Establishment and validation of a nomogram model for predicting ovulation in the PCOS women

BACKGROUND

The mechanisms underlying ovulatory dysfunction in PCOS remain debatable. This study aimed to identify the factors affecting ovulation among PCOS patients based on a large sample-sized randomized control trial.

METHODS

Data were obtained from a multi-centered randomized clinical trial, the PCOSAct, which was conducted between 2011 and 2015. Univariate and multivariate analysis using binary logistic regression were used to construct a prediction model and nomogram. The accuracy of the model was assessed using receiver operating characteristic (ROC) curves and calibration curves.

RESULTS

The predictive variables included in the training dataset model were luteinizing hormone (LH), free testosterone, body mass index (BMI), period times per year, and clomiphene treatment. The ROC curve for the model in the training dataset was 0.81 (95% CI [0.77, 0.85]), while in the validation dataset, it was 0.7801 (95% CI [0.72, 0.84]). The model showed good discrimination in both the training and validation datasets. Decision curve analysis demonstrated that the nomogram designed for ovulation had clinical utility and superior discriminative ability for predicting ovulation.

CONCLUSIONS

The nomogram composed of LH, free testosterone, BMI, period times per year and the application of clomiphene may predict the ovulation among PCOS patients.

A clinical informatics approach to bronchopulmonary dysplasia: current barriers and future possibilities

Bronchopulmonary dysplasia (BPD) is a complex, multifactorial lung disease affecting preterm neonates that can result in long-term pulmonary and non-pulmonary complications. Current therapies mainly focus on symptom management after the development of BPD, indicating a need for innovative approaches to predict and identify neonates who would benefit most from targeted or earlier interventions. Clinical informatics, a subfield of biomedical informatics, is transforming healthcare by integrating computational methods with patient data to improve patient outcomes. The application of clinical informatics to develop and enhance clinical therapies for BPD presents opportunities by leveraging electronic health record data, applying machine learning algorithms, and implementing clinical decision support systems. This review highlights the current barriers and the future potential of clinical informatics in identifying clinically relevant BPD phenotypes and developing clinical decision support tools to improve the management of extremely preterm neonates developing or with established BPD. However, the full potential of clinical informatics in advancing our understanding of BPD with the goal of improving patient outcomes cannot be achieved unless we address current challenges such as data collection, storage, privacy, and inherent data bias.

A Nationwide Chronic Disease Management Solution via Clinical Decision Support Services: Software Development and Real-Life Implementation Report

BACKGROUND

The increasing population of older adults has led to a rise in the demand for health care services, with chronic diseases being a major burden. Person-centered integrated care is required to address these challenges; hence, the Turkish Ministry of Health has initiated strategies to implement an integrated health care model for chronic disease management. We aim to present the design, development, nationwide implementation, and initial performance results of the national Disease Management Platform (DMP).

OBJECTIVE

This paper's objective is to present the design decisions taken and technical solutions provided to ensure successful nationwide implementation by addressing several challenges, including interoperability with existing IT systems, integration with clinical workflow, enabling transition of care, ease of use by health care professionals, scalability, high performance, and adaptability.

METHODS

The DMP is implemented as an integrated care solution that heavily uses clinical decision support services to coordinate effective screening and management of chronic diseases in adherence to evidence-based clinical guidelines and, hence, to increase the quality of health care delivery. The DMP is designed and implemented to be easily integrated with the existing regional and national health IT systems via conformance to international health IT standards, such as Health Level Seven Fast Healthcare Interoperability Resources. A repeatable cocreation strategy has been used to design and develop new disease modules to ensure extensibility while ensuring ease of use and seamless integration into the regular clinical workflow during patient encounters. The DMP is horizontally scalable in case of high load to ensure high performance.

RESULTS

As of September 2023, the DMP has been used by 25,568 health professionals to perform 73,715,269 encounters for 16,058,904 unique citizens. It has been used to screen and monitor chronic diseases such as obesity, cardiovascular risk, diabetes, and hypertension, resulting in the diagnosis of 3,545,573 patients with obesity, 534,423 patients with high cardiovascular risk, 490,346 patients with diabetes, and 144,768 patients with hypertension.

CONCLUSIONS

It has been demonstrated that the platform can scale horizontally and efficiently provides services to thousands of family medicine practitioners without performance problems. The system seamlessly interoperates with existing health IT solutions and runs as a part of the clinical workflow of physicians at the point of care. By automatically accessing and processing patient data from various sources to provide personalized care plan guidance, it maximizes the effect of evidence-based decision support services by seamless integration with point-of-care electronic health record systems. As the system is built on international code systems and standards, adaptation and deployment to additional regional and national settings become easily possible. The nationwide DMP as an integrated care solution has been operational since January 2020, coordinating effective screening and management of chronic diseases in adherence to evidence-based clinical guidelines.

Could Spatial Awareness Affect Situation Awareness: A Conceptual Examination

PURPOSE

The purpose of this study was to explore the relationship between situation awareness (SA) and the physical environment in patient rooms through building a conceptual model.

BACKGROUND

Nurses work in very complicated and dynamic environments where having high levels of SA could be critical for their performance. Studies have also shown that nurses' awareness of the physical environment and patient room is a part of their awareness of dynamic situations in which nurses' spatial awareness may play a role in SA. Despite literature outlining the importance of SA, there is a lack of studies exploring the relationship between the two.

METHOD

A literature review was conducted for the study from nursing and psychology databases. Thirty-three articles, books, and dissertations from a scoping review were included for in-depth review.

RESULTS

An in-depth review of the harvested literature indicated that there is in fact a relationship between these two phenomena. Founded on Endsley's model of SA, the literature review in this study offers a conceptual model that articulates a plausible causal pathway between the physical environment and SA.

CONCLUSIONS

There are a lot of studies focusing on SA and various aspects of it related to nursing, but almost none mention the physical environment and its impact on SA. The current inquiry suggests that spatial awareness plays a prominent role in SA.

Feasibility of machine learning-based modeling and prediction using multiple centers data to assess intrahepatic cholangiocarcinoma outcomes

BACKGROUND AND AIMS

Currently, there are still no definitive consensus in the treatment of intrahepatic cholangiocarcinoma (iCCA). This study aimed to build a clinical decision support tool based on machine learning using the Surveillance, Epidemiology, and End Results (SEER) database and the data from the Fifth Medical Center of the PLA General Hospital in China.

METHODS

4,398 eligible patients from the SEER database and 504 eligible patients from the hospital data, who presented with histologically proven iCCA, were enrolled for modeling by cross-validation based on machine learning. All the models were trained using the open-source Python library scikit-survival version 0.16.0. Shapley additive explanations method was used to help clinicians better understand the obtained results. Permutation importance was calculated using library ELI5.

RESULTS

All involved treatment modalities could contribute to a better prognosis. Three models were derived and tested using different data sources, with concordance indices of 0.67, 0.69, and 0.73, respectively. The prediction results were consistent with those under actual situations involving randomly selected patients. Model 2, trained using the hospital data, was selected to develop an online tool, due to its advantage in predicting short-term prognosis.

CONCLUSION

The prediction model and tool established in this study can be applied to predict the prognosis of iCCA after treatment by inputting the patient's clinical parameters or TNM stages and treatment options, thus contributing to optimal clinical decisions.KEY MESSAGESA prognostic model related to disease staging and treatment mode was conducted using the method of machine learning, based on the big data of multi centers.The online calculator can predict the short-term survival prognosis of intrahepatic cholangiocarcinoma, thus, help to make the best clinical decision.The online calculator built to calculate the mortality risk and overall survival can be easily obtained and applied.

How Natural Language Processing Can Aid With Pulmonary Oncology Tumor Node Metastasis Staging From Free-Text Radiology Reports: Algorithm Development and Validation

BACKGROUND

Natural language processing (NLP) is thought to be a promising solution to extract and store concepts from free text in a structured manner for data mining purposes. This is also true for radiology reports, which still consist mostly of free text. Accurate and complete reports are very important for clinical decision support, for instance, in oncological staging. As such, NLP can be a tool to structure the content of the radiology report, thereby increasing the report's value.

OBJECTIVE

This study describes the implementation and validation of an N-stage classifier for pulmonary oncology. It is based on free-text radiological chest computed tomography reports according to the tumor, node, and metastasis (TNM) classification, which has been added to the already existing T-stage classifier to create a combined TN-stage classifier.

METHODS

SpaCy, PyContextNLP, and regular expressions were used for proper information extraction, after additional rules were set to accurately extract N-stage.

RESULTS

The overall TN-stage classifier accuracy scores were 0.84 and 0.85, respectively, for the training (N=95) and validation (N=97) sets. This is comparable to the outcomes of the T-stage classifier (0.87-0.92).

CONCLUSIONS

This study shows that NLP has potential in classifying pulmonary oncology from free-text radiological reports according to the TNM classification system as both the T- and N-stages can be extracted with high accuracy.

Use of imaging modalities for decision-making in inflammatory bowel disease

Cross-sectional magnetic resonance enterography (MRE) and intestinal ultrasonography (IUS) provide valuable and noninvasive information to accurately assess disease activity, severity, and extent; detect complications; and monitor the response to treatment, as well as predict the postoperative recurrence of Crohn's disease and a negative disease course. Therefore, both imaging modalities are emerging as pivotal diagnostic tools to achieve the emerging therapeutic target of transmural healing associated with better disease outcomes. Despite its numerous potential advantages over endoscopy and even MRE and its good availability, IUS is still widely underused to monitor and manage inflammatory bowel disease (IBD) patients and help in making clinical decisions in routine practice. This situation is clearly due to the absence of validated, reliable, and responsive indices, as well as the lack of trained gastroenterologists and radiologists, as IUS is a component of radiologist expertise in several countries but not yet integrated into the training program of gastroenterologists. However, there is an increasing body of evidence in the literature that IUS and MRE are both becoming essential imaging resources to help clinicians in making reliable decisions. Here, we discuss the up-to-date evidence about the usefulness and performance of cross-sectional imaging, focusing on the ability of bowel US and MRE to aid clinical decision-making for the optimal management and monitoring of IBD.

[Clinical characteristics analysis of 22 062 patients of foot and ankle deformity from QIN Sihe Orthopaedic Surgery Database between May 25, 1978 and December 31, 2020]

Objective

Based on the clinical data of patients with foot and ankle deformities in the QIN Sihe Orthopaedic Surgery Database, to analyze the characteristics and treatment strategies of foot and ankle deformities, and provide a basis for clinical decision-making.

Methods

A total of 22 062 patients with foot and ankle deformities who received orthopedic surgery between May 25, 1978 and December 31, 2020 were searched in the QIN Sihe Orthopedic Surgery Database. The gender, age at operation, regional distribution, etiology, type of deformity, operation method, postoperative fixation method, and other information were collected.

Results

Among the 22 062 patients, there were 13 046 males (59.13%) and 9 016 females (40.87%); the age at operation ranged from 1 to 77 years, with a median of 17 years, and 20 026 cases (90.77%) were aged 5 to 40 years. The patients came from 32 provinces, municipalities, and autonomous regions across the China and 5 countries including India and the United States, et al. The etiology and diseases type covered 154 kinds (of which sequelae of poliomyelitis, cerebral palsy, spina bifida and tethered spinal cord, congenital equinovarus foot, post-traumatic foot and ankle deformity, and Charcot-Marie-Tooth disease accounted for the highest proportion). The types of deformities included varus foot, equinus foot, valgus foot, talipes calcaneus, equinocavus, high arched foot, claw toe, and flail foot. Surgical methods included tendon lengthening, soft tissue release, tendon transposition, osteotomy orthopedics, and ankle arthrodesis. The 36 620 operations were performed, including 11 561 cases of hip, knee, and lower leg operations to correct the foot and ankle deformities. Postoperative fixation methods included Ilizarov external fixator in 2 709 cases (12.28%), combined external fixator in 3 966 cases (17.98%), and plaster or brace fixation in 15 387 cases (69.74%).

Conclusion

Male patients with foot and ankle deformities account for a large proportion, and the population distribution is mainly adolescents, with a wide distribution of regions, causes and diseases, and talipes equinovarus and varus foot are the main types of deformities. Foot and ankle deformities are often combined with deformities of other parts of the lower limb, which requires a holistic treatment concept. The application of foot soft tissue and bone surgery combined with Ilizarov external fixator and combined external fixators provides a guarantee for the correction of complex foot and ankle deformities.

Postoperative Sigmoidoscopy and Biopsy After Elective Endovascular and Open Aortic Surgery for Preventing Mortality by Colonic Ischemia (PSB-Aorta-CI): Protocol for a Prospective Study

BACKGROUND

Endovascular aortic repair is considered the standard procedure in treating patients diagnosed with pathologies of the abdominal aorta with suitable anatomy. Open surgery remains an option mostly for patients not suitable for endovascular surgery. Colonic ischemia is an important and life-threatening postoperative complication of these procedures.

OBJECTIVE

The aim of this study is to evaluate the clinical value and safety of performing a planned sigmoidoscopy and biopsy for detection of colonic ischemia in patients undergoing elective aortic surgery. We also aim to develop prediction scores which could identify patients at risk for colonic ischemia and facilitate their timely treatment.

METHODS

The trial is designed as a prospective study. The decision for aortic surgery and eligibility for these procedures will be ascertained according to current guidelines. Afterward, screening of the patient for the remaining inclusion and exclusion criteria will occur. If eligibility for study inclusion is confirmed, the patient will be informed about the aims of the study and all study-specific procedures (sigmoidoscopy and biopsy) and asked to provide informed consent.

RESULTS

The primary end point is the proportion of patients diagnosed endoscopically with subclinical and clinically relevant colonic ischemia among all patients undergoing aortic surgery. Patient recruitment started on June 2021. The final patient is expected to be treated by the end of June 2023. Institutional Review Board review has been completed at the University of Halle (Saale; reference #052-2021).

CONCLUSIONS

this shows that sigmoidoscopy can be performed safely and is effective for the timely diagnosis of colonic ischemia in these patients, this could result in its routine implementation in both elective and emergency settings.

TRIAL REGISTRATION

German Clinical Trials Register DRKS00025587; https://www.drks.de/drks_web/navigate.do?navigationId =trial.HTML&TRIAL_ID=DRKS00025587.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/39071.

Incorporating Paid Caregivers Into Medical Education to Enhance Medical Student Exposure to This Essential Workforce

The implications of the COVID-19 pandemic underscored the utility of home-based health care due in part to social distancing requirements, curtailment of elective hospital procedures, and patient apprehension of the health care setting. The pandemic particularly accentuated the integral role of paid caregivers (eg, home health aides, personal care attendants, and other home care workers) in caring for patients with chronic health conditions. Given the paradigm shift toward community- and value-based health care models, paid caregivers are likely to play an even greater role as care team members. Despite the increasingly prominent role paid caregivers are assuming in health care, especially for patients who are chronically ill, in our experience as medical students, we have very little exposure to these care team members, with most interactions occurring in brief, chance encounters. Specifically, we advocate for increased medical student exposure to paid caregivers to facilitate their recognition as valuable care team members. We propose to achieve this through (1) classroom-based module learning with live paid caregivers and (2) plain language communication training to enhance reciprocal engagement.

Conceptions of Legacy Among People Making Treatment Choices for Serious Illness: Protocol for a Scoping Review

BACKGROUND

Legacy-what one leaves behind and how one hopes to be remembered after death-is an unexplored and important dimension of decision-making for people facing serious illnesses. A preliminary literature review suggests that patients facing serious illness consider legacy when making medical decisions, for example, forgoing expensive treatment with limited or unknown clinical benefit to preserve one's inheritance for their children. To date, very little is known about the conceptual foundations of legacy. No conceptual frameworks exist that provide a comprehensive understanding of how legacy considerations relate to patient choices about their medical care.

OBJECTIVE

The objective of this scoping review is to understand the extent and type of research addressing the concept of legacy by people facing serious illness to inform a conceptual framework of legacy and patient treatment choices.

METHODS

This protocol follows the guidelines put forth by Levac et al, which expands the framework introduced by Arksey and O'Malley, as well as the Joanna Briggs Institute Reviewer's manual. This scoping review will explore several electronic databases including PubMed, Medline, CINAHL, Cochrane Library, PsycINFO, and others and will include legacy-specific gray literature, including dissertation research available via ProQuest. An initial search will be conducted in English-language literature from 1990 to the present with selected keywords to identify relevant articles and refine the search strategy. After the search strategy has been finalized, 2 independent reviewers will undertake a 2-part study selection process. In the first step, reviewers will screen article titles and abstracts to identify the eligibility of each article based on predetermined exclusion or inclusion criteria. A third senior reviewer will arbitrate discrepancies regarding inclusions or exclusions. During the second step, the full texts will be screened by 2 reviewers, and only relevant articles will be kept. Relevant study data will be extracted, collated, and charted to summarize the key findings related to the construct of legacy.

RESULTS

This study will identify how people facing serious illness define legacy, and how their thinking about legacy impacts the choices they make about their medical treatments. We will note gaps in the literature base. The findings of this study will inform a conceptual model that outlines how ideas about legacy impact the patient's treatment choices. The results of this study will be submitted to an indexed journal.

CONCLUSIONS

Very little is known about the role of legacy in the treatment decisions of patients across the continuum of serious illness. In particular, no comprehensive conceptual model exists that would provide an understanding of how legacy is considered by people making decisions about their care during serious illness. This study will be among the first to construct a conceptual model detailing how considerations of legacy impact medical decision-making for people facing or living with serious illnesses.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/40791.

Clinical Decision Support Framework for Segmentation and Classification of Brain Tumor MRIs Using a U-Net and DCNN Cascaded Learning Algorithm

Brain tumors (BTs) are an uncommon but fatal kind of cancer. Therefore, the development of computer-aided diagnosis (CAD) systems for classifying brain tumors in magnetic resonance imaging (MRI) has been the subject of many research papers so far. However, research in this sector is still in its early stage. The ultimate goal of this research is to develop a lightweight effective implementation of the U-Net deep network for use in performing exact real-time segmentation. Moreover, a simplified deep convolutional neural network (DCNN) architecture for the BT classification is presented for automatic feature extraction and classification of the segmented regions of interest (ROIs). Five convolutional layers, rectified linear unit, normalization, and max-pooling layers make up the DCNN's proposed simplified architecture. The introduced method was verified on multimodal brain tumor segmentation (BRATS 2015) datasets. Our experimental results on BRATS 2015 acquired Dice similarity coefficient (DSC) scores, sensitivity, and classification accuracy of 88.8%, 89.4%, and 88.6% for high-grade gliomas. When it comes to segmenting BRATS 2015 BT images, the performance of our proposed CAD framework is on par with existing state-of-the-art methods. However, the accuracy achieved in this study for the classification of BT images has improved upon the accuracy reported in prior studies. Image classification accuracy for BRATS 2015 BT has been improved from 88% to 88.6%.

A deep belief network-based clinical decision system for patients with osteosarcoma

Osteosarcoma was the most frequent type of malignant primary bone tumor with a poor survival rate mainly occurring in children and adolescents. For precision treatment, an accurate individualized prognosis for Osteosarcoma patients is highly desired. In recent years, many machine learning-based approaches have been used to predict distant metastasis and overall survival based on available individual information. In this study, we compared the performance of the deep belief networks (DBN) algorithm with six other machine learning algorithms, including Random Forest, XGBoost, Decision Tree, Gradient Boosting Machine, Logistic Regression, and Naive Bayes Classifier, to predict lung metastasis for Osteosarcoma patients. Therefore the DBN-based lung metastasis prediction model was integrated as a parameter into the Cox proportional hazards model to predict the overall survival of Osteosarcoma patients. The accuracy, precision, recall, and F1 score of the DBN algorithm were 0.917/0.888, 0.896/0.643, 0.956/0.900, and 0.925/0.750 in the training/validation sets, respectively, which were better than the other six machine-learning algorithms. For the performance of the DBN survival Cox model, the areas under the curve (AUCs) for the 1-, 3- and 5-year survival in the training set were 0.851, 0.806 and 0.793, respectively, indicating good discrimination, and the calibration curves showed good agreement between the prediction and actual observations. The DBN survival Cox model also demonstrated promising performance in the validation set. In addition, a nomogram integrating the DBN output was designed as a tool to aid clinical decision-making.

Dig Deeper: A Case Report of Finding (and Fixing) the Root Cause of Add-On Laboratory Failures

BACKGROUND

Venipunctures and the testing they facilitate are clinically necessary, particularly for hospitalized patients. However, excess venipunctures lead to patient harm, decreased patient satisfaction, and waste.

OBJECTIVES

We sought to identify contributors to excess venipunctures at our institution, focusing on electronic health record (EHR)-related factors. We then implemented and evaluated the impact of an intervention targeting one of the contributing factors.

METHODS

We employed the quality improvement (QI) methodology to find sources of excess venipunctures, specifically targeting add-on failures. Once an error was identified, we deployed an EHR-based intervention which was evaluated with retrospective pre- and postintervention analysis.

RESULTS

We identified an error in how the EHR evaluated the ability of laboratories across a health system to perform add-on tests to existing blood specimens. A review of 195,263 add-on orders placed prior to the intervention showed that 165,118 were successful and 30,145 failed, a failure rate of 15.4% (95% confidence interval [CI]: 15.1-15.6). We implemented an EHR-based modification that changed the criteria for add-on testing from a health-system-wide query of laboratory capabilities to one that incorporated only the capabilities of laboratories with feasible access to existing patient samples. In the 6 months following the intervention, a review of 87,333 add-on orders showed that 77,310 were successful, and 10,023 add-on orders failed resulting in a postintervention failure rate of 11.4% (95% CI: 11.1, 11.8) (p < 0.001).

CONCLUSION

EHR features such as the ability to identify possible add-on tests are designed to reduce venipunctures but may produce unforeseen negative effects on downstream processes, particularly as hospitals merge into health systems using a single EHR. This case report describes the successful identification and correction of one cause of add-on laboratory failures. QI methodology can yield important insights that reveal simple interventions for improvement.

Development of an Interoperable and Easily Transferable Clinical Decision Support System Deployment Platform: System Design and Development Study

Background

A clinical decision support system (CDSS) is recognized as a technology that enhances clinical efficacy and safety. However, its full potential has not been realized, mainly due to clinical data standards and noninteroperable platforms.

Objective

In this paper, we introduce the common data model–based intelligent algorithm network environment (CANE) platform that supports the implementation and deployment of a CDSS.

Methods

CDSS reasoning engines, usually represented as R or Python objects, are deployed into the CANE platform and converted into C# objects. When a clinician requests CANE-based decision support in the electronic health record (EHR) system, patients’ information is transformed into Health Level 7 Fast Healthcare Interoperability Resources (FHIR) format and transmitted to the CANE server inside the hospital firewall. Upon receiving the necessary data, the CANE system’s modules perform the following tasks: (1) the preprocessing module converts the FHIRs into the input data required by the specific reasoning engine, (2) the reasoning engine module operates the target algorithms, (3) the integration module communicates with the other institutions’ CANE systems to request and transmit a summary report to aid in decision support, and (4) creates a user interface by integrating the summary report and the results calculated by the reasoning engine.

Results

We developed a CANE system such that any algorithm implemented in the system can be directly called through the RESTful application programming interface when it is integrated with an EHR system. Eight algorithms were developed and deployed in the CANE system. Using a knowledge-based algorithm, physicians can screen patients who are prone to sepsis and obtain treatment guides for patients with sepsis with the CANE system. Further, using a nonknowledge-based algorithm, the CANE system supports emergency physicians’ clinical decisions about optimum resource allocation by predicting a patient’s acuity and prognosis during triage.

Conclusions

We successfully developed a common data model–based platform that adheres to medical informatics standards and could aid artificial intelligence model deployment using R or Python.

MVI-Mind: A Novel Deep-Learning Strategy Using Computed Tomography (CT)-Based Radiomics for End-to-End High Efficiency Prediction of Microvascular Invasion in Hepatocellular Carcinoma

Simple Summary

Microvascular invasion is an important indicator for reflecting the prognosis of hepatocellular carcinoma, but the traditional diagnosis requires a postoperative pathological examination. This study is the first to propose an end-to-end deep learning architecture for predicting microvascular invasion in hepatocellular carcinoma by collecting retrospective data. This method can achieve noninvasive, accurate and efficient preoperative prediction only through the patient’s radiomic data, which is very beneficial to doctors for clinical decision making in HCC patients.

Abstract

Microvascular invasion (MVI) in hepatocellular carcinoma (HCC) directly affects a patient’s prognosis. The development of preoperative noninvasive diagnostic methods is significant for guiding optimal treatment plans. In this study, we investigated 138 patients with HCC and presented a novel end-to-end deep learning strategy based on computed tomography (CT) radiomics (MVI-Mind), which integrates data preprocessing, automatic segmentation of lesions and other regions, automatic feature extraction, and MVI prediction. A lightweight transformer and a convolutional neural network (CNN) were proposed for the segmentation and prediction modules, respectively. To demonstrate the superiority of MVI-Mind, we compared the framework’s performance with that of current, mainstream segmentation, and classification models. The test results showed that MVI-Mind returned the best performance in both segmentation and prediction. The mean intersection over union (mIoU) of the segmentation module was 0.9006, and the area under the receiver operating characteristic curve (AUC) of the prediction module reached 0.9223. Additionally, it only took approximately 1 min to output a prediction for each patient, end-to-end using our computing device, which indicated that MVI-Mind could noninvasively, efficiently, and accurately predict the presence of MVI in HCC patients before surgery. This result will be helpful for doctors to make rational clinical decisions.

Stakeholder Perspectives on Clinical Decision Support Tools to Inform Clinical Artificial Intelligence Implementation: Protocol for a Framework Synthesis for Qualitative Evidence

BACKGROUND

Quantitative systematic reviews have identified clinical artificial intelligence (AI)-enabled tools with adequate performance for real-world implementation. To our knowledge, no published report or protocol synthesizes the full breadth of stakeholder perspectives. The absence of such a rigorous foundation perpetuates the "AI chasm," which continues to delay patient benefit.

OBJECTIVE

The aim of this research is to synthesize stakeholder perspectives of computerized clinical decision support tools in any health care setting. Synthesized findings will inform future research and the implementation of AI into health care services.

METHODS

The search strategy will use MEDLINE (Ovid), Scopus, CINAHL (EBSCO), ACM Digital Library, and Science Citation Index (Web of Science). Following deduplication, title, abstract, and full text screening will be performed by 2 independent reviewers with a third topic expert arbitrating. The quality of included studies will be appraised to support interpretation. Best-fit framework synthesis will be performed, with line-by-line coding completed by 2 independent reviewers. Where appropriate, these findings will be assigned to 1 of 22 a priori themes defined by the Nonadoption, Abandonment, Scale-up, Spread, and Sustainability framework. New domains will be inductively generated for outlying findings. The placement of findings within themes will be reviewed iteratively by a study advisory group including patient and lay representatives.

RESULTS

Study registration was obtained from PROSPERO (CRD42021256005) in May 2021. Final searches were executed in April, and screening is ongoing at the time of writing. Full text data analysis is due to be completed in October 2021. We anticipate that the study will be submitted for open-access publication in late 2021.

CONCLUSIONS

This paper describes the protocol for a qualitative evidence synthesis aiming to define barriers and facilitators to the implementation of computerized clinical decision support tools from all relevant stakeholders. The results of this study are intended to expedite the delivery of patient benefit from AI-enabled clinical tools.

TRIAL REGISTRATION

PROSPERO CRD42021256005; https://tinyurl.com/r4x3thvp.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/33145.

Patient satisfaction and clinical outcomes of reverse shoulder arthroplasty: a minimum of 10 years' follow-up

BACKGROUND

Reverse shoulder arthroplasty (RSA) has been shown to reliably improve pain and functional outcomes for multiple pathologies. Despite its increasing use in the United States since its introduction in 2004, few studies have investigated long-term outcomes of this procedure. This information is vital in many ways, including durability of functional outcomes, complication profiles, and implant survivorship.

METHODS

Our prospectively collected shoulder arthroplasty registry included 471 patients who had undergone RSA prior to December 31, 2010, by a single surgeon at a high-volume shoulder arthroplasty center. The study sample included 94 patients with a minimum of 10 years' follow-up, and we evaluated the indications for RSA, complications, pain, Single Assessment Numeric Evaluation (SANE), and patient satisfaction on these patients at baseline, 2-5 years, and 10 or more years of follow-up. Prosthesis survivorship was determined by Kaplan-Meier survival analysis performed with revision for any reason as the end point for all 471 patients in the study period regardless of follow-up interval.

RESULTS

The 93 patients with at least 10 years of follow-up were 63% female (60) and 37% male (34), with an average age of 66±10 years at the time of RSA. There were 70 (75%) primary RSAs and 23 (25%) revision RSAs. Patient-reported outcome measures at 10 years or more included a current pain rating averaging 2±3 on a 0-10 scale and Single Assessment Numeric Evaluation (SANE) of 73±28. There was no deterioration in function or pain from midterm to long-term follow-up, as the SANE and pain score changed by less than the minimal clinically important difference or improved in 87% and 90% of patients, respectively. Overall, patients were satisfied with the RSA procedure, with 52 (56%) very satisfied, 24 (26%) satisfied, 13 (14%) dissatisfied, and 4 (4%) very dissatisfied. For the subset of 68 patients who were contacted for follow-up, 64 (94%) would have the procedure again and 4 (6%) would not. Kaplan-Meier prosthesis survival rate for all 471 RSA patients was 88% (95% confidence interval [CI] 84%-92%) at 5 years and 81% (95% CI 74%-86%) at 10 years.

CONCLUSIONS

This study presents the largest American cohort of Grammont design RSA at a minimum 10-year follow-up. Although RSA provided clinically significant and durable improvements in pain and function, the complication and revision rates were higher than prior reports. Despite this, the vast majority of patients were satisfied and would have the procedure again.

Generalizability of Cardiovascular Disease Clinical Prediction Models: 158 Independent External Validations of 104 Unique Models

Background:

While clinical prediction models (CPMs) are used increasingly commonly to guide patient care, the performance and clinical utility of these CPMs in new patient cohorts is poorly understood.

Methods:

We performed 158 external validations of 104 unique CPMs across 3 domains of cardiovascular disease (primary prevention, acute coronary syndrome, and heart failure). Validations were performed in publicly available clinical trial cohorts and model performance was assessed using measures of discrimination, calibration, and net benefit. To explore potential reasons for poor model performance, CPM-clinical trial cohort pairs were stratified based on relatedness, a domain-specific set of characteristics to qualitatively grade the similarity of derivation and validation patient populations. We also examined the model-based C-statistic to assess whether changes in discrimination were because of differences in case-mix between the derivation and validation samples. The impact of model updating on model performance was also assessed.

Results:

Discrimination decreased significantly between model derivation (0.76 [interquartile range 0.73–0.78]) and validation (0.64 [interquartile range 0.60–0.67], P<0.001), but approximately half of this decrease was because of narrower case-mix in the validation samples. CPMs had better discrimination when tested in related compared with distantly related trial cohorts. Calibration slope was also significantly higher in related trial cohorts (0.77 [interquartile range, 0.59–0.90]) than distantly related cohorts (0.59 [interquartile range 0.43–0.73], P=0.001). When considering the full range of possible decision thresholds between half and twice the outcome incidence, 91% of models had a risk of harm (net benefit below default strategy) at some threshold; this risk could be reduced substantially via updating model intercept, calibration slope, or complete re-estimation.

Conclusions:

There are significant decreases in model performance when applying cardiovascular disease CPMs to new patient populations, resulting in substantial risk of harm. Model updating can mitigate these risks. Care should be taken when using CPMs to guide clinical decision-making.

Jordanian Radiologists' Perspectives and Application of Evidence-Based Radiology in Clinical Practice

PURPOSE

To evaluate radiologists' education, knowledge and skills of research, attitude toward evidence-based radiology (EBR), understanding of terms and use of related published work in clinical practice and the association between these variables and sociodemographic characteristics. We also aim to assess the availability of resources and to identify sources and the main barriers to implementing EBR.

MATERIALS AND METHODS

A total of 87 radiologists completed a questionnaire, which consisted of eight sections related to radiologists' demographic characteristics, and EBR-related questions. Descriptive statistics were used, and the association between EBR-related parts and sociodemographic characteristics was performed.

RESULTS

Ninety-three percent of the radiologists believed that EBR is necessary in practice. Only 40% received formal training in search strategies and 29.9% in critical appraisal of research literature during academic preparation. Moreover, 21-62% of the respondents completely understand specific terms related to EBR. Sixty-three percent stated that they can access relevant databases and the Internet at workplace. Research articles were only used by 24% to make a clinical decision. Almost 50% reported that they read or reviewed ≤1 article per month. The primary barrier to implementing EBR was the lack of colleagues' support. Understanding terms and the number of articles used in clinical decision were significantly related to education (P-value=0.001, 0.007) and hospital section (P-value=0.002, 0.027) respectively.

CONCLUSION

Radiologists showed positive attitude toward EBR. However, there is a lack in information resources, colleagues' support, use of published literature, understanding of research terms and the ability of radiologists to access relevant databases at workplaces.

How Does Comparison With Artificial Intelligence Shed Light on the Way Clinicians Reason? A Cross-Talk Perspective

In order to create a dynamic for the psychiatry of the future, bringing together digital technology and clinical practice, we propose in this paper a cross-teaching translational roadmap comparing clinical reasoning with computational reasoning. Based on the relevant literature on clinical ways of thinking, we differentiate the process of clinical judgment into four main stages: collection of variables, theoretical background, construction of the model, and use of the model. We detail, for each step, parallels between: i) clinical reasoning; ii) the ML engineer methodology to build a ML model; iii) and the ML model itself. Such analysis supports the understanding of the empirical practice of each of the disciplines (psychiatry and ML engineering). Thus, ML does not only bring methods to the clinician, but also supports educational issues for clinical practice. Psychiatry can rely on developments in ML reasoning to shed light on its own practice in a clever way. In return, this analysis highlights the importance of subjectivity of the ML engineers and their methodologies.

Clinical Perspectives of Single-Cell RNA Sequencing

The ability of single-cell genomics to resolve cellular heterogeneity is highly appreciated in cancer and is being exploited for precision medicine. In the recent decade, we have witnessed the incorporation of cancer genomics into the clinical decision-making process for molecular-targeted therapies. Compared with conventional genomics, which primarily focuses on the specific and sensitive detection of the molecular targets, single-cell genomics addresses intratumoral heterogeneity and the microenvironmental components impacting the treatment response and resistance. As an exploratory tool, single-cell genomics provides an unprecedented opportunity to improve the diagnosis, monitoring, and treatment of cancer. The results obtained upon employing bulk cancer genomics indicate that single-cell genomics is at an early stage with respect to exploration of clinical relevance and requires further innovations to become a widely utilized technology in the clinic.

Methods for the Development of Healthcare Practice Recommendations Using Systematic Reviews and Meta-Analyses

Quality of healthcare can be improved when the best external evidence available is integrated in clinical decision-making in a systematic explicit manner. With the rapid expansion of clinical evidence, the opportunities for evidence-based high-quality healthcare increase. Paradoxically, the likelihood of any one person to get a complete and balanced picture of the evidence available decreases. This is especially true for rehabilitation interventions that are complex in nature and where clinical research is rather diverse. Given the complex nature of the evidence, there is a substantial risk of misinterpreting the complex information both at the level of individual sources (e.g., reports of clinical trials) and for aggregated data syntheses (e.g., systematic reviews and meta-analyses). These risks are inherent in these sources themselves and are in addition related to the methodological expertise necessary to make valid use of the evidence for clinical decision-making. Taken together, there is a great demand for systematic structured guidance from evidence to clinical decision. This methodology paper describes a structured process for the development and report of evidence-based clinical practice recommendations that uses systematic reviews and meta-analyses as evidence source. It provides a comprehensive framework with specific requirements for the development group, the formulation of the healthcare question addressed, the systematic search for the evidence, its critical appraisal, the extraction and the outcome-centered presentation of the evidence, the rating of its quality, strengths and weaknesses, any further considerations relevant for decision-making, and an explicit recommendation statement along with its justification, implementation, and resource aspects. The suggested methodology uses international standards in evidence synthesis, critical appraisal of systematic reviews, rating the quality of evidence, characteristics of recommendations, and guideline development as developed by Cochrane, GRADE (Grading of Recommendations Assessment, Development and Evaluation), AMSTAR (A MeaSurement Tool to Assess systematic Reviews), and AGREE (Appraisal of Guidelines for REsearch & Evaluation). An added distinctive feature of the methodology is to focus on the most up-to-date, most valid evidence and hence to support the development of valid practice recommendations in an efficient way. Practice recommendations generated by such a valid methodology would be generally applicable and promote evidence-based clinical practice globally.

Anatomic and reverse shoulder arthroplasty in patients 70 years of age and older: a comparison cohort at early to midterm follow-up

BACKGROUND

Reverse shoulder arthroplasty (RSA) has gained popularity in elderly patients because of its limited reliance on rotator cuff function and high survivorship rates. However, although there are theoretical advantages of RSA over anatomic total shoulder arthroplasty (TSA) in elderly patients, there is little data to guide surgeons on implant selection in this population.

METHODS

Patients were identified from our prospectively collected shoulder arthroplasty registry. We included patients between the age of 50 and 89 years who underwent primary TSA for osteoarthritis with intact rotator cuff or primary RSA for cuff tear arthropathy. The minimum and mean clinical follow-up was 2 and 3.1±1.3 years, respectively. Four patient groups were formed for analysis: (1) TSA age 50-69 years (n=274), (2) TSA age 70-89 years (n=208), (3) RSA age 50-69 years (n=81), and (4) RSA age 70-89 years (n=104). We evaluated age group differences in pain, Constant score, American Shoulder and Elbow Surgeons Standardized Shoulder Assessment Form (ASES) score, patient satisfaction, complications, and revisions.

RESULTS

All groups showed significant improvements from preoperative to final follow-up for all outcome measures (P < .001). Visual analog scale for pain average score decreased from 5.8 preoperatively to 1.1, with no significant differences between groups (TSA P = .180; RSA P = .103). Final ASES scores and improvement from preoperative ASES score between the age groups were not significantly different (TSA P = .520; RSA P = .065). There were no significant differences in outcomes between TSA in patients older than 70 years vs. patients younger than 70 years (all P > .05); however, older RSA patients reported better function during activities of daily living (P = .020) than their younger counterparts. Patients undergoing TSA had a lower revision rate of 3.9% compared with 8.1% in the RSA group (P = .043).

CONCLUSIONS

TSA and RSA are reliable procedures for patients older than 70 years, and have comparable results to their respective patient cohorts younger than 70 years. Although some surgeons anecdotally advocate for RSA in patients older than 70 years with primary osteoarthritis and an intact rotator cuff, we found no difference in outcomes for TSA based on our age cutoff. Given satisfactory results following TSA in patients 70 years of age and older, we do not routinely perform RSA for primary osteoarthritis with an intact rotator cuff solely based on age. Further studies and longer follow-up are needed to determine the optimal implant selection for elderly patients with primary osteoarthritis.

[Interarch distance is a target restorative space value: clinical decisionmaking of implant restoration guided by measured value]

When design an implant restoration for edentulous patients, many doctors ignore the sufficiency of the interarch distance (vertical distance) or horizontal distance of the patient to accommodate the superstructure and restoration before designing the implant plan. However, the connotation of measuring the interarch distance or horizontal distance has not been clarified in clinical practice. It is often based on visual estimation after operation, and the decision-making path of implant restoration is inverted, resulting in many mistakes regarding the restoration after implantation. The main reason is the lack of standardized paths and practical methods to use before surgery. This article recommended initially establishing a maxillo-mandibular relationship based on natural teeth, old dentures, or new ones and then using the height and horizontal distance or angle of the target restorative space, which was easier to grasp as the measured index. The minimum vertical distance (including the height of the gingival surface and the bone surface) and the horizontal distance (or the angle from the bone or gingival surface to the proposed occlusal plane) should be measured before operation. A decision tree of edentulous jaw restoration guided by the values of the repair space was established based on the measured values. This article clarified the measuring points and planes and thus provided a quantitative relationship basis for the design of implant restoration.

Value of Adaptive Trials and Surrogate Endpoints for Clinical Decision-Making in Rare Cancers

Despite high-level endorsement, the number of adaptive Phase II/III trials in rare cancers needs to be improved, with better understanding of their value for clinical decisions in daily practice. This paper describes approaches to trial design in rare cancers, which has been supplemented by a search of ClinicalTrials.gov for adaptive trial designs in rare cancer. In addition, an online survey of 3,200 oncologists was conducted. Practicing physicians were questioned on the importance of different evidence levels, types of adaptive trial design, and categories of surrogate endpoints for clinical decision making. The results of the online survey revealed that evidence from Phase II/III trials with an adaptive design and relatively small sample size was considered high value in rare cancer by 97% of responders, similar to the randomized controlled trial rating (82%). Surrogate clinical endpoints were considered valuable alternatives to overall survival by 80% of oncologists. Preferred adaptive designs were futility analysis, interim analysis, adaptive sample size, and adaptive randomization. In conclusion, rare cancer oncologists rate evidence from adaptive clinical trials with as high a value and importance for clinical decision making processes as conventional randomized controlled trials. All stakeholders have a vested interest in advances in clinical trial designs to ensure efficient and timely development of innovative medicinal products to allow more patients faster access to the pivotal treatment.

A novel method for typing of cesarean scar pregnancy based on size of cesarean scar diverticulum and its significance in clinical decision-making

AIM

There is currently no universally accepted method for typing of cesarean scar pregnancy (CSP) to guide the choice of treatment approach. We introduce a new method for typing CSP and investigate its clinical significance.

METHOD

Clinical data of 198 patients with CSP were collected and analyzed. The patients were divided into three types according to the size of their cesarean scar diverticula (CSD), measured by magnetic resonance imaging: type I (size of CSD ≤40 mm), type II (40 mm < size of CSD ≤70 mm) and type III (size of CSD >70 mm).

RESULTS

With increase in the type level, the risk of adverse events increased significantly (χ² = 36.345, P = 0.000). There was a significant difference in the choice of the treatment approaches in various types of the patients (χ² = 27.106, P = 0.000). With increase in the type level, the invasiveness level of the treatment approach increased significantly (R = 0.405, P = 0.000). Further analysis found two other factors that influenced treatment choice.

CONCLUSION

Our study, for the first time, demonstrates the value of size of CSD in typing of CSP and, thereby supplements the CSP typing system with a novel quantitative indicator. This typing method is of significance for evaluation of risk of CSP and guiding the choice of treatment approach. This typing method, combined with the two features of cesarean scar thickness and lesions protruding outside the uterine contour, will improve the risk assessment of CSP and the rationale of treatment plan formulation for this condition.

Role of Biomarkers in the Prediction of Serious Adverse Events after Syncope in Prehospital Assessment: A Multi-Center Observational Study

Syncope is defined as the nontraumatic, transient loss of awareness of rapid onset, short duration and with complete spontaneous recovery, and accounts for 1%–3% of all visits to the emergency department. The objective of this study was to evaluate the predictive capacity of the National Early Warning Score 2 (NEWS2) and prehospital lactate (pLA), individually and combined, at the prehospital level to detect patients with syncope at risk of early mortality (within 48 h) in the hospital environment. A prospective, multicenter cohort study without intervention was carried out on syncope patients aged over 18 who were given advanced life support and taken to the hospital. Our study included a total of 361 cases. Early mortality affected 21 patients (5.8%). The combined score formed by the NEWS2 and the pLA (NEWS2-L) obtained an AUC of 0.948 (95% CI: 0.88–1) and an odds ratio of 86.25 (95% CI: 11.36–645.57), which is significantly higher than that obtained by the NEWS2 or pLA in isolation (p = 0.018). The NEWS2-L can help stratify the risk in patients with syncope treated in the prehospital setting, with only the standard measurement of physiological parameters and pLA.

Rapid detection of respiratory organisms with FilmArray respiratory panel and its impact on clinical decisions in Shanghai, China, 2016-2018

BACKGROUND

In this study, we evaluated the diagnostic potential and clinical impact of an automated multiplex PCR platform (the FilmArray Respiratory Panel; FA-RP), specially designed for pathogen detection in respiratory tract infections in adults with unexplained pneumonia (UP).

METHODS

A total of 112 UP patients in Shanghai, China, were enrolled prospectively and assessed using the FA-RP from October 2016 to March 2018. We examined the test results and their influence on clinical decisions. Furthermore, as a control group, we retrospectively obtained the clinical data of 70 UP patients between October 2014 and March 2016 (before the FA-RP was available). The two patient groups were compared with respect to factors, including general antimicrobial use and defined daily dose (DDD) numbers.

RESULTS

Between October 2016 and March 2018, the positive rate obtained using FA-RP for UP was 76.8%. The primary pathogens in adults with UP were Influenza A/B (47.3%, 53/112). Compared with the patients before FA-RP was available, patients who underwent FA-RP testing had higher rates of antiviral drug use and antibiotic de-escalation during clinical treatment. FA-RP significantly decreased the total DDDs of antibiotic or antifungal drugs DDDs by 7 days after admission (10.6 ± 2.5 vs 14.1 ± 8.8, P < .01).

CONCLUSIONS

The FA-RP is a rapid and sensitive nucleic acid amplification test method for UP diagnosis in adults. The application of FA-RP may lead to a more accurately targeted antimicrobial treatment and reduced use of antibiotic/antifungal drugs.

Performance characteristics of automated clinical chemistry analyzers using commercial assay reagents contributing to quality assurance and clinical decision in a hospital laboratory

Background: Clinical laboratories provide essential diagnostic services that are essential in clinical decision making, contributing to the quality of healthcare. The performance of two Siemens ADVIA 1800 analyzers was characterized in a hospital Biochemistry laboratory in order to evaluate the analytical characteristics of such automated analyzer systems using nonoriginal assay reagents attempting to support laboratory quality service and crucial clinical decision making. Methods: We independently completed performance validation studies including trueness, precision, sensitivity as well as measurement of uncertainty and sigma metrics calculation for 25 biochemical parameters. Results: Trueness expressed as bias was less than 20% for both ADVIA 1800 analyzers. Within run and total precisions expressed as CV% were ≤9.85% on both analyzers for most parameters studied with few exceptions (Mg, TB, DB, Cl, HDL and UA) observed either in low or in high level samples and between the two analyzers. LoB, LoD and LoQ values produced by the two analyzers were comparable except Cl. Uncertainty values produced by the two analyzers were comparable with no significant differences. Quality performance of reagent assays was studied using the sigma metrics system. The sigma values were plotted on normalized method decision charts for graphical representation of assay performances for each analyzer. Conclusions: The two ADVIA systems, independently evaluated, showed consistent performance characteristics with certain discrepancies by several reagents. Sigma analysis was helpful for revealing the quality performance of non-original reagents supporting the need for strict assessment of quality assurance and in some instances optimization/improvement of assay methods.

Knowledge of sex and gender and related information needs in patients with traumatic brain injury: in-depth interview study

AIM

This research aimed to gain an understanding of biological sex and social gender phenomena experienced by patients with traumatic brain injury in recovery, and to understand the educational needs of this group.

METHODS

We conducted semi-structured interviews of 40 adult patients (22 men, 18 women) of different ages, education levels, and ethnicities, with diagnoses of mild and moderate-severe traumatic brain injury at the acute and chronic stages post-injury.

RESULTS

Applying classic content analysis with inductive coding, three overarching themes that limited patients' knowledge and subsequent efforts to obtain information on the topic emerged: (1) the complexity of sex and gender subject matters, (2) patients' dependence on others, and (3) uncertainty about the course of recovery. The first diminished the patient's desire to seek further information. Dependence on others and trust that others were in a better position to use the information, compelled patients to redirect the need for education to clinicians, significant others, and the public on the unique post-injury experiences of men and women. Uncertainty about what to expect in the acute phases, and a feeling of identity loss in the chronic phases, established patients' desire to seek out only the information they believed to be necessary for them to carry on with life.

CONCLUSIONS

In developing recommendations for patient education, variations in patients' knowledge and desire for information, and the reasons behind these variations, should be considered. Improving injury prognosis requires taking into account the gendered context of injury and recovery from it.IMPLICATIONS FOR REHABILITATIONSex/gender issues in traumatic brain injury are complex; the challenge is identifying which information is most relevant for patients; this research assessed patients' knowledge of and interest in sex/gender-related topics in traumatic brain injury.Evidence shows most patients unable to differentiate between sex and gender, but when asked about living as a man or woman with traumatic brain injury, disturbed gender roles and identities became evident.Gender shapes the health status trajectory and outcomes of patients with traumatic brain injury which becomes evident when attention is paid to patients' personal life stories.To improve traumatic brain injury prognosis, clinicians should tailor management plans taking into account gender, an amalgamation of biological, behavioural, cultural, and social characteristics of their patients.In research, explicit and consistent consideration of the interrelated constructs of sex and gender would produce a better understanding of the different mechanisms that shape the course of traumatic brain injury.

Visualization and Interpretation of Convolutional Neural Network Predictions in Detecting Pneumonia in Pediatric Chest Radiographs

Pneumonia affects 7% of the global population, resulting in 2 million pediatric deaths every year. Chest X-ray (CXR) analysis is routinely performed to diagnose the disease. Computer-aided diagnostic (CADx) tools aim to supplement decision-making. These tools process the handcrafted and/or convolutional neural network (CNN) extracted image features for visual recognition. However, CNNs are perceived as black boxes since their performance lack explanations. This is a serious bottleneck in applications involving medical screening/diagnosis since poorly interpreted model behavior could adversely affect the clinical decision. In this study, we evaluate, visualize, and explain the performance of customized CNNs to detect pneumonia and further differentiate between bacterial and viral types in pediatric CXRs. We present a novel visualization strategy to localize the region of interest (ROI) that is considered relevant for model predictions across all the inputs that belong to an expected class. We statistically validate the models' performance toward the underlying tasks. We observe that the customized VGG16 model achieves 96.2% and 93.6% accuracy in detecting the disease and distinguishing between bacterial and viral pneumonia respectively. The model outperforms the state-of-the-art in all performance metrics and demonstrates reduced bias and improved generalization.

Survival Prognosis in Very Old Adults

OBJECTIVES

To determine whether simple functional indicators are predictors of survival prognosis in very old adults.

DESIGN

In-person survey conducted over a 3-month period in 1998; assessment of survival over a 15-year follow-up period.

SETTING

Denmark.

PARTICIPANTS

All 3,600 Danes born in 1905 and living in Denmark in 1998, were invited to participate regardless of residence and health; 2,262 (63%) participated in the survey: 1,814 (80.2%) in person and 448 (19.8%) through a proxy.

MEASUREMENTS

Socioeconomic factors, medications and diseases, activities of daily living, physical performance, cognition, depression symptomatology, self-rated health, and all-cause mortality, evaluated as average remaining lifespan and chance of surviving to 100 years.

RESULTS

Men aged 92 to 93 had an overall 6.0% chance of surviving to 100 years, whereas the chance for women was 11.4%. Being able to rise without use of hands increased the chance for men to 11.2% (95% confidence interval (CI)=7.7-14.7) and for women to 22.0% (95% CI=18.9-25.1). When combining this with a Mini-Mental State Examination (MMSE) scores from 28 to 30, the chances were 21.7% (95% CI=11.5-31.9) for men and 34.2% (95% CI=24.8-43.5) for women.

CONCLUSION

Chair stand score combined with MMSE score is a quick and easy way to estimate overall chance of survival in very old adults, which is particularly relevant when treatment with potential side effects for nonacute diseases is considered.

The management of asthma in the phenotype and biomarker era: The proposal of a new diagnostic-therapeutic model

Treatment goals in asthma patients are the achievement of a good control of symptoms and the reduction of the risk of exacerbation. However, a "one-size-fits-all" therapeutic strategy is no longer appropriate to effectively pursue these goals, due to the heterogeneity of asthma. To make the treatment scenario even more complex, asthma patients often present comorbidities that may alter response to therapy. In addition, adherence to asthma treatment is poor. Given this complex and heterogeneous picture, the management of asthma is highly challenging. A clear diagnostic-therapeutic model of patients' care and the definition of the specific responsibilities of different healthcare providers appear necessary to improve clinical outcomes and better allocate healthcare resources. We present here a proposal for this model.

CD4 results with a bias larger than hundred cells per microliter can have a significant impact on the clinical decision during treatment initiation of HIV patients

BACKGROUND

CD4 counts are currently used to assess HIV patients for treatment eligibility and to monitor antiretroviral response to treatment. The emerging point-of-care devices could fill an important gap in resource-limited settings. However, the accuracy of CD4-counting instruments is diverse and data on how CD4 measurement errors have an impact on clinical decisions are lacking.

METHODS

Clinicians were queried on the use of CD4 results in their clinical setting. Subsequently, the effect of CD4 measurement errors on treatment initiation was put in a statistical model. Based on clinical CD4 databases from Belgium, Cambodia, and Senegal, the percentage of unchanged clinical decisions was calculated (treatment initiation should start within a 3-month delay [one visit]) for escalating CD4 measurement errors, taking into account the strict or preventive application of CD4 thresholds at 350 or 500 cells/µl used by clinicians.

RESULTS

To ensure that the treatment was initiated appropriately for at least 95% of patients, an error of 5 - 10 cells/µl was allowed. This is significantly smaller than the bias of ±50 cells/µl most clinicians considered acceptable. For limits of agreement (LOA, 1.96 x error) of 100 cells/µl, corresponding to most CD4 instrument evaluations, the misclassification rate of patients was found to be 3 - 28% at the threshold of 350 cells/µl (strict or flexible), and 13 - 20% at 500 cells/µl.

CONCLUSIONS

The maximum allowed CD4 bias on results from new CD4 technologies should not exceed 50 cells/µl (LOA 100 cells/µl) when applied for treatment initiation, to ensure at least 72% of correct clinical decisions. © 2016 International Clinical Cytometry Society.

Actionable clinical decisions based on comprehensive genomic evaluation in asymptomatic adults

Whole-exome sequencing (WES) arises as a new approach in diagnosing individuals affected by multigenic and complex phenotypes. Herein, we aim to examine whether WES is useful in screening asymptomatic individuals for actionable interventions, which has not yet been established. Twenty-five healthy adults underwent WES, bioinformatics, and manual curation of their exomes. Six participants (24%) harbored significant, management-changing variants in cancer predisposition genes, American College of Medical Genetics, and genomics reportable cardiac diseases and pharmacogenomic biomarkers that have led to clinical recommendations and interventions. Furthermore, more than 80% of the participants (21) carried 1–3 genetic variants with an associated clinical guideline for an altered drug dosing or administration based on the FDA’s table of pharmacogenomics. These results support WES potential not only to answer specific diagnostic questions presented by the relevant personal and/or family history but also to uncover clinically important genetic findings unrelated to the primary indication for sequencing.

Seclusion as a necessary vs. an appropriate intervention: a vignette study among mental health nurses

In a vignette study, mental health nurses were asked to score vignettes on necessity and appropriateness using a Likert scale. Sixty-nine clinical nurses from four mental health institutes scored 64 vignettes on necessity (there is no alternative) and appropriateness (seclusion supports patients' treatment) of seclusion simultaneously. Data analysis focused on the differences between both scores, and included general linear model analysis, t-test statistics and Kendall's tau. The t-test resulted in a significantly higher score on necessity than on appropriateness. Differences between both scores could be explained for 32% by a combination of nurse characteristics and vignette variables. Necessity and appropriateness were found to be strongly associated with each other, showing that underpinning patterns were largely the same. This research enhances the understanding of underlying factors that influence the decision of nurses to use seclusion. This is essential for the development of interventions aimed at the reduction of seclusion use in mental health practice.

Comparison of the SIMARD MD to Clinical Impression in Assessing Fitness to Drive in Patients with Cognitive Impairment

BACKGROUND

The assessment of fitness to drive in patients with cognitive impairment is complex. The SIMARD MD was developed to assist with assessing fitness to drive. This study compares the clinical decision made by a geriatrician regarding driving with the SIMARD MD score.

METHODS

Patients with a diagnosis of mild dementia or mild cognitive impairment, who had a SIMARD MD test, were included in the sample. A retrospective chart review was completed to gather diagnosis, driving status, and cognitive and functional information.

RESULTS

Sixty-three patients were identified and 57 met the inclusion criteria. The mean age was 77.1 years (SD 8.9). The most common diagnosis was Alzheimer's disease in 22 (38.6%) patients. The mean MMSE score was 24.9 (SD 3.34) and the mean MoCA was 19.9 (SD 3.58). The mean SIMARD MD score was 37.2 (SD 19.54). Twenty-four patients had a SIMARD MD score ≤ 30, twenty-eight between 31-70, and five scored > 70. The SIMARD MD scores did not differ significantly compared to the clinical decision (ANOVA p value = 0.14).

CONCLUSIONS

There was no association between the SIMARD MD scores and the geriatricians' clinical decision regarding fitness to drive in persons with mild dementia or mild cognitive impairment.

Factors associated with clinical inertia: an integrative review

Failure to initiate or intensify therapy according to evidence-based guidelines is increasingly being acknowledged as a phenomenon that contributes to inadequate management of chronic conditions, and is referred to as clinical inertia. However, the number and complexity of factors associated with the clinical reasoning that underlies the decision-making processes in medicine calls for a critical examination of the consistency of the concept. Indeed, in the absence of information on and justification of treatment decisions that were made, clinical inertia may be only apparent, and actually reflect good clinical practice. This integrative review seeks to address the factors generally associated with clinical inaction, in order to better delineate the concept of true clinical inertia.

Bedside clinical guidelines: the missing link

Clinical guidelines for acute general (adult) medicine, general (adult) surgery, nursing and acute paediatrics, for use at the bedside, were developed over 10 years in North Staffordshire. The guidelines have been adopted by 15 other hospitals, all members of the Bedside Clinical Guidelines Partnership. The guidelines include advice on clinical management, prescribing aids, and practical procedures. Recommendations are validated against published evidence, and provide the 'missing link' between this evidence and practical clinical care, by taking current consensus into account. The guidelines are clear, brief and specific, informing and guiding the actions of clinicians. Annual updating involves checking evidence and compatibility with national recommendations, and soliciting feedback from users to eliminate ambiguity or misunderstanding. Continued human effort and financial investment are required to ensure that the guidelines remain a 'living' document.

Patients and doctors: rights and responsibilities in the NHS

Our society is very concerned with endowing and protecting people's rights and the existence of a National Health Service in this country has allowed such concepts to be applied to medical care. It is not clear, however, whether the concept of rights helps either doctors or patients, and it may in fact be misleading or even damaging. A discussion of the suitability of rights ethics to the healthcare context is presented, particularly highlighting the problems of attributing positive rights. The way in which rights create corresponding duties and responsibilities, and the particular problems that this creates for our health service is also addressed. Finally, in the light of the ongoing changes in the doctor-patient relationship, the future balance of rights and responsibilities in healthcare and the impact this will have on clinical decision-making is discussed.