Using overbooking to manage no-shows in an Italian healthcare center

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.

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

OBJECTIVE

Outpatient no-shows have important implications for costs and the quality of care. Predictive models of no-shows could be used to target intervention delivery to reduce no-shows. We reviewed the effectiveness of predictive model-based interventions on outpatient no-shows, intervention costs, acceptability, and equity.

MATERIALS AND METHODS

Rapid systematic review of randomized controlled trials (RCTs) and non-RCTs. We searched Medline, Cochrane CENTRAL, Embase, IEEE Xplore, and Clinical Trial Registries on March 30, 2022 (updated on July 8, 2022). Two reviewers extracted outcome data and assessed the risk of bias using ROB 2, ROBINS-I, and confidence in the evidence using GRADE. We calculated risk ratios (RRs) for the relationship between the intervention and no-show rates (primary outcome), compared with usual appointment scheduling. Meta-analysis was not possible due to heterogeneity.

RESULTS

We included 7 RCTs and 1 non-RCT, in dermatology (n = 2), outpatient primary care (n = 2), endoscopy, oncology, mental health, pneumology, and an magnetic resonance imaging clinic. There was high certainty evidence that predictive model-based text message reminders reduced no-shows (1 RCT, median RR 0.91, interquartile range [IQR] 0.90, 0.92). There was moderate certainty evidence that predictive model-based phone call reminders (3 RCTs, median RR 0.61, IQR 0.49, 0.68) and patient navigators reduced no-shows (1 RCT, RR 0.55, 95% confidence interval 0.46, 0.67). The effect of predictive model-based overbooking was uncertain. Limited information was reported on cost-effectiveness, acceptability, and equity.

DISCUSSION AND CONCLUSIONS

Predictive modeling plus text message reminders, phone call reminders, and patient navigator calls are probably effective at reducing no-shows. Further research is needed on the comparative effectiveness of predictive model-based interventions addressed to patients at high risk of no-shows versus nontargeted interventions addressed to all patients.

Predicting no-shows for dental appointments

Patient no-shows is a significant problem in healthcare, reaching up to 80% of booked appointments and costing billions of dollars. Predicting no-shows for individual patients empowers clinics to implement better mitigation strategies. Patients' no-show behavior varies across health clinics and the types of appointments, calling for fine-grained studies to uncover these variations in no-show patterns. This article focuses on dental appointments because they are notably longer than regular medical appointments due to the complexity of dental procedures. We leverage machine learning techniques to develop predictive models for dental no-shows, with the best model achieving an Area Under the Curve (AUC) of 0.718 and an F1 score of 66.5%. Additionally, we propose and evaluate a novel method to represent no-show history as a binary sequence of events, enabling the predictive models to learn the associated future no-show behavior with these patterns. We discuss the utility of no-show predictions to improve the scheduling of dental appointments, such as reallocating appointments and reducing their duration.

Developing a simulation tool to quantify biomechanical load and quality of care in nursing

Nursing is a high musculoskeletal disorder (MSD) risk job with high workload demands. This study combines Digital Human Modelling (DHM) and Discrete Event Simulation (DES) to address the need for tools to better manage MSD risk. This novel approach quantifies physical-workload, work-performance, and quality-of-care, in response to varying geographical patient-bed assignments, patient-acuity levels, and nurse-patient ratios. Lumbar loads for 86 care-delivery tasks in an acute care hospital unit were used as inputs in a DES model of the care-delivery process, creating a shift-long time trace of the biomechanical load. Peak L4/L5 compression and moment were 3574 N and 111.58 Nm, respectively. This study reports trade-offs in all three experiments: (i) increasing geographical patient-bed assignment distance decreased L4/L5 compression (8.8%); (ii) increased patient-acuity decreased L4/L5 moment (4%); (iii) Increased nurse-patient ratio decreased L4/L5 compression (10%) and moment (17%). However, in all experiments, Quality of care indicators deteriorated (20, 19, and 29%, respectively). Practitioner Summary: This research has the potential to support decision-makers by developing a simulation tool that quantifies the impact of varying operational and design-policies in terms of biomechanical-load and quality of care. The demonstrator-model reports: as geographical patient-bed distance, patient-acuity levels, and nurse-patient ratios increase, biomechanical-load reduces, and quality of care deteriorates.

Causes, impacts and possible mitigation of non-attendance of appointments within the National Health Service: a literature review

PURPOSE

Missed appointments within the National Health Service (NHS) are a drain on resources, associated with not only considerable time and cost implications, but also sub-optimal health outcomes. This literature review aims to explore non-attendance within the NHS in relation to causes, impacts and possible mitigation of negative effects of missed appointments.

DESIGN/METHODOLOGY/APPROACH

MEDLINE, CINAHL Plus and PubMed were searched with a date range of 2016-2021. Databases were searched for peer-reviewed articles published in English addressing non-attendance of adults within the NHS. Studies were excluded if they were theoretical papers, dissertations or research concerning patients aged under 18. A total of 21 articles met the inclusion criteria and were selected for analysis.

FINDINGS

The results indicate a significant association of non-attendance and poor health outcomes. Patients from a lower socioeconomic status, adults aged over 85 and those with multiple co-morbidities are more likely to miss appointments. The most commonly reported patient-centred reasons for failing to attend were forgetfulness, transportation difficulties, and family commitments. Practice-specific reasons were cited as inefficiencies of the appointment booking system, failure of traditional reminders and inconvenient timings. Interventions included text reminder services, the inclusion of costs within reminders and enhanced patient involvement with the booking process.

ORIGINALITY/VALUE

Non-attendance is complex, and to secure maximum attendance, targeted interventions are required by healthcare facilities to ensure patient needs are met. The adaption of scheduling systems and healthcare services can assist in reducing DNA rates.

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.

Patient Characteristics Associated With Missed Appointments in Pediatric Subspecialty Clinics

OBJECTIVES

Missed appointments negatively affect patients, providers, and health systems. This study aimed to (1) quantify the percentage of missed appointments across 14 pediatric subspecialties in a tertiary-care children's hospital and (2) identify patient characteristics associated with missed appointments in those subspecialties.

METHODS

We extracted patient characteristics from 267,151 outpatient appointments, between January 1, 2013, and December 31, 2018, across 14 subspecialty clinics. Medical complexity was categorized using the Pediatric Medical Complexity Algorithm. The primary outcome was appointment nonattendance. Cancellations, imaging/laboratory visits, patients older than 18 years, and duplicate visits were excluded. Characteristics associated with nonattendance were analyzed with chi-square tests and included in the multivariable model if p < .1. Missing data were addressed using random forest imputation, and assuming data were "missing at random." Variables were considered statistically significant if p < .05.

RESULTS

Of the 128,117 scheduled appointments analyzed, 23,204 (18.1%) were missed. In the multivariable model, clinical nutrition had the greatest subspecialty odds of missed appointments, whereas cardiology had the lowest. Patient characteristics most strongly associated with missed appointments were public insurance, history of >2 missed appointments, appointment lead time, lesser medical complexity, Black race/ethnicity, and fewer medications.

CONCLUSIONS

Clinical characteristics including lesser medical complexity and fewer medications are associated with missed appointments in pediatric subspecialties.

Improving intervention design to promote cervical cancer screening among hard-to-reach women: assessing beliefs and predicting individual attendance probabilities in Bogotá, Colombia

Background

Despite being a preventable disease, cervical cancer continues to be a public health concern, affecting mainly lower and middle-income countries. Therefore, in Bogotá a home-visit based program was instituted to increase screening uptake. However, around 40% of the visited women fail to attend their Pap smear test appointments. Using this program as a case study, this paper presents a methodology that combines machine learning methods, using routinely collected administrative data, with Champion’s Health Belief Model to assess women’s beliefs about cervical cancer screening. The aim is to improve the cost-effectiveness of behavioural interventions aiming to increase attendance for screening. The results presented here relate specifically to the case study, but the methodology is generic and can be applied in all low-income settings.

Methods

This is a cross-sectional study using two different datasets from the same population and a sequential modelling approach. To assess beliefs, we used a 37-item questionnaire to measure the constructs of the CHBM towards cervical cancer screening. Data were collected through a face-to-face survey (N = 1699). We examined instrument reliability using Cronbach’s coefficient and performed a principal component analysis to assess construct validity. Then, Kruskal–Wallis and Dunn tests were conducted to analyse differences on the HBM scores, among patients with different poverty levels. Next, we used data retrieved from administrative health records (N = 23,370) to fit a LASSO regression model to predict individual no-show probabilities. Finally, we used the results of the CHBM in the LASSO model to improve its accuracy.

Results

Nine components were identified accounting for 57.7% of the variability of our data. Lower income patients were found to have a lower Health motivation score (p-value < 0.001), a higher Severity score (p-value < 0.001) and a higher Barriers score (p-value < 0.001). Additionally, patients between 25 and 30 years old and with higher poverty levels are less likely to attend their appointments (O.R 0.93 (CI: 0.83–0.98) and 0.74 (CI: 0.66–0.85), respectively). We also found a relationship between the CHBM scores and the patient attendance probability. Average AUROC score for our prediction model is 0.9.

Conclusion

In the case of Bogotá, our results highlight the need to develop education campaigns to address misconceptions about the disease mortality and treatment (aiming at decreasing perceived severity), particularly among younger patients living in extreme poverty. Additionally, it is important to conduct an economic evaluation of screening options to strengthen the cervical cancer screening program (to reduce perceived barriers). More widely, our prediction approach has the potential to improve the cost-effectiveness of behavioural interventions to increase attendance for screening in developing countries where funding is limited.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12905-022-01800-3.

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.

Overbooking for physical examination considering late cancellation and set-resource relationship

BACKGROUND

Late cancellations of physical examination has severe impact on the operations of a physical examination center since it is often too late to fill vacancy. A booking control policy that considers overbooking is then one natural solution. Unlike appointment scheduling problems for clinics and hospitals, in which treating a patient mostly requires only one type of resource, a physical examination set typically requires multiple types of resources. Traditional methods that do not consider set-resource relationship thus may be inapplicable.

METHODS

We formulate a stochastic mathematical programming model that maximizes the expected net reward, which is the examination revenue minus overage cost. A complete search algorithm and a greedy search algorithm are designed to search for optimal booking limits for all examination sets. To estimate the late cancellation probability for each individual consumer, we apply logistic regression to identify significant factors affecting the probability. After clustering is used to estimate individual probabilities, Monte Carlo simulation is conducted to generate probability distributions for the number of consumers without late cancellations. A discrete-event simulation is performance to evaluate the effectiveness of our proposed solution.

RESULTS

We collaborate with a leading physical examination center to collect real data to evaluate our proposed overbooking policies. We show that the proposed overbooking policy may significantly increase the expected net reward. Our simulation results also help us understand the impact of overbooking on the expected number of customers and expected overage. A sensitivity analysis is conducted to demonstrate that the benefit of overbooking is insensitive to the accuracy of cost estimation. A Pareto efficiency analysis gives practitioners suggestions regarding policy determination considering multiple performance indications.

CONCLUSIONS

Our proposed overbooking policies may greatly enhance the overall performance of a physical examination center.

Impact of demographics and appointment characteristics on patient attendance in a university dental clinic

INTRODUCTION

Failed patient attendance in a university dental clinic is detrimental to the student learning experience, the university as a business, and to members of the public awaiting urgent dental treatment.

PURPOSE

This study aimed to identify the demographic, appointment characteristics, and time-related factors associated with patient attendance in a university dental clinic from 2015 to 2019.

METHODS

A 5-year retrospective analysis was conducted in 2020 on data extracted from the Griffith University Dental Clinic patient management system. Following data cleaning and categorization, the dataset was downloaded into SPSS for statistical analysis. Frequencies, odds ratio, and chi squared were used to determine the demographic and time-related factors of patients who had completed, cancelled, and failed to attend (FTA) appointments.

RESULTS

A total of 23.4% of appointments were cancelled, and 6.6% were FTA. Demographics associated with cancellations include females, adults aged 25 to 44, and private paying patients. FTA were higher in young adults aged 19 to 24, low to mid-range socioeconomic status (SES) and those eligible for publicly funded dental treatment. Mondays and Fridays experienced the greatest number of FTA and cancellations, respectively. Emergency appointments had the greatest attendance rates and endodontic procedures the lowest.

CONCLUSION

The loss of clinical teaching hours, resources, and revenue necessitates the implementation of targeted strategies to minimize cancellations and FTA based on demographic and appointment characteristics that may render individual as high risk for failed attendance.

Evaluating waiting time with real-world health information in a high-volume cancer center

Wait time and scheduling for outpatient chemotherapy administration depends on various factors including infusion room hours of operation, availability of oncologists, nursing and pharmacy staffing, and physical space limitations. The aim of this study was to use the electronic event log of patients on health information system (HIS) to map and analyze patient flow in advanced metastatic colorectal patients at an academic cancer center. From January 2009 to December 2014, patients who were diagnosed with metastatic colorectal cancer and received outpatient chemotherapy confined to FOLFIRI (fluorouracil, leucovorin, and irinotecan) or FOLFOX (folinic acid, fluorouracil, and oxaliplatin) were identified. From the HIS, patient flow was mapped by collection of event records including blood collection and pretreatment laboratory test, arrival to outpatient clinics, outpatient session (interview, drug accountability and appointment scheduling), and initiation of chemotherapy. A total of 10,638 patients were analyzed for 136,281 outpatient visits. The total office stay time from outpatient registration to initiation of chemotherapy was 92.58 ± 87.96 (mean ± standard deviation) minutes. Each outpatient session lasted 23.75 ± 51.55 minutes. After completing the outpatient session, patients waited 1,657.23 ± 3,027.65 minutes before chemotherapy and 46.66 ± 75.94 minutes within infusion room. Compared to the prior first come first serve rule, the new reservation system showed an improvement in overall waiting time from 2,432.3 ± 4,822.9 to 2,386.7 ± 143.4 minutes; however, waiting time within infusion room slightly increased from 36.68 ± 49.33 to 48.13 ± 46.32 minutes. Our findings indicate that transaction data analytics from HIS can be used to evaluate patient flow within oncology outpatient practice based on real-world hospital data.

Evaluating the Impact of Patient No-Shows on Service Quality

Purpose

Patient no-shows are long-standing issues affecting resource utilization and posing risks to the quality of healthcare services. They also lead to loss of anticipated revenue, particularly in services where resources are expensive and in great demand.

Methods

In order to address common reasons why patients miss appointments, this study reviews the current literature and investigates various tools and methods that have been implemented to mitigate such issues. Further, a case study is conducted to identify the rate of no-shows and underlying causes at a radiology department in one of the leading hospitals in the MENA region.

Results

Our results show that the no-shows are high due to multiple factors, such as patient behavior, patients’ financial situation, environmental factors and scheduling policy.

Conclusion

In conclusion, we generate a list of recommendations that can help in reducing the rate of patient no-shows, such as patient education, application of dynamic scheduling policies and effective appointment reminder systems to patients.

A Bibliometric Analysis on No-Show Research: Status, Hotspots, Trends and Outlook

No-show is a thorny issue within the social scope. It not only affects the sustainability of service system operation but also causes heavy irretrievable losses. To maintain and develop the sustainability of service, this paper adopts bibliometric technology to reflect the current status and future prospects about no-show research. And we strive to explore and summarize appointment scheduling methods for no-show problems. The bibliometric analysis was carried out from various aspects including research areas, countries/regions, institutions, journals, authors and author keywords based on papers harvested from Web of Science Core Collection database. The total 1197 papers show that the United States is in a leading position in this field, followed by England and Canada. University of London is the most productive institution with the highest total citations and H-Index. BMC Health Services Research ranks first as the most productive journal, followed by European Journal of Operational Research and Production and Operations Management. Through the analysis of hot articles, we can conclude that how to reduce the impact of no-shows on the sustainability of service systems has become the main research direction. In addition to appointment scheduling, other effective methods are also mentioned. Further study on these methods will be a major research direction in the future.

Agile Six Sigma in Healthcare: Case Study at Santobono Pediatric Hospital

Healthcare is one of the most complex systems to manage. In recent years, the control of processes and the modelling of public administrations have been considered some of the main areas of interest in management. In particular, one of the most problematic issues is the management of waiting lists and the consequent absenteeism of patients. Patient no-shows imply a loss of time and resources, and in this paper, the strategy of overbooking is analysed as a solution. Here, a real waiting list process is simulated with discrete event simulation (DES) software, and the activities performed by hospital staff are reproduced. The methodology employed combines agile manufacturing and Six Sigma, focusing on a paediatric public hospital pavilion. Different scenarios show that the overbooking strategy is effective in ensuring fairness of access to services. Indeed, all patients respect the times dictated by the waiting list, without “favouritism”, which is guaranteed by the logic of replacement. In a comparison between a real sample of bookings and a simulated sample designed to improve no-shows, no statistically significant difference is found. This model will allow health managers to provide patients with faster service and to better manage their resources.

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.