers, and healthcare practitioners (HCPs) available in the Play Store and App Store of India.

METHODS

We performed a systematic search on the Google Play Store and Apple App Store of India to identify the mHealth apps for epilepsy which were released and updated till May 2023. The identified applications were downloaded and the quality was assessed using a Mobile app rating scale (MARS) for the overall quality, Aesthetics, Engagement, Functionality, and Information by three independent reviewers. The intraclass correlation coefficient (ICC) was calculated to assess the interrater reliability between the reviewers. An unpaired t-test was calculated to analyse the difference in mean scores for Android and iOS applications.

RESULTS

The systematic search yielded a total of 2518 apps, out of which 26 were selected for inclusion in the study. Among these, 9 apps were compatible with Android, 11 with iOS, and 6 on both platforms. The mean (SD) MARS score of the apps was 3.5 (0.6) and the ICC for the overall app quality was 0.90 (95% CI: 0.82-0.96). Overall, apps scored highest in functionality (3.9), followed by aesthetics (3.6), information (3.3), and engagement (3.2). Among the included apps, the overall quality score was found to be higher for iOS apps than Android (MD = 0.54; 95% CI: 0.02 - 1.07; p-value: 0.042).

CONCLUSION

Our study identified twenty-six mHealth applications for epilepsy that integrated various aspects of epilepsy self-management. The results of this study emphasize the importance of ensuring that current and future applications offer evidence-based information, integrate features that align with patient preferences, and generate evidence regarding the effectiveness of application usage.

Effectiveness of a supportive care program via a smartphone application on the quality of life and care burden among family caregivers of patients with major depressive disorder: a randomized controlled trial

BACKGROUND

The majority of patients with major depressive disorder require care that has generally affected caregivers' lives. Providing care could cause negative experiences as a care burden and deteriorate quality of life. However, there is a lack of evidence about caregiver training-based informatics and its impact on the caregiver's life.

METHODS

This experimental study was carried out in Mashhad, Iran. A total of 60 primary family caregivers of patients with major depressive disorder were included in the study between February and July 2021. The quadruple block randomization method was used to allocate the participants into control and intervention groups. In the intervention group, family caregivers used the application with weekly phone calls for one month. The app contains the most important points of patient care and has the possibility of communicating with the nurse. The Novak and Guest Care Burden Inventory and the short form of the World Health Organization Quality of Life Questionnaire were completed before and after the intervention. Data analysis was performed using chi-squared tests, independent sample t tests, and analysis of covariance.

RESULTS

At baseline, the mean scores of care burden and quality of life were homogeneous between the two groups. After the intervention, the mean scores of care burden and quality of life were significantly reduced and improved in the intervention group compared with the control group (p < 0.001).

CONCLUSIONS

Using the application with the ability to communicate with the caregiver, along with educational support, helps to strengthen the relationship between the family caregiver and the nurse. Despite the effectiveness of the present intervention, before including this form of implementation of support in care programs, it is necessary to evaluate its other positive aspects in future studies.

TRIAL REGISTRATION

Iranian Registry of Clinical Trials (IRCT), IRCT20210202050222N1. Registered on 05/02/2022.

On-site colorimetric food spoilage monitoring with smartphone embedded machine learning

Real-time and on-site food spoilage monitoring is still a challenging issue to prevent food poisoning. At the onset of food spoilage, microbial and enzymatic activities lead to the formation of volatile amines. Monitoring of these amines with conventional methods requires sophisticated, costly, labor-intensive, and time consuming analysis. Here, anthocyanins rich red cabbage extract (ARCE) based colorimetric sensing system was developed with the incorporation of embedded machine learning in a smartphone application for real-time food spoilage monitoring. FG-UV-CD100 films were first fabricated by crosslinking ARCE-doped fish gelatin (FG) with carbon dots (CDs) under UV light. The color change of FG-UV-CD100 films with varying ammonia vapor concentrations was captured in different light sources with smartphones of various brands, and a comprehensive dataset was created to train machine learning (ML) classifiers to be robust and adaptable to ambient conditions, resulting in 98.8% classification accuracy. Meanwhile, the ML classifier was embedded into our Android application, SmartFood++, enabling analysis in about 0.1 s without internet access, unlike its counterpart using cloud operation via internet. The proposed system was also tested on a real fish sample with 99.6% accuracy, demonstrating that it has a great advantage as a potent tool for on-site real-time monitoring of food spoilage by non-specialized personnel.

Remote Monitoring of Visual Function in Patients with Maculopathy: The Aphelion Study

INTRODUCTION

Remote monitoring of vision, using tools such as the shape discrimination hyperacuity (SDH) test, can detect disease activity in patients with maculopathy. We determined the in-clinic accuracy and repeatability of three myVisionTrack expanded version (mVTx) tests for self-testing of visual acuity (VA) and contrast sensitivity.

METHODS

Aphelion, a single-arm, prospective study conducted at two sites in the USA, included adults with any maculopathy and a baseline VA of 0.7 log of minimum angle of resolution (logMAR) (Snellen 20/100) or better. Participants completed the mVTx tests (tumbling E, Landolt C, contrast sensitivity, and SDH) and standard clinical tests (near and distance Early Treatment Diabetic Retinopathy Study [ETDRS] charts and the Pelli-Robson contrast sensitivity chart). Test-retest repeatability and agreement between the mVTx tests and the corresponding clinical test were assessed by Bland-Altman analyses. Participants also completed a usability survey.

RESULTS

The mean age of the 122 participants was 67 years. The most common diagnosis was age-related macular degeneration (42% of patients). The tumbling E test had a test-retest 95% limit of agreement (LoA) of ± 0.18 logMAR; the Landolt C test, ± 0.23 logMAR; the SDH test, ± 0.24 logMAR; and the contrast sensitivity test, ± 0.32 log contrast threshold (logCT). Compared with the distance ETDRS chart, the LoA was ± 0.35 logMAR for the tumbling E test (mean difference, - 0.07 logMAR) and ± 0.39 logMAR for the Landolt C test (mean difference, 0.03 logMAR). For the contrast sensitivity test, the LoA compared with the Pelli-Robson chart was ± 0.30 logCT (mean difference, - 0.25 logCT). Most participants (85%) reported that they learned the tests quickly. The tumbling E test scored the highest on ease of use.

CONCLUSION

The mVTx tests of VA are accurate and repeatable, supporting their potential use alongside the SDH test to detect disease progression remotely between clinic visits.

Mitigating errors in mobile-based dietary assessments: Effects of a data modification process on the validity of an image-assisted food and nutrition app

OBJECTIVE

Mobile nutrition applications (apps) provide a simple way for individuals to record their diet, but the validity and inherent errors need to be carefully evaluated. The aim of this study was to assess the validity and clarify the sources of measurement errors of image-assisted mobile nutrition apps.

METHODS

This was a cross-sectional study with 98 students recruited from School of Nutrition and Health Sciences, Taipei Medical University. A 3-d nutrient intake record by Formosa Food and Nutrient Recording App (FoodApp) was compared with a 24-h dietary recall (24-HDR). A two-stage data modification process, manual data cleaning, and reanalyzing of prepackaged foods were employed to address inherent errors. Nutrient intake levels obtained by the two methods were compared with the recommended daily intake (DRI), Taiwan. Paired t test, Spearman's correlation coefficients, and Bland-Altman plots were used to assess agreement between the FoodApp and 24-HDR.

RESULTS

Manual data cleaning identified 166 food coding errors (12%; stage 1), and 426 food codes with missing micronutrients (32%) were reanalyzed (stage 2). Positive linear trends were observed for total energy and micronutrient intake (all Ptrend < 0.05) after the two stages of data modification, but not for dietary fat, carbohydrates, or vitamin D. There were no statistical differences in mean energy and macronutrient intake between the FoodApp and 24-HDR, and this agreement was confirmed by Bland-Altman plots. Spearman's correlation analyses showed strong to moderate correlations (r = 0.834 ∼ 0.386) between the two methods. Participants' nutrient intake tended to be lower than the DRI, but no differences in proportions of adequacy/inadequacy for DRI values were observed between the two methods.

CONCLUSIONS

Mitigating errors significantly improved the accuracy of the Formosa FoodApp, indicating its validity and reliability as a self-reporting mobile-based dietary assessment tool. Dietitians and health professionals should be mindful of potential errors associated with self-reporting nutrition apps, and manual data cleaning is vital to obtain reliable nutrient intake data.

Conventional rehabilitation post-TKA achieves better knee flexion with higher resource utilization compared to application-based rehabilitation - a systematic review and meta-analysis

Background

Post-operative physiotherapy is a major component of the effectiveness of knee replacement. Adequate rehabilitation protocols are required for better functional outcomes. With the advent of smartphones and smartwatches, the use of telerehabilitation has increased recently. This study aims to compare tele rehabilitation using various mobile-based applications to conventional rehabilitation protocols.

Methods

From Jan 2000 to Jun 2022, all the RCTs from SCOPUS, EMBASE and PUBMED comparing patient-related outcome measures between the smartphone-based app and conventional rehabilitation protocols were scanned and seven studies meeting the eligibility criteria were included in this systematic review and meta-analysis. The quantitative analysis compared outcomes using the knee injury and osteoarthritis outcome score (KOOS), the knee society function score (KSFS), the active range of motion (AROM), Euro-Qol-5D-5L, and MUA. The qualitative analysis compared VAS, NRS, and Time up and go (TUG).

Results

The study shows statistically significant improvement in traditional rehabilitation over app based on KSFS score (M.D.: 6.05, p = 0.05) and AROM on long-term follow-up (12 months) (M.D.: 2.46, p = 0.02). AROM was insignificant on 3 months or less follow-up. NRS and VAS were found to be statistically better in app-based groups. No statistically significant results were seen on KOOS, Euro-Qol-5D-5L, MUA and TUG. 90 days of readmission and a number of physiotherapy visits were more in conventional groups. No difference was seen in single-leg stance and satisfaction rates.

Conclusions

The present review highlights improved early pain scores and comparable patient-reported outcome analysis at a short-term follow-up period among patients receiving mobile app-based rehabilitation. However, knee range of motion and KSFS score achieved after surgery is analysed to be better with traditional rehabilitation at the one-year end follow-up period.

Effectiveness of rescue Me CPR! smartphone app providing real-time guidance to untrained bystanders performing CPR

Background

Out-of-hospital cardiac arrest (OHCA) is a persistent global health challenge, owing, in part, to low rates of population CPR training. Smartphone applications have the potential to widely disseminate CPR basic training to a populace, but other studies have found multiple limitations in previously developed CPR guidance applications (CPR-GA). This study aims to use medical simulation to assess the relative CPR performance of novices using the 'Rescue Me CPR!' (RMC) app, a custom CPR-GA designed by this research team, to novices using 'PG-CPR!' (PGC), the most downloaded CPR-GA available in the USA, and to CPR certified medical personnel.

Methods

In a prospective randomized experimental trial of 60 individuals, subjects were either given the RMC app, the PGC app, or had active CPR certification. They were presented a cardio-pulmonary arrest scenario and were observed while performing CPR on a high-fidelity manikin. Data was collected through four cycles of CPR, during which time 24 pertinent performance metrics and CPR steps were timed and recorded. These metrics were assessed on their own and used to calculate average time to compressions, average chest compression fraction, and rate of high-quality CPR for each study group.

Results

CPR certified subjects called 911 in 100 % of simulation cases, started compressions 34 ± 10 s after first seeing the simulated patient, had an average chest compression fraction of 0.52, and performed high-quality CPR in 25 % of aggregate compression cycles. PGC app users called 911 in 70 % of simulation cases, started compressions 86 ± 17 s after first seeing the simulated patient, had an average chest compression fraction that could not be assessed due to inconsistent pauses during CPR, and performed high-quality CPR in 2.5 % of aggregate compression cycles. RMC app users called 911 in 100 % of simulation cases, started compressions 55 ± 6 s after first seeing the simulated patient, had an average chest compression fraction of 0.48, and performed high-quality CPR in 50 % of aggregate compression cycles.

Conclusion

The results of this study demonstrate that in all studied metrics, except time-to-first-compression, CPR provided by individuals using the RMC app is statistically equivalent or superior to CPR performed by a CPR certified individual and, in almost every metric, superior to CPR performed by users of the most downloaded android CPR guidance application, PG-CPR.

Effect of a sensory diet smartphone application on the symptoms of children with attention deficit hyperactivity disorder (ADHD): A feasibility study

Introduction

Sensory integration and sensory diet can improve the symptoms of children with attention deficit/hyperactivity disorder (ADHD). This feasibility study aimed to evaluate the effect of using a sensory diet smartphone application by mothers on the main symptoms of their children with ADHD, including hyperactivity, attention deficit, and impulsivity.

Methods

We conducted a need assessment study with the collaboration of 15 occupational therapists, developed an Android-based prototype, and evaluated it in terms of usability with the participation of 12 available mothers of children with ADHD. 12 other selected children were divided into control and experimental groups. At first, these children were evaluated using the hyperactivity subscale of the fourth version of the Pediatric Symptoms Questionnaire, and after two months of using the application by the mothers of the children in the experimental group, both groups were re-evaluated using the same questionnaire. We compared the mean score of this questionnaire before and after the mothers' use of the application.

Results

The application included 105 sensory diet exercises presented in animated format with accompanying text explanations. According to mothers' feedback, the usability of the application was rated at a high level with an average score of 8.35 out of 9. In the experimental group, attention deficit significantly improved compared to the pre-intervention stage (Mean ± SD = 13.67 ± 6.86 vs. 22 ± 6.13, P-value<0.0001) and compared to the control group after the intervention (P-value = 0.048). Additionally, after the intervention, the experimental group showed significant improvements in impulsivity (mean difference = -1.33) and hyperactivity (mean difference = -4.67) compared to the pre-intervention (P-value = 0.025 and 0.034, respectively). However, these improvements were not statistically significant when compared to the control group (P-value = 0.937 and 0.58, respectively).

Conclusion

The findings suggest that sensory diet smartphone applications have the potential to help alleviate symptoms related to attention deficit in children with ADHD.

The effect of mobile app-based self-care training on the quality of marital relations and the severity of menopausal symptoms in postmenopausal women: a clinical trial study in Iran

BACKGROUND

Educational interventions for self-care are a necessary solution to help postmenopausal women properly deal with menopausal problems. The present study aimed to investigate the effect of self-care training using an application on the quality of marital relations and the severity of menopausal symptoms in postmenopausal women in Iran.

METHODS

In this study, 60 postmenopausal women selected using the convenience sampling method were divided into two groups, intervention and control, using simple random allocation (lottery). The intervention group used the menopause self-care application for eight weeks in addition to routine care, but the control group only received the routine care. The Menopause Rating Scale (MRS) and the Perceived Relationship Quality Components (PRQC) questionnaire were completed in two stages, before and immediately after eight weeks, in both groups. Data were analyzed using SPSS software (version 16), descriptive (mean and standard deviation), and inferential (ANCOVA and Bonferroni post hoc) statistics.

RESULTS

The ANCOVA results showed that the use of the menopause self-care application decreased the severity of the participants' menopause symptoms (P = 0.001) and improved the quality of their marital relations (P = 0.001).

CONCLUSION

Implementation of a self-care training program through the application helped improve the quality of marital relations and reduce the severity of postmenopausal women's symptoms, so it can be used as an effective method to prevent the unpleasant consequences of menopause.

TRIAL REGISTRATION

The present study was registered at https://fa.irct.ir/ on 2021-05-28 (registration number: IRCT20201226049833N1).

Harnessing citizen science to tackle urban-sourced ocean plastic pollution: Experiences and lessons learned from implementing city-wide surveys of plastic litter

Plastic litter is an endemic problem within all regions, particularly cities. Much of this litter reaches the world's oceans with well documented environmental impacts. However, the monitoring of urban litter is often piecemeal at best. Citizen science, the action of utilising the public to support research, has been used to excellent effect for both research and engagement, usually for area clean-ups such as beach cleans. However, to date very few studies have assessed plastic pollution at a city scale. This study presents a novel citizen science approach, using a smartphone application to collect geolocated photographs of plastic litter during 5 city-wide surveys. The study has compiled a significant dataset of photographs (n = 3760), classified by plastic type to assess patterns of plastic pollution Portsmouth, UK. The method is shown to have significant potential for further development to facilitate detailed analysis of plastic litter in urban centres across the world.

Hollow microneedle microfluidic paper-based chip for biomolecules rapid sampling and detection in interstitial fluid

The interstitial fluid (ISF) contains rich bioinformation for disease diagnosis and healthcare monitoring. However, the efficient sampling and detection of the biomolecules in ISF is still challenging. Herein, we develop a facile but versatile ISF analysis platform by combining controllable hollow microneedles (HMNs) and elaborate microfluidic paper-based analytical devices (μPADs). The HMNs and μPADs was fixed in a bottom PDMS layer. A top PDMS layer containing a cylindrical cavity to produce negative pressure for sampling was packaged on the bottom PDMS layer. The HMNs enable efficient and swift sampling of sufficient ISF to the μPADs through one-touch finger operation without extra manipulations. The μPADs realized to simultaneously detect glucose and lactic acid in the detection area to produce chromogenic agents and analyzed by the self-programed RGB application (APP) in smartphones. The HMN microfluidic paper-based chip provides a point-of-care platform for accurate detection of biomolecules in ISF, holding great promise in the development of wearable device.

Efficacy of distance training program for cardiopulmonary resuscitation utilizing smartphone application and home delivery system

AIM OF THE STUDY

Community cardiopulmonary resuscitation (CPR) education is important for laypersons. However, during the COVID-19 pandemic, with social distancing, conventional face-to-face CPR training was unavailable. We developed a distance learning CPR training course (HEROS-Remote) using a smartphone application that monitors real-time chest compression quality and a home delivery collection system for mannikins. This study aimed to evaluate the efficacy of the HEROS-Remote course by comparing chest compression quality with that of conventional CPR training.

METHODS

We applied layperson CPR education with HEROS-Remote and conventional education in Seoul during the COVID-19 pandemic. Both groups underwent a 2-min post-training chest compression test, and we tested non-inferiority. Chest compression depth, rate, complete recoil, and composite chest compression score was measured. Trainees completed a satisfaction survey on CPR education and delivery. The primary outcome was the mean chest compression depth.

RESULTS

A total of 180 trainees were enrolled, with 90 assigned to each training group. Chest compression depth of HEROS-Remote training showed non-inferiority to that of conventional training (67.4 vs. 67.8, p = 0.78), as well as composite chest compression score (92.7 vs. 95.5, p = 0.16). The proportions of adequate chest compression depth, chest compression rate, and chest compressions with complete chest recoil were similar in both training sessions. In the HEROS-Remote training, 90% of the trainees were satisfied with CPR training, and 96% were satisfied with the delivery and found it convenient.

CONCLUSION

HEROS-Remote training was non-inferior to conventional CPR training in terms of chest compression quality. Distance learning CPR training using a smartphone application and mannikin delivery had high user satisfaction and was logistically feasible.

Quality of recovery after day care surgery with app-controlled remote monitoring: study protocol for a randomized controlled trial

BACKGROUND

The majority of surgical interventions are performed in day care and patients are discharged after the first critical postoperative period. At home, patients have limited options to contact healthcare providers in the hospital in case of severe pain and nausea. A smartphone application for patients to self-record pain and nausea when at home after day care surgery might improve patient's recovery. Currently patient experiences with smartphone applications are promising; however, we do not know whether remote monitoring with such an application also improves the patient's recovery. This study aims to evaluate the experienced quality of recovery after day care surgery between patients provided with the smartphone application for remote monitoring and patients receiving standard care without remote monitoring.

METHODS

This non-blinded randomized controlled trial with mixed methods design will include 310 adult patients scheduled for day care surgery. The intervention group receives the smartphone application with text message function for remote monitoring that enables patients to record pain and nausea. An anaesthesia professional trained in empathetic communication, who will contact the patient in case of severe pain or nausea, performs daily monitoring. The control group receives standard care, with post-discharge verbal and paper instructions. The main study endpoint is the difference in perceived quality of recovery, measured with the QoR-15 questionnaire on the 7th day after day care surgery. Secondary endpoints are the overall score on the Quality of Recovery-15 at day 1, 4 and 7-post discharge, the perceived quality of hospital aftercare and experienced psychological effects of remote monitoring during postoperative recovery from day care surgery.

DISCUSSION

This study will investigate if facilitating patients and healthcare professionals with a tool for accessible and empathetic communication might lead to an improved quality of the postoperative recovery period.

TRIAL REGISTRATION

The 'Quality of recovery after day care surgery with app-controlled remote monitoring: a randomized controlled trial' is approved and registered on 23 February 2022 by Research Ethics Committees United with registration number R21.076/NL78144.100.21. The protocol NL78144.100.21, 'Quality of recovery after day care surgery with app-controlled remote monitoring: a randomized controlled trial', is registered at the ClinicalTrials.gov public website (registration date 16 February 2022; NCT05244772).

Evaluation of a smartphone application for self-rehabilitation after anterior cruciate ligament reconstruction during a COVID-19 lockdown

BACKGROUND

Rehabilitation after surgery is a crucial process that governs the final functional outcome. The self-rehabilitation smartphone application Doct'up (Healing SAS, Lyon, France) is designed for patients who have had anterior cruciate ligament (ACL) reconstruction surgery. In France in the spring of 2020, the lockdown mandated due to the COVID-19 pandemic prevented patients from seeing their physiotherapists for 2 months. The objective of this study was to compare the clinical outcomes in two groups of patients who underwent ACL reconstruction surgery: in one group, surgery performed before the lockdown was followed by standard in-person physiotherapy while, in the other, surgery was done just before the lockdown and rehabilitation was performed by the patients themselves using the phone application.

HYPOTHESIS

Using a self-rehabilitation smartphone app limits the negative effects of not receiving physiotherapist rehabilitation after ACL reconstruction.

MATERIAL AND METHODS

We performed a case-control study involving the retrospective analysis of prospectively collected data from two groups of patients who had undergone ACL reconstruction surgery. Patients in the App group had surgery just before the 2-month COVID-19-related lockdown that started in France on March 17, 2020,and used only the smartphone app for rehabilitation. The standard-care group was composed of matched controls who had surgery 1 year before the cases and received rehabilitation therapy during in-person physiotherapist visits. The ACL reconstruction technique was the same in the two groups. The primary outcome measure was extension lag 6 weeks after surgery. The secondary outcome measures were extension lag 3 weeks and 6 months after surgery, quadriceps muscle activation, knee extension locking 3 and 6 weeks after surgery, and the 6-month rate of surgical revision for cyclops syndrome.

RESULTS

We included 32 cases managed using only self-rehabilitation guided by the phone app, and we identified 101 matched controls managed using standard care. We found no significant between-group difference in extension lag after 6 weeks: 9.4% (28/32) vs. 4.6% (87/101), p=0.39. After 3 weeks, the App group had a higher proportions of patients with quadriceps activation (94% [30/32] vs. 73% [74/101], p=0.015) and extension control using canes (78.1% [25/32] vs. 40.6% [41/101], p=0.0002). None of the other measured outcomes differed significantly between the two groups (extension lag after 3 weeks: 12.5% [4/32] vs. 13.8% 14/101]; extension lag after 6 months: 3.2% [1/32] vs. 1% [1/101]; quadriceps activation after 6 weeks: 97% [31/32] vs. 99% [100/101]; extension locking with canes after 6 weeks: 96.9% [31/32] vs. 93.1% [94/101]; extension locking without canes after 3 weeks: 53.2% [17/32] vs. 47.5% [48/101]; extension locking without canes after 6 weeks: 93.7% [30/32] vs. 82.2% [83/101]; and surgery for cyclops syndrome (3.1% [1/32] vs. 1% [1/101]).

DISCUSSION

The use of a self-rehabilitation phone app after ACL reconstruction during a COVID-19 lockdown limited the adverse effects of not receiving in-person physiotherapy. The 6-month outcomes were similar to those seen with standard rehabilitation. The study results demonstrate the usefulness of self-rehabilitation after ACL reconstruction surgery. Self-rehabilitation guided by a phone app could be used as a complement to the protocols generally applied by physiotherapists.

LEVEL OF EVIDENCE

IV, single-centre retrospective case-control study.

Prognostic factors and effect modifiers for personalisation of internet-based cognitive behavioural therapy among university students with subthreshold depression: A secondary analysis of a factorial trial

BACKGROUND

Internet-cognitive behavioural therapy (iCBT) for depression can include multiple components. This study explored depressive symptom improvement prognostic factors (PFs) and effect modifiers (EMs) for five common iCBT components including behavioural activation, cognitive restructuring, problem solving, self-monitoring, and assertion training.

METHODS

We used data from a factorial trial of iCBT for subthreshold depression among Japanese university students (N = 1093). The primary outcome was the change in PHQ-9 scores at 8 weeks from baseline. Interactions between each component and various baseline characteristics were estimated using a mixed-effects model for repeated measures. We calculated multiplicity-adjusted p-values at 5 % false discovery rate using the Benjamini-Hochberg procedure.

RESULTS

After multiplicity adjustment, the baseline PHQ-9 total score emerged as a PF and exercise habits as an EM for self-monitoring (adjusted p-values <0.05). The higher the PHQ-9 total score at baseline (range: 5-14), the greater the decrease after 8 weeks. For each 5-point increase at baseline, the change from baseline to 8 weeks was bigger by 2.8 points. The more frequent the exercise habits (range: 0-2 points), the less effective the self-monitoring component. The difference in PHQ-9 change scores between presence or absence of self-monitoring was smaller by 0.94 points when the participant exercised one level more frequently. Additionally, the study suggested seven out of 36 PFs and 14 out of 160 EMs examined were candidates for future research.

LIMITATIONS

Generalizability is limited to university students with subthreshold depression.

CONCLUSIONS

These results provide some helpful information for the future development of individualized iCBT algorithms for depression.

Comparing the effects of self- care education by lecture and smartphone application on self-efficacy of patients with thalassemia

BACKGROUND

Patients with the thalassemia have a basic requirement for self-efficacy regarding their treatment procedure. The present study aimed to compare the effect of self-care education via a smartphone application and lectures on the self-efficacy of patients with thalassemia.

METHODS

In the present quasi-experimental study, 99 patients with thalassemia at Shahid Beheshti Hospital in Yasuj, Iran, in 2019 who were eligible to enter the study, were selected. The block randomization was done with the block sizes of 3, 6, and 9, and participants were randomly assigned to 3 groups: smartphone application (A), lecture intervention (B), and control (c). Smartphone application and lecture interventions were performed for intervention groups A and B, respectively, during 8 weeks. Scherer's self-efficacy measure was used to collect the data at baseline and eight weeks after the intervention. Data were analyzed by SPSS-version 25 software using Paired t-test, Wilcoxon and Kruskal-Wallis tests.

RESULTS

Ninety-nine patients with thalassemia with a mean (SD) age of 25 (6) and 58 females (58.59%) participated in the present study. The results indicated a significant difference in self-efficacy among 3 groups after intervention (P = 0.001). However, self-care education with smartphone application revealed a significant increase in the mean (SD) of self-efficacy of the patients with thalassemia 68.36(8.45) compared to the lecture method 62.55 (7.3) (P = 0.003) and control 62.09 (6.7) (P = 0.001). There were no significant differences among the self-efficacy scores of the patients in lecture intervention and control groups.

CONCLUSIONS

The results revealed that smartphone application was a suitable educational software to promote self-efficacy in patients with thalassemia. It is recommended to use smartphone application methods to improve the self-efficacy levels of patients with thalassemia.

Patient-level performance evaluation of a smartphone-based malaria diagnostic application

BACKGROUND

Microscopic examination is commonly used for malaria diagnosis in the field. However, the lack of well-trained microscopists in malaria-endemic areas impacted the most by the disease is a severe problem. Besides, the examination process is time-consuming and prone to human error. Automated diagnostic systems based on machine learning offer great potential to overcome these problems. This study aims to evaluate Malaria Screener, a smartphone-based application for malaria diagnosis.

METHODS

A total of 190 patients were recruited at two sites in rural areas near Khartoum, Sudan. The Malaria Screener mobile application was deployed to screen Giemsa-stained blood smears. Both expert microscopy and nested PCR were performed to use as reference standards. First, Malaria Screener was evaluated using the two reference standards. Then, during post-study experiments, the evaluation was repeated for a newly developed algorithm, PlasmodiumVF-Net.

RESULTS

Malaria Screener reached 74.1% (95% CI 63.5-83.0) accuracy in detecting Plasmodium falciparum malaria using expert microscopy as the reference after a threshold calibration. It reached 71.8% (95% CI 61.0-81.0) accuracy when compared with PCR. The achieved accuracies meet the WHO Level 3 requirement for parasite detection. The processing time for each smear varies from 5 to 15 min, depending on the concentration of white blood cells (WBCs). In the post-study experiment, Malaria Screener reached 91.8% (95% CI 83.8-96.6) accuracy when patient-level results were calculated with a different method. This accuracy meets the WHO Level 1 requirement for parasite detection. In addition, PlasmodiumVF-Net, a newly developed algorithm, reached 83.1% (95% CI 77.0-88.1) accuracy when compared with expert microscopy and 81.0% (95% CI 74.6-86.3) accuracy when compared with PCR, reaching the WHO Level 2 requirement for detecting both Plasmodium falciparum and Plasmodium vivax malaria, without using the testing sites data for training or calibration. Results reported for both Malaria Screener and PlasmodiumVF-Net used thick smears for diagnosis. In this paper, both systems were not assessed in species identification and parasite counting, which are still under development.

CONCLUSION

Malaria Screener showed the potential to be deployed in resource-limited areas to facilitate routine malaria screening. It is the first smartphone-based system for malaria diagnosis evaluated on the patient-level in a natural field environment. Thus, the results in the field reported here can serve as a reference for future studies.

The effectiveness of designing and evaluating i-STAR applications in pediatric nursing courses

To apply the App to the curriculum could improve students' motivation and concentration, and also strengthen the effectiveness of professional knowledge of nursing students.

OBJECTIVES

To construct and evaluate the effectiveness of smartphone applications (i-STAR) in pediatric nursing courses.

METHODS

Quasi-experimental study and two-group repeated-measure design were used to evaluate the effectiveness of smartphone applications (i-STAR) in pediatric nursing courses. The "i" means "interactive", students had to log into App and finish four steps, including "Situation(S), Task(T), Action(A), and Reflection(R). A total of 163 nursing students in the third grade of associate's degree in nursing (ADN) participated in the study. The experimental group consisted of 77 participants, whereas the control group consisted of 86 participants. The instruments included the clinical reasoning readiness scale (CRRS), self-directed learning instrument (SDLI), and learning satisfaction of students. The 1st phase was the development, construction, and testing of the "i-STAR App", including hyperbilirubinemia, pneumonia, and urinary tract infection (UTI). In the 2nd phase, students operated and applied the App in the classroom. The 3rd phase was to evaluate the effectiveness of the "i-STAR App" in the course.

RESULTS

The average scores of CRRS and SDLI were not significantly different between the two groups in the T0 andT1 (p > .05). The experimental group of CRRS and SDLI were better than the control group in T0-T1, T1-T2, and T0-T2 (p < .001). The experimental group showed better CRRS and SDLI scores than the control group in T0-T1, and T0-T2 with Repeated measures ANOVA. Also, the experimental group showed prolonged learning effectiveness. The experimental group (41.22 ± 6.08) was more satisfied than the control group (37.29 ± 7.40) (p < .05), although their academic performance was about the same (p > .05).

CONCLUSION

"i-STAR App" could enhance students' interest in pediatric nursing courses, strengthen nursing students' clinical reasoning and self-directed learning ability.

Development of a mobile application to improve exercise accuracy and quality of life in knee osteoarthritis patients: a randomized controlled trial

INTRODUCTION

Knee Osteoarthritis (OA) is a degenerative joint disease that needs consistent exercise and an accurate understanding of the condition for long-term maintenance. While the accessibility of outpatient care is essential for disease management, many patients lack the resources to receive adequate healthcare. To address this challenge, we developed a not-for-profit interactive mobile application that provides a disease-specific educational background and a structured exercise regimen to patients.

MATERIAL AND METHODS

"Rak Kao" (English translation: Love-Your-Knee) mobile application was designed to analyze the questionnaire data to assess the stage of knee OA and generate a personalized recommendation of treatment and exercise type using rule-based and Artificial Intelligence (AI) techniques. A single-blinded study was conducted with patients (n = 82) who were randomly assigned to the mobile application group (M-group) and the handout group (H-group). Patient groups were controlled for age, gender, BMI, onset of pain, grade of disease, education level, and occupation. Accuracy in performance of three prescribed knee exercises (catch-bend-down, stretch-touch-feet, and sit-stretch-hold) was evaluated. Clinical outcomes were evaluated before and after the 4-weeks program to assess the range of motion, symptoms, pain, physical activity, and quality of life via the KOOS and KSS scores.

RESULTS

Completion of the study led to significantly more overall exercise accuracy in the M-group (76.2%) than the H-group (52.5%). Activities of daily life, quality of life, ability to do sports and recreational activities were significantly more improved in the M-group than the H-group (p < .01). No difference in the range of motion between groups. Satisfaction of patients' experience was higher in the M-group than the H-group (p = .001) after the 4-week regimen.

CONCLUSIONS

With the better accuracy and outcomes for rehabilitation in the M-group than the H-group, we strongly recommend using our mobile application as a better alternative than handouts for exercises and information for patients with knee OA.

TRIAL REGISTRATION

ClinicalTrials.gov: NCT03666585.

A future orientation intervention delivered through a smartphone application and virtual reality: study protocol for a randomized controlled trial

BACKGROUND

Short-term mindsets are associated with self-defeating behaviors, such as delinquency and alcohol use. In contrast, people who consider the longer-term consequences of their decisions tend to report positive outcomes, like feeling more competent and enhanced goal achievement. We evaluate an intervention, FutureU, that aims to stimulate future-oriented thinking, increase goal achievement, and reduce self-defeating behavior, by strengthening people's identification with their future self. The intervention will be delivered through a smartphone application (app) or immersive Virtual Reality (VR). We test the effectiveness of FutureU for both delivery methods, examine working mechanisms, and identify potential moderators of intervention effects.

METHODS

In this Randomized Controlled Trial, a total of 240 first-year university students (n = 80 per condition) will be randomized into one of three conditions: (1) a smartphone condition, (2) a VR condition, and (3) an active control condition. We will assess proximal (i.e., future self-identification) and distal intervention outcomes (e.g., future orientation, self-defeating behaviors, goal achievement), user engagement, and examine usage data and goal content. Assessments will take place at baseline, during the intervention, immediately after the intervention, and at 3- and 6-months follow-up.

DISCUSSION

This study will provide information on the effectiveness of the intervention and allows for comparisons between delivery methods using novel technologies, a smartphone app versus immersive VR. Knowledge gained through this study can be used for further intervention development as well as theory building. Trial registration This trial is registered on Clinicaltrials.gov (NCT05578755) on 13 October 2022.

Pre-partum HRV as a predictor of postpartum depression: The potential use of a smartphone application for physiological recordings

BACKGROUND

This study aimed to investigate the role of a time-domain Heart Rate Variability index (the root mean square of successive difference between NN intervals, rMSSD) as a predictor of the onset of postpartum depression. HRV has been related to an increased risk of depression in the general population. However, its role in pregnant women is not clear, and the potential use of smartphone applications to evaluate HRV in this population has not been investigated.

METHODS

In study 1, simultaneous electrocardiogram and smartphone photoplethysmography were collected. The rMSSD was determined from each recording to evaluate the accuracy of a smartphone application in the measurement of HRV. In study 2, 135 pregnant women provided rMSSD values measured through a smartphone application in the prepartum (second or third trimester) and filled in the Edinburgh Postnatal Depression Scale in the postpartum (one month after the childbirth).

RESULTS

Study 1 showed the excellent accuracy of the smartphone application in the measurement of rMSSD. Study 2 indicated that lower prepartum rMSSD predicted higher depressive symptoms in the postpartum (β = -0.217, p = 0.010) after controlling for prepartum depressive symptoms and other potential covariates.

LIMITATIONS

Artefacts (e.g., hand movements) might have corrupted the physiological signal registered.

CONCLUSION

This study showed that a reduced vagal tone, indexed by lower rMSSD, during pregnancy was a predictor of depressive symptoms one month after childbirth. The prepartum period may offer an important timeframe to implement preventive intervention on vagal modulation in order to prevent depressive symptoms in the postpartum.

Identification of preferred reminder systems and patient factors to promote adherence in the management of urinary incontinence

Objective

To investigate comfort level and preferences of automated reminder systems (mail, email, text message, phone call, patient-portal message, and/or smartphone application) to promote adherence to recommended therapies for patients seeking care for urinary incontinence (UI) at our urology clinic in Phoenix, Arizona.

Methods

Anonymous surveys were distributed in English to adult patients with UI from 4/2019-5/2019. Patient demographics, UI type, and access to and use of the Internet, smartphone and patient-portal were assessed. Using a Likert scale, patients indicated level of comfort with each reminder system and numerically ranked each system. Statistical analyses were performed to identify patient characteristics associated with reminder modality and determine significance in ranking of systems.

Results

Fifty-seven patients (67.3 ± 16.3 years) completed the survey with an 87% response rate. Text-message and phone call reminder modalities were ranked the highest compared to other modalities (p < 0.05). A Chi-squared test showed no correlation between preferred reminder system modality and type of incontinence, age, gender, race/ethnicity, or language spoken (p > 0.05). Internet usage and access significantly correlated with preference for smartphone application and patient-portal message reminder systems (p < 0.05).

Conclusion

Patients reported they were extremely comfortable with all communication modalities, except for smartphone applications in which patients were the least comfortable. The modalities most preferred by patients were phone call and text message and least preferred were patient portal and smart phone application. In conclusion, phone calls and text messages were the most preferred communication modality, with smart phone applications as the least comfortable.

Innovation

This study demonstrates the potential utility of specific reminder modalities for patients seeking help with treatment adherence.

A qualitative exploration of perceived needs and barriers of individuals with schizophrenia, caregivers and clinicians in using mental health applications in Madhya Pradesh, India

Introduction

About 3.5 million people are living with schizophrenia in India, with most failing to receive minimally adequate care. Digital mental health applications could potentially decrease this treatment gap; however, these applications should be tailored to meet the needs and overcoming barriers of its end-users to ensure their adoption and sustained usage. Few studies in India have explored the perspectives of target stakeholders to understand how digital tools could be viable for supporting care. Therefore, this study explores the perceived needs and barriers of patients with schizophrenia, caregivers and clinicians in using digital mental health applications.

Methods

Focus group discussions (FGDs) were conducted with patients having schizophrenia attending outpatient clinics at a government tertiary hospital, and their caregivers, and mental health clinicians in Bhopal, Madhya Pradesh, India. FGDs were audio-recorded and coded. Framework analysis was employed to guide the analysis, involving deductive and inductive generation of themes, data triangulation and comparison of perspectives between participant groups.

Results

Six FGDs were conducted with individuals with schizophrenia (n ​= ​11), their caregivers (n ​= ​14), and mental health clinicians (n ​= ​19). Four a priori themes were established: a) Prior experiences with health applications; b) Content of a mental health application; c) Involvement of caregivers in mental health application usage and d) Supporting doctors' work through mental health applications. Additionally, two themes were generated inductively: a) Qualities of a mental health application and b) Data privacy and confidentiality.

Conclusion

Exploration of stakeholder perspectives on the content, features, and uses of mental health applications is crucial to yield initial insights about the use of these digital programs in India. This study generated a multitude of suggestions on app functionality and components, which can guide ongoing efforts to develop and deliver digital mental health applications for patients living with schizophrenia in low-resource settings, with limited access to mental health services.

Mobile Phone Applications Voice Tools and Voice Pitch Analyzer Validated With LingWAVES to Measure Voice Frequency

OBJECTIVES

Voice frequency can be measured to assess the voice change in transgender men and women during treatment. There are many applications that can analyze voice frequency. This validation study aimed to compare the ability to measure voice frequency of the mobile phone applications "Voice Tools" and "Voice Pitch Analyzer" with the registration program LingWAVES as the gold standard.

STUDY DESIGN

Prospective validation study.

METHODS

A total of 45 participants of whom 20 transgender individuals were included. They were asked to read "The North Wind and the Sun" twice. The first measurement compared voice frequency measured by Voice Tools with LingWAVES while the second measurement compared Voice Pitch Analyzer with LingWAVES. The two applications that were being compared simultaneously measured the voice frequency. Pearson's regression correlations were performed to test for correlation between the mobile phone applications and LingWAVES.

RESULTS

Significant correlations were demonstrated between the measurements of Voice Tools and LingWAVES (P < 0.001) and between Voice Pitch Analyzer and LingWAVES (P < 0.001). Voice Tools overestimated voice frequency with a median deviation of 2Hz (range -4 to 20). The overestimation was more pronounced in the high ranges. Voice Pitch Analyzer showed underestimation of voice frequency in high ranges. Median deviation was -2Hz (range -16 to 14).

CONCLUSIONS

This validation study shows that voice frequency can be reliably measured with the mobile phone applications "Voice Tools" and "Voice Pitch Analyzer". Combined with the ease of use, these applications can be used to measure voice frequency in clinical practice and for research purposes.

Patient and public involvement in mobile health-based research for hay fever: a qualitative study of patient and public involvement implementation process

BACKGROUND

Smartphones are being increasingly used for research owing to their multifunctionality and flexibility, and crowdsourced research using smartphone applications (apps) is effective in the early detection and management of chronic diseases. We developed the AllerSearch app to gather real-world data on individual subjective symptoms and lifestyle factors related to hay fever. This study established a foundation for interactive research by adopting novel, diverse perspectives accrued through implementing the principles of patient and public involvement (PPI) in the development of our app.

METHODS

Patients and members of the public with a history or family history of hay fever were recruited from November 2019 to December 2021 through a dedicated website, social networking services, and web briefing according to the PPI Guidebook 2019 by the Japan Agency for Medical Research and Development. Nine opinion exchange meetings were held from February 2020 to December 2021 to collect opinions and suggestions for updating the app. After each meeting, interactive evaluations from PPI contributors and researchers were collected. The compiled suggestions were then incorporated into the app, establishing an active feedback loop fed by the consistently interactive infrastructure.

RESULTS

Four PPI contributors (one man and three women) were recruited, and 93 items were added/changed in the in-app survey questionnaire in accordance with discussions from the exchange meetings. The exchange meetings emphasized an atmosphere and opportunity for participants to speak up, ensuring frequent opportunities for them to contribute to the research. In March 2020, a public website was created to display real-time outcomes of the number of participants and users' hay-fever-preventative behaviors. In August 2020, a new PPI-implemented AllerSearch app was released.

CONCLUSIONS

This study marks the first research on clinical smartphone apps for hay fever in Japan that implements PPI throughout its timeline from research and development to the publication of research results. Taking advantage of the distinct perspectives offered by PPI contributors, a step was taken toward actualizing a foundation for an interactive research environment. These results should promote future PPI research and foster the establishment of a social construct that enables PPI efforts in various fields.

Parents can reliably and accurately detect trunk asymmetry using an inclinometer smartphone app

PURPOSE

An inclinometer smartphone application has been developed to enable the measurement of the angle of trunk inclination (ATI) to detect trunk surface asymmetry. The objective was to determine the reliability and validity of the smartphone app in the hands of non-professionals.

METHODS

Three non-professional observers and one expert surgeon measured maximum ATI twice in a study involving 69 patients seen in the spine clinics to rule out scoliosis or for regular follow-up (10-18 y.o., Cobb [0°-58°]). Observers were parents not familiar with scoliosis screening nor use of an inclinometer. They received training from a 4-minute video. Intra and inter-observer reliability was determined using the generalizability theory and validity was assessed from intraclass correlation coefficients (ICC), agreement with the expert on ATI measurements using Bland-Altman analysis, and correct identification of the threshold for consultation (set to ≥6° ATI).

RESULTS

Intra-observer and inter-observer reliability coefficients were excellent ϕ = 0.92. The standard error of measurement was 1.5° (intra-observer, 2 measurements) meaning that a parent may detect a change of 4° between examinations 95% of the time. Comparison of measurements between non-professionals and the expert resulted in ICC varying from 0.82 [0.71-0.88] to 0.84 [0.74-0.90] and agreement on the decision to consult occurred in 83 to 90% of cases.

CONCLUSION

The use of a smartphone app resulted in excellent reliability, sufficiently low standard error of measurement (SEM) and good validity in the hands of non-professionals. The device and the instructional video are adequate means to allow detection and regular examination of trunk asymmetries by non-professionals.

Clinical feasibility of the Q1.6 Inguinal Hernia application: a prospective cohort study

PURPOSE

Patient-reported outcomes (PROs) are essential to evaluate inguinal hernia surgery. There is a need for digital and disease-specific PRO measurement. Current measuring instruments (PROMs) have several disadvantages, for example, fixed measuring moments with a chance of recall bias. The Q1.6 Inguinal Hernia application has been developed to overcome these challenges. This pilot study reports the first clinical feasibility results.

METHODS

All surgically treated inguinal hernia patients were eligible for inclusion. The application uses "twitch crowdsourcing"; after unlocking a smartphone or tablet, a single short question is asked. This can easily be repeated multiple times a day/week/month. Questions from validated questionnaires were implemented. The adaptive question engine generates an individualised set of questions. Alerts are generated when a complication is suspected.

RESULTS

A total of 229 patients were given over 50.000 questions of which 92% were answered. Pre- and postoperative patient characteristics and their reported clinical outcomes confirmed a standard inguinal hernia population. Compliance with the application was 91.7% after 14 days, 69.0% after 3 months and 28.8% after one year. After months 3, 6 and 11, respectively, 3.0%, 4.4% and 4.5% of patients reported inguinal pain or discomfort (NRS ≥ 4). Patients were highly satisfied (92.8% preferred the app over standard care).

CONCLUSIONS

This smartphone application shows promising results for clinical practice. It might allow for continuous digital patient-reported outcome measurement using non-intrusive, concise questions. Remote monitoring may become standard postoperative care after (inguinal hernia) surgery. The current application will be further improved and evaluated for cost-effectiveness, safety and validity.

Validity and reliability of a smartphone-based assessment for anticipatory and compensatory postural adjustments during predictable perturbations

BACKGROUND

Postural adjustments involve displacements of the center of mass (COM), controlled by the central nervous system (CNS), to maintain equilibrium whilst standing. Postural adjustments can be anticipatory (APAs) or compensatory (CPAs), and are triggered to counteract predictable perturbations.

RESEARCH QUESTION

Is the new smartphone application, Momentum, a valid and reliable tool for the assessment of body balance, by measuring APAs and CPAs using accelerometer readings?

METHODS

20 young adults were exposed to external predictable perturbations induced at the shoulder level, whilst standing. COM linear acceleration was recorded by Momentum (extracting data from a smartphone's accelerometer) and a 3D motion capture system.

RESULTS

The key results demonstrated a very high, significant correlation (r ≥ 0.7, p < 0.05) between the two device settings in the APA parameters_, which obtained r = 0.65, denoting a high correlation. Considering the reliability, variables that are compensatory in nature are presented on a scale of good to excellent in measurement methods, kinematics, and Momentum. However, the anticipatory variables presented excellent reliability only for the kinematics.

SIGNIFICANCE

These experiments show that Momentum is a valid method for measuring COM acceleration under predictable perturbations and is reliable for compensatory events.

Design and Methods of a Prospective Smartphone App-Based Study for Digital Phenotyping of Mood and Anxiety Symptoms Mixed With Centralized and Decentralized Research Form: The Search Your Mind (S.Y.M., ) Project

In this study, the Search Your Mind (S.Y.M., ) project aimed to collect prospective digital phenotypic data centered on mood and anxiety symptoms across psychiatric disorders through a smartphone application (app) platform while using both centralized and decentralized research designs: the centralized research design is a hybrid of a general prospective observational study and a digital platform-based study, and it includes face-to-face research such as informed written consent, clinical evaluation, and blood sampling. It also includes digital phenotypic assessment through an application-based platform using wearable devices. Meanwhile, the decentralized research design is a non-face-to-face study in which anonymous participants agree to electronic informed consent forms on the app. It also exclusively uses an application-based platform to acquire individualized digital phenotypic data. We expect to collect clinical, biological, and digital phenotypic data centered on mood and anxiety symptoms, and we propose a possible model of centralized and decentralized research design.

A smartphone application of diabetes coaching intervention to prevent the onset of complications and to improve diabetes self-management: A randomized control trial

BACKGROUND AND AIM

Diabetes mellitus (DM) has been a worldwide public health problem during the last two decades. To examine the effect of a smartphone application of diabetes coaching intervention on improving self-management behaviors and preventing onset diabetes complications.

METHODS

A randomized control trial, two groups, pre-test, and post-test design with a non-equivalent control group was conducted. The intervention group received a 12-week smartphone application of diabetes coaching intervention to improve diabetes self-management behaviors and to prevent onset diabetes complications. While the control group received the usual care from the community health centers. The smartphone application consisted of narrative App-based coaching, a printed user guide, mindfulness-based coaching; skill-based coaching, and a small App-interaction.

RESULTS

After implementation, the self-management behaviors among the experimental group were improved than the control group in terms of dietary control, physical exercise, blood glucose monitoring, medication adherence, and screening of complications. The clinical outcomes were also significantly improved among the experimental group and to the control group.

CONCLUSIONS

A smartphone application-based diabetes coaching intervention was feasible to apply as a nationwide program to promote diabetes self-management (DSM) during the covid-19 pandemic.

Effects of a smartphone application named "Shared Decision Making Assistant" for informed patients with primary liver cancer in decision-making in China: a quasi-experimental study

BACKGROUND

It is well known that decision aids can promote patients' participation in decision-making, increase patients' decision preparation and reduce decision conflict. The goal of this study is to explore the effects of a "Shared Decision Making Assistant" smartphone application on the decision-making of informed patients with Primary Liver Cancer (PLC) in China.

METHODS

In this quasi-experimental study , 180 PLC patients who knew their real diagnoses in the Eastern Hepatobiliary Surgery Hospital, Naval Medical University, Shanghai, China, from April to December 2020 were randomly assigned to a control group and an intervention group. Patients in the intervention group had an access to the "Shared Decision Making Assistant" application in decision-making, which included primary liver cancer treatment knowledge, decision aids path, continuing nursing care video clips, latest information browsing and interactive platforms. The study used decision conflict scores to evaluate the primary outcome, and the data of decision preparation, decision self-efficacy, decision satisfaction and regret, and knowledge of PLC treatment for secondary outcomes. Then, the data were entered into the SPSS 22.0 software and were analyzed by descriptive statistics, Chi-square, independent t-test, paired t-test, and Mann-Whitney tests.

RESULTS

Informed PLC patients in the intervention group ("SDM Assistant" group) had significantly lower decision conflict scores than those in the control group. ("SDM Assistant" group: 16.89 ± 8.80 vs. control group: 26.75 ± 9.79, P < 0.05). Meanwhile, the decision preparation score (80.73 ± 8.16), decision self-efficacy score (87.75 ± 6.87), decision satisfaction score (25.68 ± 2.10) and knowledge of PLC treatment score (14.52 ± 1.91) of the intervention group were significantly higher than those of the control group patients (P < 0.05) at the end of the study. However, the scores of "regret of decision making" between the two groups had no statistical significance after 3 months (P > 0.05).

CONCLUSIONS

Access to the "Shared Decision Making Assistant" enhanced the PLC patients' performance and improved their quality of decision making in the areas of decision conflict, decision preparation, decision self-efficacy, knowledge of PLC treatment and satisfaction. Therefore, we recommend promoting and updating the "Shared Decision Making Assistant" in clinical employment and future studies.

Cost-effectiveness of a smartphone Application for Tinnitus Treatment (the CATT trial): a study protocol of a randomised controlled trial

BACKGROUND

Tinnitus is a highly prevalent symptom, affecting 10-15% of the adult population. Tinnitus influenced by alterations in somatosensory afference from the neck or jaw is referred to as somatic tinnitus (ST). ST is known to respond positively to physiotherapy treatment; however, it is challenging to motivate patients to systematically perform home exercises correctly, and the necessary tinnitus counselling is often lacking. The aim of this study is twofold, namely to investigate both the effectiveness and cost-effectiveness of a blended physiotherapy program for ST, including a smartphone application designed to increase exercise therapy compliance and provide tinnitus counselling.

METHODS

This study is designed as a single-blind two-arm 1:1 randomised controlled trial (RCT). Adult patients diagnosed with ST, without psychiatric comorbidities and with experience in using a smartphone, will be recruited at the Ear Nose Throat (ENT) department of the Antwerp University Hospital (UZA). Patients will be randomised into two groups. The experimental group will receive the blended physiotherapy program comprising six in-clinic physiotherapy sessions over a period of 12 weeks (1x/2 weeks) and an exercise and counselling program provided by the smartphone application. The control group will receive the standard care program comprising twelve weekly in-clinic physiotherapy sessions. Each physiotherapy session has a duration of 30 min. The primary outcome measure is the change in Tinnitus Functional Index (TFI) score. Additionally, a cost-effectiveness analysis will be performed from a societal perspective considering both direct and indirect costs. There will be follow-up assessments at one and 3 months after the final treatment session.

DISCUSSION

Our study is the first to combine both tinnitus counselling and neck/jaw treatment provided by a digital application in a blended physiotherapy program. This, in order to empower ST patients to improve and better manage their own health and, possibly, reduce economic costs by alleviating the tinnitus burden that ST patients experience. The strengths of the planned RCT are the high-quality methodological design, the large sample size and the expertise of the involved multidisciplinary research team.

TRIAL REGISTRATION

Clinicaltrials.gov NCT05245318 . Registered on 26 January 2022.

Comparative effectiveness of smartphone healthcare applications for improving quality of life in lung cancer patients: study protocol

BACKGROUND

Although pulmonary rehabilitation is helpful for patients following lung cancer surgery, rehabilitation is not widely available, due in part to a lack of medical resources. Recent developments in digital health care have overcome the space limitations associated with in-person health care. This study will evaluate and compare the efficacy of three different smartphone healthcare systems in patients with lung cancer.

METHODS

This single center randomized controlled study is designed to evaluate the efficacy of digital healthcare applications for lung cancer patients after thoracoscopic lung resection. A total of 320 patients will be enrolled and randomized 1:1:1:1 into four different groups, with one group each using the smartphone applications NOOM, Walkon, and Efilcare and the fourth being the control group without intervention. Questionnaires will be administered to patients at baseline and after 3, 6, and 12 months. The primary endpoint will be the score on the EuroQol five-dimension index. Secondary endpoints will include other questionnaires about quality of life and dyspnea.

DISCUSSION

This prospective randomized controlled study may allow assessments and comparisons of the efficacy of various smartphone applications in patients who undergo lung cancer surgery. This process may enable the introduction of healthcare interventions that maintain quality of life in patients with lung cancer. Trial registration CRIS, KCT0005447. Registered 06 October 2020, https://cris.nih.go.kr/cris/search/detailSearch.do/19346.

DryEyeRhythm: A reliable and valid smartphone application for the diagnosis assistance of dry eye

PURPOSE

Undiagnosed or inadequately treated dry eye disease (DED) decreases the quality of life. We aimed to investigate the reliability, validity, and feasibility of the DryEyeRhythm smartphone application (app) for the diagnosis assistance of DED.

METHODS

This prospective, cross-sectional, observational, single-center study recruited 82 participants (42 with DED) aged ≥20 years (July 2020-May 2021). Patients with a history of eyelid disorder, ptosis, mental disease, Parkinson's disease, or any other disease affecting blinking were excluded. Participants underwent DED examinations, including the Japanese version of the Ocular Surface Disease Index (J-OSDI) and maximum blink interval (MBI). We analyzed their app-based J-OSDI and MBI results. Internal consistency reliability and concurrent validity were evaluated using Cronbach's alpha coefficients and Pearson's test, respectively. The discriminant validity of the app-based DED diagnosis was assessed by comparing the results of the clinical-based J-OSDI and MBI. The app feasibility and screening performance were evaluated using the precision rate and receiver operating characteristic curve analysis.

RESULTS

The app-based J-OSDI showed good internal consistency (Cronbach's α = 0.874). The app-based J-OSDI and MBI were positively correlated with their clinical-based counterparts (r = 0.891 and r = 0.329, respectively). Discriminant validity of the app-based J-OSDI and MBI yielded significantly higher total scores for the DED cohort (8.6 ± 9.3 vs. 28.4 ± 14.9, P < 0.001; 19.0 ± 11.1 vs. 13.2 ± 9.3, P < 0.001). The app's positive and negative predictive values were 91.3% and 69.1%, respectively. The area under the curve (95% confidence interval) was 0.910 (0.846-0.973) with concurrent use of the app-based J-OSDI and MBI.

CONCLUSIONS

DryEyeRhythm app is a novel, non-invasive, reliable, and valid instrument for assessing DED.

Colorimetric food spoilage monitoring with carbon dot and UV light reinforced fish gelatin films using a smartphone application

The objective of this study was to develop novel colorimetric films for food freshness monitoring. UV light irradiation (365 nm) and carbon dots (CDs) were tested as the potential crosslinkers in the fabrication of anthocyanins doped fish gelatin (FG) films. The effect of crosslinkers on the optical, surface, structural, barrier and mechanical properties of FG films was investigated. The incorporation of CD under UV irradiation improved the tested properties of FG films. The kinetic colorimetric responses of FG films against ammonia vaporwere studied to simulate the food spoilage and determine the ammonia sensitivity of the films. Among the tested films, UV-treated FG films containing 100 mg/l (FG-UV-CD100) indicated the best properties. Later, the color difference of FG-UV-CD100 films was observed to correlate well with microbial growth and TVB-N release in skinless chicken breast samples. At the same time, a custom-designed smartphone application (SmartFood) was also developed to be used with the FG-UV-CD100 film for quantitative estimation of food freshness in real-time. The proposed food freshness monitoring platform reveals a great potential to minimize global food waste and the outbreak of foodborne illness.

Impact of exercise as a complementary management strategy in people with epilepsy: A randomized controlled trial

OBJECTIVE

To measure the impact of 12 weeks of physical exercise as complementary management strategy on quality of life (QOL) in people with epilepsy (PWE).

METHODS

In a parallel-group, randomized controlled study with blinded outcome assessment, PWE of 18-65 years old, smartphone users were randomized into two groups. The exercise group was advised minimum 150 min per week of moderate-intense aerobic activity, as per current WHO recommendation [1], in addition to standard medical care; the control group received only standard medical care. QOL was assessed using Quality of Life in Epilepsy (QOLIE-31) inventory [2,3]; physical activity, with Global Physical Activity Questionnaire version 2 (GPAQ), and Pedometer Step Counter (a smartphone-based activity tracker application), at baseline and after 12 weeks. Body weight, body mass index, seizure frequency, and stigma scores (Epilepsy Stigma Scale Austin and colleagues) [4] were also noted.

RESULTS

One hundred and seventeen PWE were recruited (58 exercise, 59 control). Although there was an improvement in the physical activity correlates after 12 weeks compared to mean values at baseline, the differences were not significant between the groups. The total QOL mean scores at baseline in the exercise and control groups were 64.9 and 63.7 (p = 0.597) and after 12 weeks, 68.4 and 66.9 (p = 0.660), respectively. However, intragroup comparison of energy/fatigue score in the exercise group showed significant change with a p value of 0.009 and intragroup comparison of Overall QOL score in the control group showed a significant change with a p value of 0.003. Similar improvement was seen in stigma scores (p = 0.500) and seizure frequency (p = 0.388) at 12 weeks in exercise and control groups. After 12 weeks, mean values of METS ((metabolic equivalents) were 794.81 and 714.27 (p = 0.159), steps per day were 4018.32 and 3730.0 (p = 0.314), calories spent per day were 173.85 and 159.68 (p = 0.320 and distance walked per day in meters were 2576.52 and 2198.42 (p = 0.072), in the exercise and control groups, respectively.

SIGNIFICANCE

Regular physical activity for at least 150 min per week, in the form of moderate-intense aerobic exercises resulted in positive yet non-significant improvement of QOL, seizure frequency, and stigma in PWE.

Effectiveness of clinical pharmacist-led smartphone application on medication adherence, insulin injection technique and glycemic control for women with gestational diabetes receiving multiple daily insulin injection: A randomized clinical trial

AIM

To investigate the efficacy of a clinical pharmacist-led smartphone application (app) on medication adherence, insulin injection technique (IIT) and diabetes-related outcomes among women with gestational diabetes mellitus (GDM) receiving insulin therapy.

METHOD

In all, 124 women were randomly (1:1 ratio) assigned to receive app intervention plus usual care (intervention) or usual care (control), and were followed up till 12 weeks postpartum. Interventions centralized on medication adherence and IIT. Primary outcome was medication adherence assessed by the 5-item Medication Adherence Report Scale. Secondary outcomes included IIT, insulin requirement, prepartal and puerperal glycemic control, hypoglycemia, and pregnancy and neonatal outcomes.

RESULTS

A total of 119 patients completed the follow-up evaluation (58 intervention, 61 control). Significant more women with high medication adherence in the intervention group was observed (69.0% vs. 34.4%, p = 0.000). The other notable benefits (all p < 0.05) included patient percentage with appropriate IIT, lesser preprandial insulin dose, patient proportion with both qualified prepartal FPG and 2 hPG, and puerperal FPG or HbA1c, fewer hypoglycemia, and lower neonatal intensive care unit (NICU) admission rate. Cesarean delivery rate was higher among intervention cases (p < 0.05). Qualified prepartal glycemic control was related to high medication adherence and proper IIT. NICU admission was associated with complicated with gestational hypertension, deficient medication adherence and premature rupture of fetal membrane.

CONCLUSION

Combined with usual care, clinical pharmacist-led smartphone app might be a valid tool for GDM management.

Stimulating a future-oriented mindset and goal attainment through a smartphone-based intervention: Study protocol for a randomized controlled trial

BACKGROUND

Short-term mindsets interfere with the consideration of future consequences and therefore predict negative behaviors. We developed a smartphone-based intervention aiming to increase a future-oriented mindset and personal goal attainment by strengthening future self-identification and stimulating episodic future thinking. The aims of the study are 1) to examine users' experiences with the application and their treatment adherence, 2) to examine the effectiveness of the intervention, and 3) to explore which intervention modules generate the strongest changes in key outcomes.

METHODS

First-year university students (N = 166) will be randomly assigned to two conditions: 1) the smartphone-based intervention, or 2) a goal-setting control group. The intervention consists of three week-long modules. Data will be collected at the start of the intervention, at weekly intervals during the intervention, immediately after the intervention, and at 3-month follow-up (and at parallel time points for the control group). We will assess users' experiences, application usage data, primary intervention outcomes (e.g., self-defeating behavior, future orientation, future self-identification), and secondary intervention outcomes (e.g., psychosocial wellbeing, self-efficacy).

DISCUSSION

The study will provide information about users' experiences with the application, the intervention's general effectiveness, and which intervention modules show most promise. This information will be used to further develop the application and optimize this novel intervention.

TRIAL REGISTRATION

The trial is registered in the Netherlands Trial Register (number: NL9671) on 16 August 2021.

Portable smartphone-based colorimetric system for simultaneous on-site microfluidic paper-based determination and mapping of phosphate, nitrite and silicate in coastal waters

Early and on-site detection of environmental contaminations and physicochemical parameters of seawater is increasingly preferred to guarantee hazard minimization in many settings. In this paper, we describe a combination of microfluidic paper-based sensors (µPADs) and an Android-based smartphone application (App) for simultaneous on-site quantification of phosphate (PO₄-P), silicate (SiO₃-Si) and nitrite (NO₂-N) in coastal seawater samples. The developed App can on-site capture, process, and quantify the µPAD colorimetric outputs. This App uses an image processing algorithm for quantifying color intensity and relating the RGB components to the analyte concentrations. The GPS-tagged data can be stored on the smartphone or sent via social networks. The significant factors affecting the detection of the analytes were optimized using Box-Behnken design. Under optimized parameters, the proposed method presented the linear ranges between 5 and 100 µg L^-1 for phosphate (R² = 0.9909), 5 to 100 µg L^-1 (R² = 0.9819) for nitrite and 10 to 600 µg L^-1 (R² = 0.9933) for silicate. The LODs of the method for detection of phosphate, nitrite and silicate were 1.52 µg L^-1, 0.61 µg L^-1 and 3.74 µg L^-1, respectively. The device was successfully used to simultaneous analyze and map the PO₄-P, SiO₃-Si and NO₂-N of Bushehr coastal seawater samples (Iran). The results were confirmed by the lab-based conventional colorimetric methods using spectrophotometer.

The kleineWeltentdecker App - A smartphone-based developmental diary

Today, a vast number of tools exist to measure development in early childhood in a variety of domains such as cognition, language, or motor, cognition. These tools vary in different aspects. Either children are examined by a trained experimenter, or caregivers fill out questionnaires. The tools are applied in the controlled setting of a laboratory or in the children's natural environment. While these tools provide a detailed picture of the current state of children's development, they are at the same time subject to several constraints. Furthermore, the measurement of an individual child's change of different skills over time requires not only one measurement but high-density longitudinal assessments. These assessments are time-consuming, and the breadth of developmental domains assessed remains limited. In this paper, we present a novel tool to assess the development of skills in different domains, a smartphone-based developmental diary app (the kleineWeltentdecker App, henceforth referred to as the APP (The German expression "kleine Weltentdecker" can be translated as "young world explorers".)). By using the APP, caregivers can track changes in their children's skills during development. Here, we report the construction and validation of the questionnaires embedded in the APP as well as the technical details. Empirical validations with children of different age groups confirmed the robustness of the different measures implemented in the APP. In addition, we report preliminary findings, for example, on children's communicative development by using existing APP data. This substantiates the validity of the assessment. With the APP, we put a portable tool for the longitudinal documentation of individual children's development in every caregiver's pocket, worldwide.

A computer vision-based mobile tool for assessing human posture: A validation study

BACKGROUND AND OBJECTIVE

Non-invasive methods for postural assessment are tools used for tracking and monitoring the progression of postural deviations. Different computer-based methods have been used to assess human posture, including mobile applications based on images and sensors. However, such solutions still require manual identification of anatomical points. This study aims to present and validate the NLMeasurer, a mobile application for postural assessment. This application takes advantage of the PoseNet, a solution based on computer vision and machine learning used to estimate human pose and identify anatomical points. From the identified points, NLMeasurer calculates postural measures.

METHODS

Twenty participants were photographed in front view while using surface markers over anatomical landmarks. Then, the surface markers were removed, and new photos were taken. The photos were analyzed by two examiners, and six postural measurements were computed with NLMeasurer and a validated biophotogrammetry software. One-sample t-test and Bland Altman procedure were used to assess agreement between the methods, and Intraclass Correlation Coefficient (ICC) was used to assess inter- and intra-rater reliability.

RESULTS

Postural measurements calculated using the NLMeasurer were in agreement with the biophotogrammetry software. Furthermore, there was good inter- and intra-rater reliability for most photos without surface markers.

CONCLUSIONS

NLMeasurer demonstrated to be a valid tool method to assess postural measurements in the frontal view. The use of surface markers on specific anatomical landmarks (i.e., ears, iliac spines and ankles) can facilitate the digital identification of these landmarks and improve the reliability of the postural measurements performed with NLMeasurer.

A touch-actuated glucose sensor fully integrated with microneedle array and reverse iontophoresis for diabetes monitoring

The development of non-invasive biosensor for monitoring glucose in interstitial fluid (ISF) is still challenging, because ISF extraction through classical reverse iontophoresis (RI) is limited by low extraction flux and consistency. Here, we developed a touch-actuated biosensor for monitoring glucose in ISF. The biosensor is composed of three main components: 1) the solid microneedle array (MA) for painless skin penetration; 2) the RI unit for ISF extraction through the MA-created microchannels; and 3) the sensing unit for glucose monitoring. The sensing strategy of this biosensor is "skin penetration-RI extraction-electrochemical detection". Compared with RI extraction only, the reported skin penetration-RI extraction sampling strategy obviously increased the glucose extraction flux by ∼1.6 times not only in vitro but also in vivo. Moreover, we developed a wearable glucose monitoring system by incorporating this touch-actuated biosensor, a wireless electrochemical detector, and a smartphone application. In vivo experiments using healthy and diabetic rats revealed a high correlation between the results measured by the reported wearable system and commercially blood glucometer. This sampling strategy which combined skin penetration and RI extraction paves the way to develop wearable platforms for not only glucose monitoring but also various ISF biomarkers without the need of painful finger-stick blood sampling.

A smartphone application for remote adjustment of warfarin dose: Development and usability study

AIM

The aim of this article is (a) to design and develop a smartphone app called Alfalfa that can provide remote dose adjustment (b) to evaluate its usability.

BACKGROUND

Patients taking warfarin need to spend substantial time, money, and energy frequently visiting the hospital in order to adjust its dose. Internet technology may be able to provide convenient dose adjustment services for these patients.

METHODS

We thought and discussed repeatedly about how to ensure the safety and effectiveness of remote administration of warfarin, and finally designed and developed the Alfalfa app. In addition, patients and medical practitioners were invited to participate in a system usability scale (SUS) to assess the usability of Alfalfa.

RESULTS

As of July 5, 2021, the number of Alfalfa accounts was 1736, including 1624 patients and 112 medical staff, and it provided a total of 12,968 remote dose adjustments. A total of 26 people participated in the questionnaire, including 15 patients and 11 medical staff. The results of SUS show that the usability score of patient terminal and medical terminal is 61.8 and 82.7, respectively. And age does not affect the usability of patient terminal. The usability of the Alfalfa app was rated similarly by younger and older adults (63.5 vs. 58.5, P = .535).

CONCLUSIONS

This study proves that the Alfalfa app can be used for remote management of warfarin. The usability of medical terminal is acceptable to medical practitioners, while the usability of patient terminal needs further improvement.

TRIAL REGISTRATION

ChiCTR1900021920.

A preliminary analysis of AI based smartphone application for diagnosis of COVID-19 using chest X-ray images

The COVID-19 outbreak has catastrophically affected both public health system and world economy. Swift diagnosis of the positive cases will help in providing proper medical attention to the infected individuals and will also aid in effective tracing of their contacts to break the chain of transmission. Blending Artificial Intelligence (AI) with chest X-ray images and incorporating these models in a smartphone can be handy for the accelerated diagnosis of COVID-19. In this study, publicly available datasets of chest X-ray images have been utilized for training and testing of five pre-trained Convolutional Neural Network (CNN) models namely VGG16, MobileNetV2, Xception, NASNetMobile and InceptionResNetV2. Prior to the training of the selected models, the number of images in COVID-19 category has been increased employing traditional augmentation and Generative Adversarial Network (GAN). The performance of the five pre-trained CNN models utilizing the images generated with the two strategies has been compared. In the case of models trained using augmented images, Xception (98%) and MobileNetV2 (97.9%) turned out to be the ones with highest validation accuracy. Xception (98.1%) and VGG16 (98.6%) emerged as models with the highest validation accuracy in the models trained with synthetic GAN images. The best performing models have been further deployed in a smartphone and evaluated. The overall results suggest that VGG16 and Xception, trained with the synthetic images created using GAN, performed better compared to models trained with augmented images. Among these two models VGG16 produced an encouraging Diagnostic Odd Ratio (DOR) with higher positive likelihood and lower negative likelihood for the prediction of COVID-19.

PulsePoint dispatch associated patient characteristics and prehospital outcomes in a mid-sized metropolitan area

BACKGROUND

Mobile phone-based dispatch of volunteers to out-of-hospital cardiac arrests (OHCA) has been shown to increase the likelihood of early CPR and AED application. In the United States, limited characterization of patients encountered as a result of such systems exists.

AIMS

Examine prehospital case characteristics and outcomes from a multi-year deployment of PulsePoint Respond in Pittsburgh, Pennsylvania.

METHODS

PulsePoint event timing, location, and associated prehospital electronic health records (ePCRs) were obtained for EMS-encountered OHCA cases that did and did not generate PulsePoint alerts within the service area of Pittsburgh EMS from July 2016 to October 2020. ePCRs were reviewed and OHCA case characteristics were extracted according to the Utstein template. PulsePoint-associated OHCA and non-PulsePoint-associated OHCA were compared.

RESULTS

Of 840 total PulsePoint dispatches, 64 (7.6%) were for OHCA associated with a resuscitation attempt. Forty-one (64.1%) were witnessed, 38 (59.4%) received bystander CPR, and 13 (20.0%) of these patients had an AED applied prior to EMS arrival. Twenty-seven (39.7%) had an initial shockable rhythm, and 31 (48.4%) patients achieved ROSC in the field. In the city of Pittsburgh, there were 1229 total OHCA during the study period, with an estimated 29.6% occurring in public. When PulsePoint-associated and publicly occurring non-PulsePoint-associated OHCA were compared, baseline characteristics (age, sex, witnessed status) were similar, but PulsePoint-associated OHCA received more bystander CPR (p = 0.008).

CONCLUSIONS

A minority of PulsePoint dispatches in Pittsburgh were triggered by true OHCA. The majority of OHCA during the study period occurred within private residences where PulsePoint responders are not currently dispatched. PulsePoint dispatches were associated with prognostically favorable OHCA characteristics and increased bystander CPR performance.