Predictive model-based interventions to reduce outpatient no-shows: a rapid systematic review

Validation and Recalibration of a Model for Predicting Surgical-Site Infection After Pelvic Organ Prolapse Surgery

INTRODUCTION AND HYPOTHESIS

The objective was to externally validate and recalibrate a previously developed model for predicting postoperative surgical-site infection (SSI) after pelvic organ prolapse (POP) surgery.

METHODS

This study utilized a previously validated model for predicting post-POP surgery SSI within 90 days of surgery using a Medicare population. For this study, the model was externally validated and recalibrated using the Premier Healthcare Database (PHD) and the National Surgical Quality Improvement Project (NSQIP) database. Discriminatory performance was assessed via the c-statistic and calibration was assessed using calibration curves. Methods of recalibration in the large and logistic recalibration were used to update the models.

RESULTS

The PHD contained 420,277 POP procedures meeting the inclusion criteria and 1.6% resulted in SSI. The NSQIP dataset contained 62,553 POP surgeries and 1.4% resulted in SSI. Discrimination of the original model was comparable with that seen in the initial validation (c-statistic = 0.57 in PHD, 0.59 in NSQIP vs 0.60 in the original Medicare data). Recalibration greatly improved model calibration when evaluated in NSQIP data.

CONCLUSION

A previously developed model for predicting SSI after POP surgery demonstrated stable discriminatory ability when externally validated on the PHD and NSQIP databases. Model recalibration was necessary to improve prediction. Prospective studies are needed to validate the clinical utility of such a model.

Predictive Optimization of Patient No-Show Management in Primary Healthcare Using Machine Learning

The "no-show" problem in healthcare refers to the prevalent phenomenon where patients schedule appointments with healthcare providers but fail to attend them without prior cancellation or rescheduling. In addressing this issue, our study delves into a multivariate analysis over a five-year period involving 21,969 patients. Our study introduces a predictive model framework that offers a holistic approach to managing the no-show problem in healthcare, incorporating elements into the objective function that address not only the accurate prediction of no-shows but also the management of service capacity, overbooking, and idle resource allocation resulting from mispredictions. Our approach simplifies preprocessing and eliminates the need for expert judgment in variable selection, thereby enhancing the model's usability in routine healthcare operations. Our research revealed that key predictors of no-shows are consistent across various studies. We employed semi-automatic feature selection techniques, achieving results comparable to state-of-the-art approaches but with significantly reduced complexity in their selection. This method not only streamlines the feature selection process but also enhances the overall efficiency and scalability of our predictive models, making them more adaptable to diverse healthcare settings. This comprehensive strategy enables healthcare providers to optimize resource allocation and improve service delivery, making our findings relevant for healthcare systems globally facing similar challenges. Future work aims to expand the analysis by incorporating additional third-party data sources, such as weather and commuting activities, to explore the broader impacts of external factors on patient no-show behavior. To the best of our knowledge, this innovative approach is expected to provide deeper insights and further enhance the predictability and effectiveness of no-show mitigation strategies in healthcare systems.

Reasons for Missed Appointments

IMPORTANCE

Little is known about reasons behind missed appointments in subspecialty settings, particularly in urogynecology practices.

OBJECTIVE

The aim of the study was to understand patient-perceived barriers to appointment attendance at an academic urban multisite urogynecology practice.

STUDY DESIGN

This was a prospective, qualitative study of patients who missed their appointments at a urogynecology practice from April to September 2023. Patients were invited to participate in semistructured interviews. Nonrandom, purposive sampling ensured a reflective sample. The interview guide addressed attendance barriers, reasons for missed appointments, and clinic accessibility. Inductive coding was applied to interview text fragments and a codebook was developed.

RESULTS

Of the 230 eligible patients, 110 (48%) were contacted and 26/110 (24%) consented and completed interviews. Patients identified the following 3 major barriers to appointment attendance: (1) community and environmental barriers, (2) patient-related factors, and (3) clinic-related factors. Community and environmental barriers (n = 20 [77%]) included unforeseen circumstances and transportation issues, with 52% citing transportation difficulties. Patient-related factors (n = 16 [62%]) included family obligations, personal illness, mental health concerns, confusion with appointments, or competing job responsibilities. Clinic-related factors (n = 9 [35%]) included scheduling and timing issues. Participants proposed changes to facilitate attendance, which included clinics offering transportation assistance, providing interpersonal support through support groups, and improving the internet-based portal to make patient communication easier.

CONCLUSIONS

Identifying the reasons why patients miss appointments is pivotal to providing patient-centered care. Our findings provide a deeper understanding of issues underlying missed urogynecology appointments. Future research to develop an algorithm to identify barriers to attending appointments and provide interventions such as transportation support could result in more accessible, equitable care.

Telemedicine appointments are more likely to be completed than in-person healthcare appointments: a retrospective cohort study

Objectives

Missed appointments can lead to treatment delays and adverse outcomes. Telemedicine may improve appointment completion because it addresses barriers to in-person visits, such as childcare and transportation. This study compared appointment completion for appointments using telemedicine versus in-person care in a large cohort of patients at an urban academic health sciences center.

Materials and Methods

We conducted a retrospective cohort study of electronic health record data to determine whether telemedicine appointments have higher odds of completion compared to in-person care appointments, January 1, 2021, and April 30, 2023. The data were obtained from the University of South Florida (USF), a large academic health sciences center serving Tampa, FL, and surrounding communities. We implemented 1:1 propensity score matching based on age, gender, race, visit type, and Charlson Comorbidity Index (CCI).

Results

The matched cohort included 87 376 appointments, with diverse patient demographics. The percentage of completed telemedicine appointments exceeded that of completed in-person care appointments by 9.2 points (73.4% vs 64.2%, P < .001). The adjusted odds ratio for telemedicine versus in-person care in relation to appointment completion was 1.64 (95% CI, 1.59-1.69, P < .001), indicating that telemedicine appointments are associated with 64% higher odds of completion than in-person care appointments when controlling for other factors.

Discussion

This cohort study indicated that telemedicine appointments are more likely to be completed than in-person care appointments, regardless of demographics, comorbidity, payment type, or distance.

Conclusion

Telemedicine appointments are more likely to be completed than in-person healthcare appointments.

Sociodemographic Factors Associated with Outpatient Radiology No-shows Versus Cancellations

RATIONALE AND OBJECTIVES

To assess prevalence of missed outpatient radiology appointments and sociodemographic factors associated with no-shows vs. cancellations.

METHODS

Adults with outpatient radiology appointments in 2022 and January 2023 at a single tertiary academic health center were included. Generalized estimating equation regression was used to evaluate sociodemographic factors associated with missed vs. completed appointments, no-shows vs. cancellations and time interval between cancellations and appointments.

RESULTS

19,262 (24.3%) examinations were either a cancellation (22.3%) or no-show (2.0%) among 9713 patients (mean age 60.8 ± 15.5; 67.1% female, 63.9% White, 20.0% Asian, 22.0% Hispanics). Among cancellations, 70.19% were patient-initiated. Age ≥ 65 significantly decreased the probability of missed appointments by 5.4% point (pp) (95% CI: 3.7-7.2) or no-shows (4.2 pp; 95% CI, 1.4-6.9), while being single increased probability of missed appointments (2.2 pp; 95% CI, 1.2-3.1) or no-shows (2.6 pp; 95% CI, 1.2-4.1). Those uninsured or with public insurance were 1.3-4.9 pp more likely to miss appointments than commercial insurance, and 2.2-7.6 pp more likely to have no-shows than cancellations. Living in disadvantaged neighborhoods 4.9 pp (95% CI, 3.9-6.0) increased likelihood of missing appointment and was associated with shorter time interval between cancellation and appointment. English speakers were 2.2 pp (95% CI, 1.1-3.3) more likely to miss their exam, while 2.7 pp (95% CI, 1.1-0.4.3) less likely to be a no-show than cancellation.

CONCLUSION

Cancellations represented a significant portion of missed appointments. Specific sociodemographic subgroups exhibited higher tendencies for having missed appointments and no-shows.

Applying Machine Learning Techniques to Implementation Science

Machine learning (ML) approaches could expand the usefulness and application of implementation science methods in clinical medicine and public health settings. The aim of this viewpoint is to introduce a roadmap for applying ML techniques to address implementation science questions, such as predicting what will work best, for whom, under what circumstances, and with what predicted level of support, and what and when adaptation or deimplementation are needed. We describe how ML approaches could be used and discuss challenges that implementation scientists and methodologists will need to consider when using ML throughout the stages of implementation.

To confirm your appointment, please press one: Examining demographic and health system interface factors that predict missed appointments in a pediatric outpatient neuropsychology clinic

Objective: Missed patient appointments have a substantial negative impact on patient care, child health and well-being, and clinic functioning. This study aims to identify health system interface and child/family demographic characteristics as potential predictors of appointment attendance in a pediatric outpatient neuropsychology clinic. Method: Pediatric patients (N = 6,976 across 13,362 scheduled appointments) who attended versus missed scheduled appointments at a large, urban assessment clinic were compared on a broad array of factors extracted from the medical record, and the cumulative impact of significant risk factors was examined. Results: In the final multivariate logistic regression model, health system interface factors that significantly predicted more missed appointments included a higher percentage of previous missed appointments within the broader medical center, missing pre-visit intake paperwork, assessment/testing appointment type, and visit timing relative to the COVID-19 pandemic (i.e. more missed appointments prior to the pandemic). Demographic characteristics that significantly predicted more missed appointments in the final model included Medicaid (medical assistance) insurance and greater neighborhood disadvantage per the Area Deprivation Index (ADI). Waitlist length, referral source, season, format (telehealth vs. in-person), need for interpreter, language, and age were not predictive of appointment attendance. Taken together, 7.75% of patients with zero risk factors missed their appointment, while 22.30% of patients with five risk factors missed their appointment. Conclusions: Pediatric neuropsychology clinics have a unique array of factors that impact successful attendance, and identification of these factors can help inform policies, clinic procedures, and strategies to decrease barriers, and thus increase appointment attendance, in similar settings.

Factors associated with nonattendance at annual diabetes check-up in Ningbo, China: a case-control study

Background

Type 2 diabetes mellitus (T2DM) is a grave issue in China. The annual check-up is recommended in clinical guidelines on T2DM. It plays an important role in monitoring and managing the condition and detecting and managing any comorbidities and T2DM-related complications. However, people with T2DM may miss the annual check-up, and the benefits of this check-up are lost. Therefore, this study aimed to determine the factors associated with nonattendance at the annual T2DM check-up in Ningbo, China.

Methods

A case-control study was conducted using the Ningbo National Metabolic Management Center dataset. Cases were people with T2DM who were alive but did not attend the first annual check-up, scheduled between 1 March 2019 and 28 February 2022 (n = 1,549). Controls were people with T2DM who were alive and attended the first annual check-up during the same period (n = 1,354). The characteristics of cases and controls were compared using logistic regressions.

Results

The odds of being a female [odds ratio (OR) 1.26, 95% confidence interval (CI) 1.06-1.50], alcohol drinker (1.26, 1.06-1.49), and with glycated hemoglobin A1c (HbA1c) ≥7% (1.67, 1.42-1.97) were higher among case patients than controls. The odds of being a high school graduate (0.77, 0.66-0.89) and on standard treatments in addition to lifestyle modification (oral hypoglycemic drug 0.63, 0.42-0.96; oral hypoglycemic drug and injection therapy 0.48, 0.32-0.73) were lower among case patients than controls.

Conclusion

The factors associated with nonattendance at the annual T2DM check-up in Ningbo, China were female sex, not a high school graduate, alcohol drinker, HbA1c ≥7%, and only on lifestyle modification. The study findings should be used for improving attendance at the annual check-up among people with T2DM in Ningbo.

Large Language Models and Medical Education: Preparing for a Rapid Transformation in How Trainees Will Learn to Be Doctors

Artificial intelligence has the potential to revolutionize health care but has yet to be widely implemented. In part, this may be because, to date, we have focused on easily predicted rather than easily actionable problems. Large language models (LLMs) represent a paradigm shift in our approach to artificial intelligence because they are easily accessible and already being tested by frontline clinicians, who are rapidly identifying possible use cases. LLMs in health care have the potential to reduce clerical work, bridge gaps in patient education, and more. As we enter this era of healthcare delivery, LLMs will present both opportunities and challenges in medical education. Future models should be developed to support trainees to develop skills in clinical reasoning, encourage evidence-based medicine, and offer case-based training opportunities. LLMs may also change what we continue teaching trainees with regard to clinical documentation. Finally, trainees can help us train and develop the LLMs of the future as we consider the best ways to incorporate LLMs into medical education. Ready or not, LLMs will soon be integrated into various aspects of clinical practice, and we must work closely with students and educators to make sure these models are also built with trainees in mind to responsibly chaperone medical education into the next era.