Who is not coming to clinic? A predictive model of excessive missed appointments in persons with multiple sclerosis

Perceived health- related quality of life in persons with multiple sclerosis with and without a vascular comorbidity

PURPOSE

Vascular comorbidities are prevalent and can contribute to adverse health outcomes in persons with multiple sclerosis (PwMS). Understanding the association between vascular comorbidities and health-related quality of life (HRQOL) among PwMS may be beneficial in improving outcomes and disease management. This cross-sectional study aimed to examine the relationship between vascular comorbidities and the different dimensions of HRQOL in PwMS.

METHODS

Participants (n = 185) were PwMS recruited from a community-based comprehensive MS care center. Demographics, comorbid conditions, and disability level were collected via a self-report REDCap survey, with the 29-item Multiple Sclerosis Quality of Life (MSQOL-29) as the outcome measure. Regression models were used to examine the association between vascular comorbidities and the MSQOL-29, controlling for age, gender, ethnicity, level of education, marital status, MS subtype, disease duration, and disability.

RESULTS

Approximately 35% reported at least one vascular comorbidity, with the most common being hypertension (27.0%), followed by hyperlipidemia (24.9%) and diabetes (8.1%). After factoring in for demographics and disability, having a vascular comorbidity was associated with lower physical HRQOL (β = - 10.05, 95% CI: - 28.24, 23.50), but not mental HRQOL (β = - 2.61, 95% CI: - 10.54, 5.32). Hypertension was negatively associated with several dimensions of HRQOL, including Physical Function, Change in Health, Health Perceptions, Energy, and Health Distress.

CONCLUSIONS

 Having at least one vascular comorbidity is associated with lower physical HRQOL, independent of demographics and level of physical disability. Focus should be directed to the physical burden and challenges vascular comorbidities may cause on the lives of PwMS.

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.

Risk Factors for Chronic Prescription Opioid Use in Multiple Sclerosis

OBJECTIVE

To characterize patterns of prescription opioid use among individuals with multiple sclerosis (MS) and identify risk factors associated with chronic use.

DESIGN

Retrospective longitudinal cohort study examining US Department of Veterans Affairs electronic medical record data of Veterans with MS. The annual prevalence of prescription opioid use by type (any, acute, chronic, incident chronic) was calculated for each study year (2015-2017). Multivariable logistic regression was used to identify demographics and medical, mental health, and substance use comorbidities in 2015-2016 associated with chronic prescription opioid use in 2017.

SETTING

US Department of Veterans Affairs, Veteran's Health Administration.

PARTICIPANTS

National sample of Veterans with MS (N=14,974).

MAIN OUTCOME MEASURE

Chronic prescription opioid use (≥90 days).

RESULTS

All types of prescription opioid use declined across the 3 study years (chronic opioid use prevalence=14.6%, 14.0%, and 12.2%, respectively). In multivariable logistic regression, prior chronic opioid use, history of pain condition, paraplegia or hemiplegia, post-traumatic stress disorder, and rural residence were associated with greater risk of chronic prescription opioid use. History of dementia and psychotic disorder were both associated with lower risk of chronic prescription opioid use.

CONCLUSION

Despite reductions over time, chronic prescription opioid use remains common among a substantial minority of Veterans with MS and is associated with multiple biopsychosocial factors that are important for understanding risk for long-term use.

Machine Learning Predictions on Outpatient No-Show Appointments in a Malaysia Major Tertiary Hospital

Introduction

A no-show appointment occurs when a patient does not attend a previously booked appointment. This situation can cause other problems, such as discontinuity of patient treatments as well as a waste of both human and financial resources. One of the latest approaches to address this issue is predicting no-shows using machine learning techniques. This study aims to propose a predictive analytical approach for developing a patient no-show appointment model in Hospital Kuala Lumpur (HKL) using machine learning algorithms.

Methods

This study uses outpatient data from the HKL's Patient Management System (SPP) throughout 2019. The final data set has 246,943 appointment records with 13 attributes used for both descriptive and predictive analyses. The predictive analysis was carried out using seven machine learning algorithms, namely, logistic regression (LR), decision tree (DT), k-near neighbours (k-NN), Naïve Bayes (NB), random forest (RF), gradient boosting (GB) and multilayer perceptron (MLP).

Results

The descriptive analysis showed that the no-show rate was 28%, and attributes such as the month of the appointment and the gender of the patient seem to influence the possibility of a patient not showing up. Evaluation of the predictive model found that the GB model had the highest accuracy of 78%, F1 score of 0.76 and area under the curve (AUC) value of 0.65.

Conclusion

The predictive model could be used to formulate intervention steps to reduce no-shows, improving patient care quality.

Appointment attendance behaviors in multiple sclerosis: Understanding the factors that differ between no shows, short notice cancellations, and attended appointments

BACKGROUND

There has yet to be an examination of how appointment attendance behaviors in multiple sclerosis (MS) are related to scheduling metrics and certain demographic, clinical, and behavioral factors such as cognitive functioning and personality traits. This study aimed to examine the factors that differ between no shows (NS), short notice cancellations (SNC), and attended appointments.

METHODS

Participants (n = 110) were persons with MS who were enrolled in a larger cross-sectional study, during which they completed a battery of neuropsychological measures. Data about their appointments in three MS-related clinics the year prior to their study evaluation were extracted from the medical record. Bivariate analyses were done, with post-hoc tests conducted with Bonferroni corrections if there was an overall group difference.

RESULTS

A higher number of SNC were noted during the winter, with 22.4% being due to the weather. SNC were also more common on Thursdays, but less frequent during the early morning time slots (7am to 9am). In contrast, NS were associated with lower annual income, weaker healthcare provider relationships, lower self-efficacy, higher levels of neuroticism, depressive symptom severity, and health distress, and greater cognitive difficulties, particularly with prospective memory.

CONCLUSIONS

While SNC are related to clinic structure and situational factors like the weather, NS may be more influenced by behavioral issues, such as difficulty remembering an appointment and high levels of distress. These findings highlight potential targets for reducing the number of missed appointments in the clinic, providing opportunities for improved healthcare efficiency and most importantly health.

Identifying prospective memory deficits in multiple sclerosis: Preliminary evaluation of the criterion and ecological validity of a single item version of the memory for intentions test (MIST)

Objectives: Difficulties with prospective memory (PM) are not routinely assessed in persons with multiple sclerosis (MS) even though they can impact daily functioning. This study aimed to examine the preliminary criterion and ecological validity of a highly abbreviated Memory for Intentions Test (MIST) intended to serve as an initial screening of PM in persons with MS. Methods: Participants (n = 112) were classified as impaired if they performed 1.5 standard deviations below the normative mean on the MIST. Individual MIST trials with adequate difficulty and discriminability were examined using receiver operating characteristic analyses, with their classification accuracies, sensitivities, and specificities compared to each other. Regressions were run to evaluate their ecological validity, with appointment attendance and employment as the outcomes. Results: Two trials had a classification accuracy of ≥80%: Trial 3 (79% sensitivity, 84% specificity) and Trial 4 (57% sensitivity, 91% specificity). These two trials had comparable specificity (p=.127), with Trial 3 having slightly higher sensitivity (p=.083). Only Trial 4 was significantly associated with appointment attendance (b = 1.63, p=.047) and unemployment (aOR = 11.20, p=.027). Discussion:Trial 4 of the MIST, a verbal task with a time-based cue that requires participants to complete a pre-specified response after a 15-minute delay, has the potential to be a screener for PM.

The effect of social support, depression, and illness perception on treatment adherence in patients with multiple sclerosis

Objective: This study was planned to determine the treatment adherence levels of multiple sclerosis (MS) patients and the factors affecting treatment adherence. Patients and Methods: This descriptive and cross-sectional study was conducted with 211 people with MS. Data for this study was obtained through face-to-face interviews with MS patients who presented at the neurology outpatient clinics of two university hospitals between April and October 2018. The “Morisky, Green, and Levine Adherence Scale”, “Beck Depression Inventory”, “Multidimensional Perceived Social Support Scale”, and the “Illness Perception Scale” were used in data collection. Results: The mean age of the sample was 40.03±10.82, and 70.1% were female. Treatment adherence was not good in half of the patients (51.7%). Patients with good adherence were found to have higher Multidimensional Perceived Social Support Scale scores (p

Understanding no-show behaviour for cervical cancer screening appointments among hard-to-reach women in Bogotá, Colombia: A mixed-methods approach

The global burden of cervical cancer remains a concern and higher early mortality rates are associated with poverty and limited health education. However, screening programs continue to face implementation challenges, especially in developing country contexts. In this study, we use a mixed-methods approach to understand the reasons for no-show behaviour for cervical cancer screening appointments among hard-to-reach low-income women in Bogotá, Colombia. In the quantitative phase, individual attendance probabilities are predicted using administrative records from an outreach program (N = 23384) using both LASSO regression and Random Forest methods. In the qualitative phase, semi-structured interviews are analysed to understand patient perspectives (N = 60). Both inductive and deductive coding are used to identify first-order categories and content analysis is facilitated using the Framework method. Quantitative analysis shows that younger patients and those living in zones of poverty are more likely to miss their appointments. Likewise, appointments scheduled on Saturdays, during the school vacation periods or with lead times longer than 10 days have higher no-show risk. Qualitative data shows that patients find it hard to navigate the service delivery process, face barriers accessing the health system and hold negative beliefs about cervical cytology.

Reducing non-attendance in outpatient appointments: predictive model development, validation, and clinical assessment

Background

Non-attendance to scheduled hospital outpatient appointments may compromise healthcare resource planning, which ultimately reduces the quality of healthcare provision by delaying assessments and increasing waiting lists. We developed a model for predicting non-attendance and assessed the effectiveness of an intervention for reducing non-attendance based on the model.

Methods

The study was conducted in three stages: (1) model development, (2) prospective validation of the model with new data, and (3) a clinical assessment with a pilot study that included the model as a stratification tool to select the patients in the intervention. Candidate models were built using retrospective data from appointments scheduled between January 1, 2015, and November 30, 2018, in the dermatology and pneumology outpatient services of the Hospital Municipal de Badalona (Spain). The predictive capacity of the selected model was then validated prospectively with appointments scheduled between January 7 and February 8, 2019. The effectiveness of selective phone call reminders to patients at high risk of non-attendance according to the model was assessed on all consecutive patients with at least one appointment scheduled between February 25 and April 19, 2019. We finally conducted a pilot study in which all patients identified by the model as high risk of non-attendance were randomly assigned to either a control (no intervention) or intervention group, the last receiving phone call reminders one week before the appointment.

Results

Decision trees were selected for model development. Models were trained and selected using 33,329 appointments in the dermatology service and 21,050 in the pneumology service. Specificity, sensitivity, and accuracy for the prediction of non-attendance were 79.90%, 67.09%, and 73.49% for dermatology, and 71.38%, 57.84%, and 64.61% for pneumology outpatient services. The prospective validation showed a specificity of 78.34% (95%CI 71.07, 84.51) and balanced accuracy of 70.45% for dermatology; and 69.83% (95%CI 60.61, 78.00) for pneumology, respectively. The effectiveness of the intervention was assessed on 1,311 individuals identified as high risk of non-attendance according to the selected model. Overall, the intervention resulted in a significant reduction in the non-attendance rate to both the dermatology and pneumology services, with a decrease of 50.61% (p<0.001) and 39.33% (p=0.048), respectively.

Conclusions

The risk of non-attendance can be adequately estimated using patient information stored in medical records. The patient stratification according to the non-attendance risk allows prioritizing interventions, such as phone call reminders, to effectively reduce non-attendance rates.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-022-07865-y.

The Role of Cognitive Impairment on Physical Therapy Attendance and Outcomes in Multiple Sclerosis

BACKGROUND AND PURPOSE

Many persons with multiple sclerosis (PwMS) experience cognitive impairments, which may affect their ability to engage in physical therapy. There is limited information on how cognitive impairments are associated with PwMS' ability to participate and improve their functional outcomes. This study aimed to assess the relationship between cognitive functioning and PwMS' attendance, total goal attainment, and functional improvement following physical therapy intervention.

METHODS

Participants (n = 45) were PwMS who participated in a larger self-management study and enrolled in physical therapy within the past 2 years. Objective cognitive functioning was examined using tests of prospective memory, retrospective memory, working memory, and processing speed, along with a self-report measure. Bivariate analyses were conducted to examine the relationship between cognitive functioning and each physical therapy outcome (session attendance, attaining goals, and changes in functional outcome measures), followed by logistic regressions with age, education, gender, and disability level as covariates.

RESULTS

Difficulty learning new verbal information was associated with a greater likelihood of "no showing" one or more of their physical therapy sessions. Reductions in working memory and processing speed were associated with PwMS not meeting all their rehabilitation goals. Despite deficits in new learning, memory, and processing speed, 85.2% of those with pre-/postscores showed improvements in at least one functional outcome measure following physical therapy intervention.

DISCUSSION AND CONCLUSIONS

These findings demonstrate the ability for PwMS to make functional motor gains despite the presence of cognitive impairments and highlight the potential contributions of cognitive functioning on attendance and goal attainment of physical therapy intervention.Video Abstract available for more insights from the authors (see the Video, Supplemental Digital Content 1, available at: http://links.lww.com/JNPT/A362, which includes background, methods, results, and discussion in the authors' own voices).

Demographic and Clinical Factors Are Associated Wwith Frequent Short-Notice Cancellations in Veterans with Multiple Sclerosis on Disease Modifying Therapies

OBJECTIVES

(1) To identify the rate of short-notice canceled appointments in a large national sample of persons with multiple sclerosis (MS) and (2) examine the demographic and clinical factors associated with frequent cancellations.

DESIGN

Retrospective cross-sectional cohort using electronic health records.

SETTING

Veterans Health Administration.

PARTICIPANTS

Veterans with MS (N=3742) who were part of the Veterans Health Administraiton's MS Center of Excellence Data Repository and (1) had at least one outpatient appointment at the VA in 2013, (2) were alive in 2015, and (3) were prescribed a disease modifying therapy (DMT).

INTERVENTIONS

Not applicable.

MAIN OUTCOME MEASURES

Frequent short-notice cancellations, defined as >20% of scheduled appointments canceled with less than 24-hour notification over a 24-month period. This threshold was based on the definition of ≤80% for suboptimal treatment adherence. Several demographics and clinical variables were examined as potential explanatory factors.

RESULTS

Approximately 75% (n=2827) had at least 1 short-notice cancellation, with more than 3% (n=117) categorized as frequent cancelers. The odds of frequent cancellations were greater in women (odds ratio [OR], 1.81; P=.004) and among 18- to 44-year-olds (OR, 2.77; P=.004) and 45- to 64-year-olds (OR, 2.49; P=.003) compared to those over 65. The odds were lower among persons who lived <25 miles away (OR, 0.58; P=.043) compared with persons who lived ≥75 miles away and those who had at least 1 emergency department visit (OR, 0.55; P=.012).

CONCLUSIONS

Short-notice cancellations are common in persons with MS, although few have more than 20%. These findings highlight who is at greater risk for frequent cancellation and disruptions in their care. Although additional research is needed, the results provide insights into how clinics may approach handling frequent short-notice cancellations among persons with MS.

Characterising the nationwide burden and predictors of unkept outpatient appointments in the National Health Service in England: A cohort study using a machine learning approach

BACKGROUND

Unkept outpatient hospital appointments cost the National Health Service £1 billion each year. Given the associated costs and morbidity of unkept appointments, this is an issue requiring urgent attention. We aimed to determine rates of unkept outpatient clinic appointments across hospital trusts in the England. In addition, we aimed to examine the predictors of unkept outpatient clinic appointments across specialties at Imperial College Healthcare NHS Trust (ICHT). Our final aim was to train machine learning models to determine the effectiveness of a potential intervention in reducing unkept appointments.

METHODS AND FINDINGS

UK Hospital Episode Statistics outpatient data from 2016 to 2018 were used for this study. Machine learning models were trained to determine predictors of unkept appointments and their relative importance. These models were gradient boosting machines. In 2017-2018 there were approximately 85 million outpatient appointments, with an unkept appointment rate of 5.7%. Within ICHT, there were almost 1 million appointments, with an unkept appointment rate of 11.2%. Hepatology had the highest rate of unkept appointments (17%), and medical oncology had the lowest (6%). The most important predictors of unkept appointments included the recency (25%) and frequency (13%) of previous unkept appointments and age at appointment (10%). A sensitivity of 0.287 was calculated overall for specialties with at least 10,000 appointments in 2016-2017 (after data cleaning). This suggests that 28.7% of patients who do miss their appointment would be successfully targeted if the top 10% least likely to attend received an intervention. As a result, an intervention targeting the top 10% of likely non-attenders, in the full population of patients, would be able to capture 28.7% of unkept appointments if successful. Study limitations include that some unkept appointments may have been missed from the analysis because recording of unkept appointments is not mandatory in England. Furthermore, results here are based on a single trust in England, hence may not be generalisable to other locations.

CONCLUSIONS

Unkept appointments remain an ongoing concern for healthcare systems internationally. Using machine learning, we can identify those most likely to miss their appointment and implement more targeted interventions to reduce unkept appointment rates.

What Biopsychosocial Factors Explain Self-management Behaviors in Multiple Sclerosis? The Role of Demographics, Cognition, Personality, and Psychosocial and Physical Functioning

OBJECTIVES

To examine the biopsychosocial correlates of overall and individual self-management behaviors in persons with multiple sclerosis (MS), including demographics, co-occurring medical diagnoses, cognition, personality traits, and psychosocial and physical functioning as variables.

DESIGN

Prospective cross-sectional cohort study.

SETTING

Community-based comprehensive MS center.

PARTICIPANTS

Adults with MS (n=112) who completed a brief neuropsychological battery that included a self-report survey and performance-based measures of cognitive function.

INTERVENTIONS

Not applicable.

MAIN OUTCOME MEASURES

The MS Self-management Scale-Revised total score was the primary outcome and its 5 subscales (Healthcare Provider Relationship/Communication, Treatment Adherence/Barriers, Social/Family Support, MS Knowledge and Information, Health Maintenance Behaviors) were secondary outcomes.

RESULTS

Disease-modifying therapy usage (β=0.39), social support (β=0.31), subjective prospective memory (β=-0.25), emotional well-being (β=0.20), and histories of diabetes (β=-0.18) and high cholesterol (β=0.15) were significantly associated with overall self-management in a multivariate model. Correlates of individual self-management behaviors are also described.

CONCLUSIONS

The findings provide insights into the biopsychosocial characteristics contributing to the overall and individual self-management behaviors of persons with multiple sclerosis. The next steps will be to evaluate these factors in a clinical intervention.

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.