Predicting Non-Adherence with Outpatient Colonoscopy Using a Novel Electronic Tool that Measures Prior Non-Adherence

Development and Validation of a Predictive Model of Prostate Screening Compliance: A Nationwide Population-Based Study

INTRODUCTION

Prostate cancer (PCa) is the second most common cancer in men worldwide, with significant incidence and mortality, particularly in Mexico, where diagnosis at advanced stages is common. Early detection through screening methods such as digital rectal examination and prostate-specific antigen testing is essential to improve outcomes. Despite current efforts, compliance with prostate screening (PS) remains low due to several barriers. This study aims to develop and validate a predictive model for PCa screening compliance in Mexican men.

MATERIALS AND METHODS

Retrospective observational design with data from the Mexican Health and Aging Study (MHAS). Participants were men aged 50-69 from three cohorts: development/internal validation, temporal validation, and external validation. Key predictors were identified using relaxed Least Absolute Shrinkage and Selection Operator (LASSO) regression, and model performance was assessed using the area under the curve (AUC) from receiver operating characteristic (ROC) analyses, along with calibration and decision curve analysis (DCA). A web nomogram was also developed.

RESULTS

The final model included seven key predictors. AUC values indicated good predictive performance: 0.783 for the training subgroup, 0.722 for the test subgroup, 0.748 for the time cohort, and 0.756 for the external cohort, with sensitivities of 73.5%. The DCA demonstrated the superior clinical utility of the model compared to the reference strategies.

CONCLUSIONS

The predictive model developed for performance to PCa screening is robust across different cohorts and highlights critical factors influencing performance. The accompanying web-based nomogram enhances clinical applicability and supports interventions aimed at improving PCa screening rates among Mexican men.

A foundation systematic review of natural language processing applied to gastroenterology & hepatology

OBJECTIVE

This review assesses the progress of NLP in gastroenterology to date, grades the robustness of the methodology, exposes the field to a new generation of authors, and highlights opportunities for future research.

DESIGN

Seven scholarly databases (ACM Digital Library, Arxiv, Embase, IEEE Explore, Pubmed, Scopus and Google Scholar) were searched for studies published between 2015 and 2023 that met the inclusion criteria. Studies lacking a description of appropriate validation or NLP methods were excluded, as were studies ufinavailable in English, those focused on non-gastrointestinal diseases and those that were duplicates. Two independent reviewers extracted study information, clinical/algorithm details, and relevant outcome data. Methodological quality and bias risks were appraised using a checklist of quality indicators for NLP studies.

RESULTS

Fifty-three studies were identified utilising NLP in endoscopy, inflammatory bowel disease, gastrointestinal bleeding, liver and pancreatic disease. Colonoscopy was the focus of 21 (38.9%) studies; 13 (24.1%) focused on liver disease, 7 (13.0%) on inflammatory bowel disease, 4 (7.4%) on gastroscopy, 4 (7.4%) on pancreatic disease and 2 (3.7%) on endoscopic sedation/ERCP and gastrointestinal bleeding. Only 30 (56.6%) of the studies reported patient demographics, and only 13 (24.5%) had a low risk of validation bias. Thirty-five (66%) studies mentioned generalisability, but only 5 (9.4%) mentioned explainability or shared code/models.

CONCLUSION

NLP can unlock substantial clinical information from free-text notes stored in EPRs and is already being used, particularly to interpret colonoscopy and radiology reports. However, the models we have thus far lack transparency, leading to duplication, bias, and doubts about generalisability. Therefore, greater clinical engagement, collaboration, and open sharing of appropriate datasets and code are needed.

Emerging applications of NLP and large language models in gastroenterology and hepatology: a systematic review

Background and aim

In the last years, natural language processing (NLP) has transformed significantly with the introduction of large language models (LLM). This review updates on NLP and LLM applications and challenges in gastroenterology and hepatology.

Methods

Registered with PROSPERO (CRD42024542275) and adhering to PRISMA guidelines, we searched six databases for relevant studies published from 2003 to 2024, ultimately including 57 studies.

Results

Our review of 57 studies notes an increase in relevant publications in 2023-2024 compared to previous years, reflecting growing interest in newer models such as GPT-3 and GPT-4. The results demonstrate that NLP models have enhanced data extraction from electronic health records and other unstructured medical data sources. Key findings include high precision in identifying disease characteristics from unstructured reports and ongoing improvement in clinical decision-making. Risk of bias assessments using ROBINS-I, QUADAS-2, and PROBAST tools confirmed the methodological robustness of the included studies.

Conclusion

NLP and LLMs can enhance diagnosis and treatment in gastroenterology and hepatology. They enable extraction of data from unstructured medical records, such as endoscopy reports and patient notes, and for enhancing clinical decision-making. Despite these advancements, integrating these tools into routine practice is still challenging. Future work should prospectively demonstrate real-world value.

Decision analysis framework for predicting no-shows to appointments using machine learning algorithms

BACKGROUND

No-show to medical appointments has significant adverse effects on healthcare systems and their clients. Using machine learning to predict no-shows allows managers to implement strategies such as overbooking and reminders targeting patients most likely to miss appointments, optimizing the use of resources.

METHODS

In this study, we proposed a detailed analytical framework for predicting no-shows while addressing imbalanced datasets. The framework includes a novel use of z-fold cross-validation performed twice during the modeling process to improve model robustness and generalization. We also introduce Symbolic Regression (SR) as a classification algorithm and Instance Hardness Threshold (IHT) as a resampling technique and compared their performance with that of other classification algorithms, such as K-Nearest Neighbors (KNN) and Support Vector Machine (SVM), and resampling techniques, such as Random under Sampling (RUS), Synthetic Minority Oversampling Technique (SMOTE) and NearMiss-1. We validated the framework using two attendance datasets from Brazilian hospitals with no-show rates of 6.65% and 19.03%.

RESULTS

From the academic perspective, our study is the first to propose using SR and IHT to predict the no-show of patients. Our findings indicate that SR and IHT presented superior performances compared to other techniques, particularly IHT, which excelled when combined with all classification algorithms and led to low variability in performance metrics results. Our results also outperformed sensitivity outcomes reported in the literature, with values above 0.94 for both datasets.

CONCLUSION

This is the first study to use SR and IHT methods to predict patient no-shows and the first to propose performing z-fold cross-validation twice. Our study highlights the importance of avoiding relying on few validation runs for imbalanced datasets as it may lead to biased results and inadequate analysis of the generalization and stability of the models obtained during the training stage.

Associations between Missed Colonoscopy Appointments and Multiple Prior Adherence Behaviors in an Integrated Healthcare System: An Observational Study

BACKGROUND

Missed colonoscopy appointments delay screening and treatment for gastrointestinal disorders. Prior nonadherence with other care components may be associated with missed colonoscopy appointments.

OBJECTIVE

To assess variability in prior adherence behaviors and their association with missed colonoscopy appointments.

DESIGN

Retrospective cohort study.

PARTICIPANTS

Patients scheduled for colonoscopy in an integrated healthcare system between January 2016 and December 2018.

MAIN MEASURES

Prior adherence behaviors included: any missed outpatient appointment in the previous year; any missed gastroenterology clinic or colonoscopy appointment in the previous 2 years; and not obtaining a bowel preparation kit pre-colonoscopy. Other sociodemographic, clinical, and system characteristics were included in a multivariable model to identify independent associations between prior adherence behaviors and missed colonoscopy appointments.

KEY RESULTS

The median age of the 57,590 participants was 61 years; 52.8% were female and 73.4% were white. Of 77,684 colonoscopy appointments, 3,237 (4.2%) were missed. Individuals who missed colonoscopy appointments were more likely to have missed a previous primary care appointment (62.5% vs. 38.4%), a prior gastroenterology appointment (18.4% vs. 4.7%) or not to have picked up a bowel preparation kit (42.4% vs. 17.2%), all p < 0.001. Correlations between the three adherence measures were weak (phi < 0.26). The rate of missed colonoscopy appointments increased from 1.8/100 among individuals who were adherent with all three prior care components to 24.6/100 among those who were nonadherent with all three care components. All adherence variables remained independently associated with nonadherence with colonoscopy in a multivariable model that included other covariates; adjusted odds ratios (with 95% confidence intervals) were 1.6 (1.5-1.8) for outpatient appointments, 1.9 (1.7-2.1) for gastroenterology appointments, and 3.1 (2.9-3.4) for adherence with bowel preparation kits, respectively.

CONCLUSIONS

Three prior adherence behaviors were independently associated with missed colonoscopy appointments. Studies to predict adherence should use multiple, complementary measures of prior adherence when available.

Colorectal cancer screening barriers and facilitators among Jordanians: A cross-sectional study

The factors affecting the adherence of Jordanians to colorectal cancer (CRC) screening remain underexplored. We examined the inhibitory and facilitating factors that influence the uptake of CRC screening among Jordanians. We conducted questionnaire interviews between April 2020 and June 2021 with 861 Jordanians aged 50-75. We analyzed the differences between proportions using the chi-square test. Binary logistic regression was conducted to determine factors associated with awareness of CRC and its screening. Of all participants, 41.7 % were aware of the necessity of screening for CRC, and 27.2 % were aware of at least one of the tests for CRC screening. However, only 17.2 % of participants underwent screening. In the multivariate analysis, participants with higher income (p-value < 0.001, odds ratio[OR] = 1.9, 95 % confidence interval [CI]: 1.4-2.7), higher level of education (p-value < 0.001, OR = 2.6, 95 % CI: 1.8-3.7), family history of colon cancer (p-value < 0.001, OR = 2.8, 95 % CI = 1.7-4.5), and those who had been screened for other cancers (p-value = 0.003, OR = 1.7, 95 % CI: 1.2-2.5) were more aware of the necessity of screening. Concerning barriers to screening, 'feeling well,' lack of physician endorsement, and difficult access to health care were the most commonly reported inhibitory factors (53.9 %, 52.3 %, and 31.9 %, respectively). The most commonly stated incentivizing factor was physician endorsement (82.3 %). Screening rates for CRC in eligible Jordanians remain low, albeit more than one-third of participants are aware of the necessity of screening. Enhanced awareness of barriers and incentivizing factors should help to prioritize national strategies to improve screening rates.

Recommended practices and ethical considerations for natural language processing-assisted observational research: A scoping review

An increasing number of studies have reported using natural language processing (NLP) to assist observational research by extracting clinical information from electronic health records (EHRs). Currently, no standardized reporting guidelines for NLP-assisted observational studies exist. The absence of detailed reporting guidelines may create ambiguity in the use of NLP-derived content, knowledge gaps in the current research reporting practices, and reproducibility challenges. To address these issues, we conducted a scoping review of NLP-assisted observational clinical studies and examined their reporting practices, focusing on NLP methodology and evaluation. Through our investigation, we discovered a high variation regarding the reporting practices, such as inconsistent use of references for measurement studies, variation in the reporting location (reference, appendix, and manuscript), and different granularity of NLP methodology and evaluation details. To promote the wide adoption and utilization of NLP solutions in clinical research, we outline several perspectives that align with the six principles released by the World Health Organization (WHO) that guide the ethical use of artificial intelligence for health.

Factors associated with non-attendance at appointments in the gastroenterology endoscopy unit: a retrospective cohort study

Background and Aims

Gastrointestinal (GI) endoscopy is a limited health resource because of a scarcity of qualified personnel and limited availability of equipment. Non-adherence to endoscopy appointments therefore wastes healthcare resources and may compromise the early detection and treatment of GI diseases. We aimed to identify factors affecting non-attendance at scheduled appointments for GI endoscopy and thus improve GI healthcare outcomes.

Methods

This was a single-center retrospective cohort study performed at a tertiary hospital gastroenterology endoscopy unit, 12 months before and 12 months after the start of the COVID-19 pandemic. We used multiple logistic regression analysis to identify variables associated with non-attendance at scheduled appointments.

Results

Overall, 5,938 appointments were analyzed, and the non-attendance rate was 18.3% (1,088). The non-attendance rate fell significantly during the pandemic (22.6% vs. 11.6%, p < 0.001). Multivariable regression analysis identified the absence of deep sedation (OR: 3.253, 95% CI [2.386-4.435]; p < 0.001), a referral from a physician other than a gastroenterologist (OR: 1.891, 95% CI [1.630-2.193]; p < 0.001), a longer lead time (OR: 1.006, 95% CI [1.004-1.008]; p < 0.001), and female gender (OR: 1.187, 95% CI [1.033-1.363]; p = 0.015) as associated with appointment non-attendance.

Conclusions

Female patients, those undergoing endoscopic procedures without deep sedation, those referred by physicians other than gastroenterologists, and with longer lead time were less likely to adhere to appointments. Precautions should be directed at patients with one or more of these risk factors, and for those scheduled for screening procedures during the COVID-19 pandemic.

Modelling the no-show of patients to exam appointments of computed tomography

BACKGROUND

Patients' no-shows negatively impact healthcare systems, leading to resources' underutilisation, efficiency loss, and cost increase. Predicting no-shows is key to developing strategies that counteract their effects. In this paper, we propose a model to predict the no-show of ambulatory patients to exam appointments of computed tomography at the Radiology department of a large Brazilian public hospital.

METHODS

We carried out a retrospective study on 8382 appointments to computed tomography (CT) exams between January and December 2017. Penalised logistic regression and multivariate logistic regression were used to model the influence of 15 candidate variables on patients' no-shows. The predictive capabilities of the models were evaluated by analysing the Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC).

RESULTS

The no-show rate in computerised tomography exams appointments was 6.65%. The two models performed similarly in terms of AUC. The penalised logistic regression model was selected using the parsimony criterion, with 8 of the 15 variables analysed appearing as significant. One of the variables included in the model (number of exams scheduled in the previous year) had not been previously reported in the related literature.

CONCLUSIONS

Our findings may be used to guide the development of strategies to reduce the no-show of patients to exam appointments.

Precision Patient Navigation to Improve Rates of Follow-up Colonoscopy, An Individual Randomized Effectiveness Trial

BACKGROUND

Colorectal cancer screening by annual fecal immunochemical test (FIT) with follow-up on abnormal results is a cost-effective strategy to reduce colorectal cancer incidence and mortality. Unfortunately, many patients with abnormal results do not complete a follow-up colonoscopy. We tested whether navigation targeted to patients who are unlikely to complete the procedure may improve adherence and long-term outcomes.

METHODS

Study participants were patients at a large, integrated health system (Kaiser Permanente Northwest) who were ages 50 to 75 and were due for a follow-up colonoscopy after a recent abnormal FIT result. Probability of adherence to follow-up was estimated at baseline using a predictive risk model. Patients whose probability was 70% or lower were randomized to receive patient navigation or usual care, with randomization stratified by probability category (<50%, 50% < 60%, 60% < 65%, 65% ≤ 70%). We compared colonoscopy completion within 6 months between the navigation and usual care groups using Cox proportional hazards regression.

RESULTS

Participants (n = 415; 200 assigned to patient navigation, 215 to usual care) had a mean age of 62 years, 54% were female, and 87% were non-Hispanic white. By 6 months, 76% of the patient navigation group had completed a colonoscopy, compared with 65% of the usual care group (HR = 1.35; 95% confidence interval, 1.07-1.72; log-rank P value = 0.027).

CONCLUSIONS

In this randomized trial, patient navigation led to improvements in follow-up colonoscopy adherence.

IMPACT

More research is needed to assess the value of precision-directed navigation programs.

Short Message Service reminders reduce outpatient colonoscopy nonattendance rate: A randomized controlled study

BACKGROUND AND AIM

Nonattendance of outpatient colonoscopy leads to inefficient use of health-care resources. We aimed to study the effectiveness of using Short Message Service (SMS) reminder prior in patients scheduled for outpatient colonoscopy on their nonattendance rate.

METHODS

Patients who scheduled for an outpatient colonoscopy and had access of SMS were recruited from three clinics in Hong Kong. Patients were randomized to SMS group and standard care (SC) group. All patients were given a written appointment slip on the booking date. In addition, patients in the SMS group received an SMS reminder 7-10 days before their colonoscopy appointment. Patients' demographics, attendance, colonoscopy completion, and bowel preparation quality were recorded. Logistic regression was performed to identify predictors of nonattendance.

RESULTS

From November 2013 to October 2019, a total of 2225 eligible patients were recruited. A total of 1079 patients were allocated to the SMS group and 1146 to the SC group. The nonattendance rate of patients in the SMS group was significantly lower than that in the SC group (8.9% vs 11.9%, P = 0.022). There were no significant differences in their baseline characteristics and colonoscopy completion rate and bowel preparation quality. A trend towards a higher rate of adequate bowel preparation was observed in the SMS group when compared with the SC group (69.9% vs 65.8%, P = 0.053). Independent predictors for nonattendance included younger age, underprivilege, and existing diabetes.

CONCLUSIONS

An SMS reminder for outpatient colonoscopy is effective in reducing the nonattendance rate and may potentially improve the bowel preparation quality.

Evaluation of Patient No-Shows in a Tertiary Hospital: Focusing on Modes of Appointment-Making and Type of Appointment

No-show appointments waste resources and decrease the sustainability of care. This study is an attempt to evaluate patient no-shows based on modes of appointment-making and types of appointments. We collected hospital information system data and appointment data including characteristics of patients, service providers, and clinical visits over a three-month period (1 September 2018 to 30 November 2018), at a large tertiary hospital in Seoul, Korea. We used multivariate logistic regression analyses to identify the factors associated with no-shows (Model 1). We further assessed no-shows by including the interaction term (“modes of appointment-making” X “type of appointment”) (Model 2). Among 1,252,127 appointments, the no-show rate was 6.12%. Among the modes of appointment-making, follow-up and online/telephone appointment were associated with higher odds of no-show compared to walk-in. Appointments for treatment and surgery had higher odds ratios of no-show compared to consultations. Tests for the interaction between the modes of appointment-making and type of appointment showed that follow-up for examination and online/telephone appointments for treatment and surgery had much higher odds ratios of no-shows. Other significant factors of no-shows include age, type of insurance, time of visit, lead time (time between scheduling and the appointment), type of visits, doctor’s position, and major diagnosis. Our results suggest that future approaches for predicting and addressing no-show should also consider and analyze the impact of modes of appointment-making and type of appointment on the model of prediction.

Evolving Role and Future Directions of Natural Language Processing in Gastroenterology

In line with the current trajectory of healthcare reform, significant emphasis has been placed on improving the utilization of data collected during a clinical encounter. Although the structured fields of electronic health records have provided a convenient foundation on which to begin such efforts, it was well understood that a substantial portion of relevant information is confined in the free-text narratives documenting care. Unfortunately, extracting meaningful information from such narratives is a non-trivial task, traditionally requiring significant manual effort. Today, computational approaches from a field known as Natural Language Processing (NLP) are poised to make a transformational impact in the analysis and utilization of these documents across healthcare practice and research, particularly in procedure-heavy sub-disciplines such as gastroenterology (GI). As such, this manuscript provides a clinically focused review of NLP systems in GI practice. It begins with a detailed synopsis around the state of NLP techniques, presenting state-of-the-art methods and typical use cases in both clinical settings and across other domains. Next, it will present a robust literature review around current applications of NLP within four prominent areas of gastroenterology including endoscopy, inflammatory bowel disease, pancreaticobiliary, and liver diseases. Finally, it concludes with a discussion of open problems and future opportunities of this technology in the field of gastroenterology and health care as a whole.

Will They Show? Predictors of Nonattendance for Scheduled Screening Colonoscopies at a Safety Net Hospital

BACKGROUND

Colonoscopy can reduce colorectal cancer-related mortality by up to 90% through early detection and polyp removal. Despite this, nonattendance rates for scheduled colonoscopies have been reported ranging from 4.1% to as high as 67% depending on the population studied.

AIM

The aim of the study was to measure the nonattendance rate for scheduled screening colonoscopy at a large safety net hospital and identify predictors of nonattendance within this patient population.

MATERIALS AND METHODS

This was a population-based study of 1186 adults who were scheduled to undergo screening colonoscopy at a safety net hospital as part of their routine preventative health program. Health systems variables were assessed including procedure time and scheduling patterns as well as patient-centered variables such as socioeconomic indicators and specific comorbid diagnoses. Associations with nonattendance were examined by univariate and multivariate logistic regression.

RESULTS

The overall rate of nonattendance for scheduled screening colonoscopy was 33%. A multivariate model was constructed to predict nonattendance revealing that private payer status [odds ratio (OR)=0.368, 95% confidence interval (CI): 0.225, 0.602] and prior colonoscopy (OR=0.371, 95% CI: 0.209, 0.656) were associated with greater attendance rates. Chronic obstructive pulmonary disease (OR=2.034, 95% CI: 1.239, 3.341), afternoon procedure time (OR=1.807, 95% CI: 1.137, 2.871), and a greater interval time between the date the colonoscopy was ordered and the date the colonoscopy was scheduled to occur (OR=1.005, 95% CI: 1.001, 1.009) were independently associated with nonattendance when controlling for age, sex, and race.

CONCLUSIONS

Specific predictors for scheduled screening colonoscopy nonattendance at a safety net hospital can be identified. These findings can be used to tailor community-based interventions to improve colorectal cancer screening rates.

Patient No-Show Prediction: A Systematic Literature Review

Nowadays, across the most important problems faced by health centers are those caused by the existence of patients who do not attend their appointments. Among others, these patients cause loss of revenue to the health centers and increase the patients’ waiting list. In order to tackle these problems, several scheduling systems have been developed. Many of them require predicting whether a patient will show up for an appointment. However, obtaining these estimates accurately is currently a challenging problem. In this work, a systematic review of the literature on predicting patient no-shows is conducted aiming at establishing the current state-of-the-art. Based on a systematic review following the PRISMA methodology, 50 articles were found and analyzed. Of these articles, 82% were published in the last 10 years and the most used technique was logistic regression. In addition, there is significant growth in the size of the databases used to build the classifiers. An important finding is that only two studies achieved an accuracy higher than the show rate. Moreover, a single study attained an area under the curve greater than the 0.9 value. These facts indicate the difficulty of this problem and the need for further research.

A survey on colonoscopy shows poor understanding of its protective value and widespread misconceptions across Europe

Background

Colonoscopy is a valuable screening tool for colorectal cancer. However, patients experience anxiety when faced with attending a first colonoscopy, and negative attitudes may contribute to non-attendance. Few studies in Europe have explored these attitudes, despite increasing colorectal cancer incidence.

Study aim

We conducted an online survey of the public in five European Union countries (France, Germany, Italy, Spain, and the UK), with the aim of understanding public knowledge of, perceptions of, and attitudes towards, colonoscopy and bowel preparation, amongst colonoscopy-naïve respondents. Attitudes towards colonoscopy were also gathered from colonoscopy-experienced patients.

Methods

Survey answers were gathered from 2,500 colonoscopy-naïve respondents and 500 colonoscopy-experienced patients, divided equally between countries.

Results

Across Europe, 72% of colonoscopy-naïve respondents showed receptiveness to colonoscopy if advised by their doctor to receive one, but only 45% understood its use to prevent colorectal cancer. Forty-three percent of colonoscopy-experienced respondents would still be embarrassed about having another colonoscopy, although 59% said that the experience had been better than expected. Colonoscopy-experienced respondents had greater aversion to bowel preparation than colonoscopy-naïve respondents (47% vs 26%), and 67% of colonoscopy-naïve respondents thought that only 1 litre of bowel preparation or less is required. Italians and the Spanish wanted more information than on average in Europe, while Germans had more realistic expectations of bowel preparation.

Discussion

There are perceptual gaps amongst the public around the purpose of colonoscopies, the subjective experience of the colonoscopy procedure, and the quantity of bowel preparation needed. These concerns could be mitigated by better education and using lower-volume bowel preparation techniques.

Conclusion

Europeans would have a colonoscopy, but its preventive medical purpose is poorly understood and there are misconceptions around the process. Further education about the procedure, its benefits and bowel preparation is vital to improve understanding and compliance.

Colonoscopy education delivered via the patient portal does not improve adherence to scheduled first-time screening colonoscopy

Background and study aims  Non-adherence to scheduled colonoscopy burdens endoscopic practices and innovative approaches to improve adherence are needed. We aimed to assess the effect of an educational video emphasizing colonoscopy importance delivered through the electronic health record patient portal upon "no-show" and late cancellation rates (non-adherence) in patients scheduled for first-time screening colonoscopy. Patients and methods  We conducted a single center randomized controlled trial among patients scheduled for their first screening colonoscopy. Patients were randomized to routine care ("control") or video education ("video"). Control patients received a portal message 14 days prior to colonoscopy date; video patients additionally received a link to the educational video. Results  In total, 830 patients (59 % female, median age 55 years) were randomized ("control": 406; "video": 424). Nearly all (88 %) opened the message; in the video arm, most (72 %) watched a majority of the video. Overall, 80 % attended their scheduled colonoscopy appointment (late cancel: 18 %, "no show": 1 %) and 90 % underwent colonoscopy within 3 months of appointment. Adherence rates did not differ between video and control arms for the scheduled appointment (OR 1.2, CI 0.9-1.8) or for colonoscopy within 3 months of scheduled appointment (OR 1.3, CI 0.8-2.1). Bowel preparation quality did not differ between the groups. Conclusion  Most patients scheduled for colonoscopy will open a patient portal message and, when delivered, watch an educational video. However, delivery of an educational video two weeks prior to screening colonoscopy appointment did not improve adherence.

Patient randomized trial of a targeted navigation program to improve rates of follow-up colonoscopy in community health centers

BACKGROUND

Colorectal cancer (CRC) screening by annual fecal immunochemical test (FIT) is an accessible and cost-effective strategy to lower CRC incidence and mortality. However, this mode of screening depends on follow-up colonoscopy after a positive FIT result. Unfortunately, nearly one-half of FIT-positive patients fail to complete this essential screening component. Patient navigation may improve follow-up colonoscopy adherence. To deliver patient navigation cost-effectively, health centers could target navigation to patients who are unlikely to complete the procedure on their own.

OBJECTIVES

The Predicting and Addressing Colonoscopy Non-adherence in Community Settings (PRECISE) clinical trial will validate a risk model of follow-up colonoscopy adherence and test whether patient navigation raises rates of colonoscopy adherence overall and among patients in each probability stratum (low, moderate, and high probability of adherence without intervention).

METHODS

PRECISE is a collaboration with a large community health center whose patient population is 37% Latino. Eligible patients will be aged 50-75, have an abnormal FIT result in the past month, and be due for a follow-up colonoscopy. Patients will be randomized to patient navigation or usual care. Primary outcomes will be colonoscopy completion within one year of a positive FIT result, cost, and cost-effectiveness. Secondary outcomes will include time to colonoscopy receipt, adequacy of bowel prep, and communication of results to primary care providers. Primary and secondary outcomes will be reported overall and by probability stratum.

DISCUSSION

This innovative clinical trial will test the effectiveness and financial feasibility of using a precision health intervention to improve CRC screening completion in community health centers.

TRIAL REGISTRATION

National Clinical Trial (NCT) Identifier: NCT03925883.

Data Analytics and Modeling for Appointment No-show in Community Health Centers

Objectives: Using predictive modeling techniques, we developed and compared appointment no-show prediction models to better understand appointment adherence in underserved populations. Methods and Materials: We collected electronic health record (EHR) data and appointment data including patient, provider and clinical visit characteristics over a 3-year period. All patient data came from an urban system of community health centers (CHCs) with 10 facilities. We sought to identify critical variables through logistic regression, artificial neural network, and naïve Bayes classifier models to predict missed appointments. We used 10-fold cross-validation to assess the models’ ability to identify patients missing their appointments. Results: Following data preprocessing and cleaning, the final dataset included 73811 unique appointments with 12,392 missed appointments. Predictors of missed appointments versus attended appointments included lead time (time between scheduling and the appointment), patient prior missed appointments, cell phone ownership, tobacco use and the number of days since last appointment. Models had a relatively high area under the curve for all 3 models (e.g., 0.86 for naïve Bayes classifier). Discussion: Patient appointment adherence varies across clinics within a healthcare system. Data analytics results demonstrate the value of existing clinical and operational data to address important operational and management issues. Conclusion: EHR data including patient and scheduling information predicted the missed appointments of underserved populations in urban CHCs. Our application of predictive modeling techniques helped prioritize the design and implementation of interventions that may improve efficiency in community health centers for more timely access to care. CHCs would benefit from investing in the technical resources needed to make these data readily available as a means to inform important operational and policy questions.

Cloud-based multi-media systems for patient education and adherence: a pilot study to explore patient compliance with colonoscopy procedure preparation

Technology based patient education and adherence approaches are increasingly utilized to instruct and remind patients to prepare correctly for medical procedures. This study examines the interaction between two primary factors: patterns of patient adherence to challenging medical preparation procedures; and the demonstrated, measurable potential for cloud-based multi-media information technology (IT) interventions to improve patient adherence. An IT artifact was developed through prior design science research to serve information, reminders, and online video instruction modules to patients. The application was tested with 297 patients who were assessed clinically by physicians. Results indicate modest potential (43.4% relative improvement) for the IT-based approach for improving patient adherence to endoscopy preparations. Purposively designed cloud-based applications hold promise for aiding patients with complex medical procedure preparation. Health care provider involvement in the design and evaluation of a patient application may be an effective strategy to produce medical evidence and encourage the adoption of adherence apps.

Predicting scheduled hospital attendance with artificial intelligence

Failure to attend scheduled hospital appointments disrupts clinical management and consumes resource estimated at £1 billion annually in the United Kingdom National Health Service alone. Accurate stratification of absence risk can maximize the yield of preventative interventions. The wide multiplicity of potential causes, and the poor performance of systems based on simple, linear, low-dimensional models, suggests complex predictive models of attendance are needed. Here, we quantify the effect of using complex, non-linear, high-dimensional models enabled by machine learning. Models systematically varying in complexity based on logistic regression, support vector machines, random forests, AdaBoost, or gradient boosting machines were trained and evaluated on an unselected set of 22,318 consecutive scheduled magnetic resonance imaging appointments at two UCL hospitals. High-dimensional Gradient Boosting Machine-based models achieved the best performance reported in the literature, exhibiting an area under the receiver operating characteristic curve of 0.852 and average precision of 0.511. Optimal predictive performance required 81 variables. Simulations showed net potential benefit across a wide range of attendance characteristics, peaking at £3.15 per appointment at current prevalence and call efficiency. Optimal attendance prediction requires more complex models than have hitherto been applied in the field, reflecting the complex interplay of patient, environmental, and operational causal factors. Far from an exotic luxury, high-dimensional models based on machine learning are likely essential to optimal scheduling amongst other operational aspects of hospital care. High predictive performance is achievable with data from a single institution, obviating the need for aggregating large-scale sensitive data across governance boundaries.

Social Disadvantage, Healthcare Utilization, and Colorectal Cancer Screening: Leveraging Longitudinal Patient Address and Health Records Data

BACKGROUND

Social disadvantage predicts colorectal cancer outcomes across the cancer care continuum for many populations and places. For medically underserved populations, social disadvantage is likely intersectional-affecting individuals at multiple levels and through membership in multiple disadvantaged groups. However, most measures of social disadvantage are cross-sectional and limited to race, ethnicity, and income. Linkages between electronic health records (EHR) and external datasets offer rich, multilevel measures that may be more informative.

METHODS

We identified urban safety-net patients eligible and due for colorectal cancer screening from the Parkland-UT Southwestern PROSPR cohort. We assessed one-time screening receipt (via colonoscopy or fecal immunochemical test) in the 18 months following cohort entry via the EHR. We linked EHR data to housing and Census data to generate measures of social disadvantage at the parcel- and block-group level. We evaluated the association of these measures with screening using multilevel logistic regression models controlling for sociodemographics, comorbidity, and healthcare utilization.

RESULTS

Among 32,965 patients, 45.1% received screening. In adjusted models, residential mobility, residence type, and neighborhood majority race were associated with colorectal cancer screening. Nearly all measures of patient-level social disadvantage and healthcare utilization were significant.

CONCLUSIONS

Address-based linkage of EHRs to external datasets may have the potential to expand meaningful measurement of multilevel social disadvantage. Researchers should strive to use granular, specific data in investigations of social disadvantage.

IMPACT

Generating multilevel measures of social disadvantage through address-based linkages efficiently uses existing EHR data for applied, population-level research.

Colorectal Cancer Screening: The Role of Psychological, Social and Background Factors in Decision-making Process

Since ColoRectal Cancer (CRC) remains the third cause of cancer death in the world, a better understanding of the reasons underlying poor adherence to and delay in undergoing CRC screening programs is important. CRC screening decision-making process can be conceptualized as the relationship between intention and behavior and needs to be investigated including the impact on patients' decision of a broad range of psychological factors and personal predisposition as fear of a positive screening test, poor understanding of the procedure, psychological distress, anxiety, anticipation of pain, feelings of embarrassment and vulnerability. Also socioeconomic, ethnic and sociological influences, and organizational barriers have been identified as factors influencing CRC screening adherence. Decision-making process can finally be influenced by the healthcare background in which the intervention is promoted and screening programs are carried out. However, there is still a gap on the scientific knowledge about the influences of diverse elements on screening adherence and this deserves further investigations in order to carry out more focused and effective prevention programs.

Predicting poor adherence to antiretroviral therapy among treatment-naïve veterans infected with human immunodeficiency virus

Previous studies suggested that human immunodeficiency virus (HIV) infected patients at risk of poor adherence were not distinguishable only based on the baseline characteristics. This study is to identify patient characteristics that would be consistently associated with poor adherence across regimens and to understand the associations between initial and long-term adherence. HIV treatment-naïve patients initiated on protease inhibitors, nonnucleoside reverse transcriptase inhibitors, or integrase strand transfer inhibitors were identified from the Veteran Health Administration system. Initial adherence measured as initial coverage ratio (ICR) and long-term adherence measured as thereafter 1-year proportion days covered (PDC) of base agent and complete regimen were estimated for each patient. The patients most likely to exhibit poor adherence were African-American, with lower socioeconomic status, and healthier. The initial coverage ratio of base agent and complete regimen were highly correlated, but the correlations between ICR and thereafter 1-year PDC were low. However, including initial adherence as a predictor in predictive model would substantially increase predictive accuracy of future adherence.

Predicting No-Shows in Radiology Using Regression Modeling of Data Available in the Electronic Medical Record

PURPOSE

To test whether data elements available in the electronic medical record (EMR) can be effectively leveraged to predict failure to attend a scheduled radiology examination.

MATERIALS AND METHODS

Using data from a large academic medical center, we identified all patients with a diagnostic imaging examination scheduled from January 1, 2016, to April 1, 2016, and determined whether the patient successfully attended the examination. Demographic, clinical, and health services utilization variables available in the EMR potentially relevant to examination attendance were recorded for each patient. We used descriptive statistics and logistic regression models to test whether these data elements could predict failure to attend a scheduled radiology examination. The predictive accuracy of the regression models were determined by calculating the area under the receiver operator curve.

RESULTS

Among the 54,652 patient appointments with radiology examinations scheduled during the study period, 6.5% were no-shows. No-show rates were highest for the modalities of mammography and CT and lowest for PET and MRI. Logistic regression indicated that 16 of the 27 demographic, clinical, and health services utilization factors were significantly associated with failure to attend a scheduled radiology examination (P ≤ .05). Stepwise logistic regression analysis demonstrated that previous no-shows, days between scheduling and appointments, modality type, and insurance type were most strongly predictive of no-show. A model considering all 16 data elements had good ability to predict radiology no-shows (area under the receiver operator curve = 0.753). The predictive ability was similar or improved when these models were analyzed by modality.

CONCLUSION

Patient and examination information readily available in the EMR can be successfully used to predict radiology no-shows. Moving forward, this information can be proactively leveraged to identify patients who might benefit from additional patient engagement through appointment reminders or other targeted interventions to avoid no-shows.

Appointment-keeping behaviors and procedure day are associated with colonoscopy attendance in a patient navigator population

BACKGROUND

Patient navigator programs (PNP) have been shown to improve colonoscopy completion with demonstrated cost-effectiveness. Despite additional resources available to these patients, many still do not attend their colonoscopies. The aim of this study was to determine factors associated with colonoscopy attendance amongst patients in whom logistical barriers to attendance have been minimized through enrollment in a PNP.

METHODS

Retrospective case-control study of patients enrolled in a PNP for colonoscopy performed at a tertiary endoscopy center from 2009 to 2014. Cases were defined as patients who did not attend their first scheduled colonoscopy after PNP enrollment. Age- and gender-matched controls completed their first scheduled colonoscopy after PNP enrollment.

RESULTS

514 subjects (257 cases, mean age 57.1years, 36.6% males) were included. Patients who attended their colonoscopy were less likely to be Spanish-speaking (64.6% vs 78.2%, p=0.0003) and uninsured (0.4% vs 3.9%, p=0.006). Attendance rates were significantly lower for screening colonoscopies compared to an indication of surveillance or diagnostic (45.5% vs 65.3%, p<0.0001). Fewer patients attended colonoscopies scheduled on Monday (39.2% vs 52.1%, p=0.04) and in December (10.7% vs 52.3%, p<0.0001). On multivariate analysis, poor appointment-keeping behaviors, including a prior missed colonoscopy (OR 0.20, 95% CI 0.10-0.39) or missed office visit (OR 0.44, 95% CI 0.26-0.73) and procedures scheduled on Mondays (OR 0.51, 95% CI 0.27-0.94) were negatively associated with attendance.

CONCLUSIONS

Appointment-keeping behaviors, in addition to insurance-status, language-barriers and medical comorbidities, influence colonoscopy attendance in a PNP population. Patients scheduled for colonoscopies on Mondays or in December may require more resources to ensure attendance.

Enhancing the Prediction of 30-Day Readmission After Percutaneous Coronary Intervention Using Data Extracted by Querying of the Electronic Health Record

BACKGROUND

Early readmission after percutaneous coronary intervention is an important quality metric, but prediction models from registry data have only moderate discrimination. We aimed to improve ability to predict 30-day readmission after percutaneous coronary intervention from a previously validated registry-based model.

METHODS AND RESULTS

We matched readmitted to non-readmitted patients in a 1:2 ratio by risk of readmission, and extracted unstructured and unconventional structured data from the electronic medical record, including need for medical interpretation, albumin level, medical nonadherence, previous number of emergency department visits, atrial fibrillation/flutter, syncope/presyncope, end-stage liver disease, malignancy, and anxiety. We assessed differences in rates of these conditions between cases/controls, and estimated their independent association with 30-day readmission using logistic regression conditional on matched groups. Among 9288 percutaneous coronary interventions, we matched 888 readmitted with 1776 non-readmitted patients. In univariate analysis, cases and controls were significantly different with respect to interpreter (7.9% for cases and 5.3% for controls; P=0.009), emergency department visits (1.12 for cases and 0.77 for controls; P<0.001), homelessness (3.2% for cases and 1.6% for controls; P=0.007), anticoagulation (33.9% for cases and 22.1% for controls; P<0.001), atrial fibrillation/flutter (32.7% for cases and 28.9% for controls; P=0.045), presyncope/syncope (27.8% for cases and 21.3% for controls; P<0.001), and anxiety (69.4% for cases and 62.4% for controls; P<0.001). Anticoagulation, emergency department visits, and anxiety were independently associated with readmission.

CONCLUSIONS

Patient characteristics derived from review of the electronic health record can be used to refine risk prediction for hospital readmission after percutaneous coronary intervention.