A Bayesian Belief Network-based probabilistic mechanism to determine patient no-show risk categories

Abstract Patients who miss their appointments (no-shows) reduce revenues and impair the delivery of quality healthcare. Much research has been devoted to identifying “no-show patients”. In this study, we build a Tree Augmented Naive Bayes (TAN)-based, probabilistic data driven methodology that consists of five steps. After data acquisition and preparation in the first step, the second step is dedicated to selecting important variables through purely data-driven wrapper methods such as Extreme Gradient Boosting (XGB), Particle Swarm Optimization (PSO) and Genetic Algorithms (GA). Then, in the third step, the Synthetic Minority Oversampling Technique (SMOTE) and Random under Sampling (RUS) are employed to overcome the data imbalance issue that exists in the dataset. In the fourth step, the conditional interrelations among the predictors are obtained via TAN model, and Bayesian-belief based posterior probabilities are calculated. It should be noted that, the parameters of the TAN model are tuned in a way that there does not have to exist a conditional interrelation between every single predictor. The consistency and reliability of these posterior probabilities are then justified/investigated via the proposed algorithm. The patients are clustered into five risk groups, and a web-based decision support system graphical user interface is built as a proof of concept. Results show that interesting conditional inter-relations exist between the seven variables that are commonly selected by GA and PSO. In addition, an overall area under the receiver operating characteristic curve (ROC) score of 0.828 was achieved with a sensitivity score of 0.785. The reliable, TAN-based posterior probabilities and conditional relationships among the predictors for such a parsimonious model that has a fairly high sensitivity in detecting the minority samples, can be adopted by primary care facilities to improve the decision-making process in managing the no-show problem.

[1]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[2]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[3]  Sanja Percac-Lima,et al.  No-Show to Primary Care Appointments , 2013, Journal of primary care & community health.

[4]  Jane Garb,et al.  Risk factor model to predict a missed clinic appointment in an urban, academic, and underserved setting. , 2015, Population health management.

[5]  Mehmet Bayram Yildirim,et al.  Predicting pediatric clinic no-shows: a decision analytic framework using elastic net and Bayesian belief network , 2018, Ann. Oper. Res..

[6]  Bartosz Krawczyk,et al.  Learning from imbalanced data: open challenges and future directions , 2016, Progress in Artificial Intelligence.

[7]  David L. Olson,et al.  Advanced Data Mining Techniques , 2008 .

[8]  T Vikander,et al.  New-patient no-shows in an urban family practice center: analysis and intervention. , 1986, The Journal of family practice.

[9]  David A Hanauer,et al.  International Journal of Health Care Quality Assurance Time dependent patient no-show predictive modelling development , 2016 .

[10]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[11]  V. Charles,et al.  Stochastic simulation based genetic algorithm for chance constrained data envelopment analysis problems , 2011 .

[12]  A. Hansen.  Broken appointments in a child health conference. , 1953, Nursing outlook.

[13]  Nir Friedman,et al.  Bayesian Network Classifiers , 1997, Machine Learning.

[14]  Ali Dag,et al.  Predicting heart transplantation outcomes through data analytics , 2017, Decis. Support Syst..

[15]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[16]  G O'Brien,et al.  Telephone call reminders and attendance in an adolescent clinic. , 1998, Pediatrics.

[17]  Herbert Moskowitz,et al.  An empirical investigation into factors affecting patient cancellations and no-shows at outpatient clinics , 2014, Decis. Support Syst..

[18]  J. Car,et al.  Mobile phone messaging for preventive health care. , 2012, The Cochrane database of systematic reviews.

[19]  G. Ungvari,et al.  An Audit Study of Defaulters of Regular Psychiatric Outpatient Appointments in Hong Kong , 1995, The International journal of social psychiatry.

[20]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[21]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[22]  Karolina J. Glowacka,et al.  A hybrid data mining/simulation approach for modelling outpatient no-shows in clinic scheduling , 2009, J. Oper. Res. Soc..

[23]  Ron Kohavi,et al.  Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid , 1996, KDD.

[24]  Yawn Bp,et al.  Factors associated with appointment keeping in a family practice residency clinic. , 1994, The Journal of family practice.

[25]  M. Wieland,et al.  Missed appointments in resident continuity clinic: patient characteristics and health care outcomes. , 2011, Journal of graduate medical education.

[26]  Huan Liu,et al.  Consistency Based Feature Selection , 2000, PAKDD.

[27]  Darrell Whitley,et al.  A genetic algorithm tutorial , 1994, Statistics and Computing.

[28]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[29]  Michael Pignone,et al.  Estimating the Cost of No-Shows and Evaluating the Effects of Mitigation Strategies , 2013, Medical decision making : an international journal of the Society for Medical Decision Making.

[30]  A. Ravi Ravindran,et al.  Optimizing outpatient appointment system using machine learning algorithms and scheduling rules: A prescriptive analytics framework , 2018, Expert Syst. Appl..

[31]  Yutian Li,et al.  Individualized No‐Show Predictions: Effect on Clinic Overbooking and Appointment Reminders , 2019, Production and Operations Management.

[32]  H. N. Suresh,et al.  A novel method for image processing using Particle Swarm Optimization technique , 2016, 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT).

[33]  Greg Rubin,et al.  Non-attendance in general practice: a systematic review and its implications for access to primary health care. , 2003, Family practice.

[34]  Ali Dag,et al.  A probabilistic data-driven framework for scoring the preoperative recipient-donor heart transplant survival , 2016, Decis. Support Syst..

[35]  Ali Dag,et al.  A hybrid data mining approach for identifying the temporal effects of variables associated with breast cancer survival , 2020, Expert Syst. Appl..

[36]  David E. Goldberg,et al.  Genetic algorithms and Machine Learning , 1988, Machine Learning.

[37]  Giuseppe Palermo,et al.  Performance of PLS regression coefficients in selecting variables for each response of a multivariate PLS for omics-type data , 2009, Advances and applications in bioinformatics and chemistry : AABC.

[38]  Ali Dag,et al.  Impact of commitment, information sharing, and information usage on supplier performance: a Bayesian belief network approach , 2019, Annals of Operations Research.

[39]  K. Hardy,et al.  Information given to patients before appointments and its effect on non-attendance rate , 2001, BMJ : British Medical Journal.

[40]  Mengjie Zhang,et al.  Particle swarm optimisation for feature selection in classification: Novel initialisation and updating mechanisms , 2014, Appl. Soft Comput..

[41]  Ji Lin,et al.  Clinic scheduling models with overbooking for patients with heterogeneous no-show probabilities , 2010, Ann. Oper. Res..

[42]  Simon Fong,et al.  Accelerated Particle Swarm Optimization and Support Vector Machine for Business Optimization and Applications , 2011, NDT.

[43]  Ali Dag,et al.  Predicting graft survival among kidney transplant recipients: A Bayesian decision support model , 2018, Decis. Support Syst..

[44]  Chandan K. Reddy,et al.  A probabilistic model for predicting the probability of no-show in hospital appointments , 2011, Health care management science.

[45]  E F Cook,et al.  A multivariate approach to the prediction of no-show behavior in a primary care center. , 1982, Archives of internal medicine.

[46]  Yi-Zeng Liang,et al.  Monte Carlo cross validation , 2001 .

[47]  H. McLeod,et al.  Introducing consultant outpatient clinics to community settings to improve access to paediatrics: an observational impact study , 2015, BMJ Quality & Safety.

[48]  Randall S. Sexton,et al.  Comparing backpropagation with a genetic algorithm for neural network training , 1999 .

[49]  J. Frey,et al.  A multi-method intervention to reduce no-shows in an urban residency clinic. , 2013, Family medicine.

[50]  Hank Wang,et al.  Preventing Endoscopy Clinic No-Shows: Prospective Validation of a Predictive Overbooking Model , 2016, The American Journal of Gastroenterology.

[51]  C. G. Moore,et al.  Time and money: effects of no-shows at a family practice residency clinic. , 2001, Family medicine.

[52]  F. Agakov,et al.  Application of high-dimensional feature selection: evaluation for genomic prediction in man , 2015, Scientific Reports.

[53]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[54]  J. Talaga,et al.  Appointment breaking: causes and solutions. , 1992, Journal of health care marketing.

[55]  Mohammed Aladeemy,et al.  New feature selection methods based on opposition-based learning and self-adaptive cohort intelligence for predicting patient no-shows , 2020, Appl. Soft Comput..

[56]  Amlan Chakrabarti,et al.  Feature Selection: A Practitioner View , 2014 .

[57]  D. Hanauer,et al.  Patient No-Show Predictive Model Development using Multiple Data Sources for an Effective Overbooking Approach , 2014, Applied Clinical Informatics.

[58]  Jie Pan,et al.  Operational decision making for a referral coordination alliance- When should patients be referred and where should they be referred to? , 2020 .

[59]  N. Santamaria,et al.  Why outpatients fail to attend their scheduled appointments: a prospective comparison of differences between attenders and non-attenders. , 2003, Australian health review : a publication of the Australian Hospital Association.

[60]  R. Javalgi,et al.  Tackling no-show behavior: a market-driven approach. , 1998, Health marketing quarterly.

[61]  R. Kirschen,et al.  The Royal London Space Planning: an integration of space analysis and treatment planning: Part I: Assessing the space required to meet treatment objectives. , 2000, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics.

[62]  Alexa Boer Kimball,et al.  A multivariate analysis of dermatology missed appointment predictors. , 2013, JAMA dermatology.

[63]  Wei Li,et al.  Determinants of outpatient clinic attendance amongst adults with congenital heart disease and outcome. , 2016, International journal of cardiology.

[64]  C. N. Liu,et al.  Approximating discrete probability distributions with dependence trees , 1968, IEEE Trans. Inf. Theory.

[65]  Ling Wang,et al.  An effective hybrid PSO-based algorithm for flow shop scheduling with limited buffers , 2008, Comput. Oper. Res..

[66]  M. Cosgrove,et al.  Defaulters in general practice: reasons for default and patterns of attendance. , 1990, The British journal of general practice : the journal of the Royal College of General Practitioners.

[67]  Ali Dag,et al.  An AHP-IFT Integrated Model for Performance Evaluation of E-Commerce Web Sites , 2018, Information Systems Frontiers.

[68]  R. A. Lugo,et al.  The effect of confirmation calls on appointment-keeping behavior of patients in a children's hospital dental clinic. , 2001, Pediatric dentistry.

[69]  Henry Lenzi,et al.  Development and validation of a patient no-show predictive model at a primary care setting in Southern Brazil , 2019, PloS one.

[70]  Yi-Ming Wei,et al.  Carbon price forecasting with a novel hybrid ARIMA and least squares support vector machines methodology , 2013 .

[71]  Shih-Wei Lin,et al.  Particle swarm optimization for parameter determination and feature selection of support vector machines , 2008, Expert Syst. Appl..

[72]  Barron Wm.  Failed appointments. Who misses them, why they are missed, and what can be done. , 1980 .

[73]  Charles X. Ling,et al.  AUC: A Better Measure than Accuracy in Comparing Learning Algorithms , 2003, Canadian Conference on AI.

[74]  Tammy Toscos,et al.  Data Analytics and Modeling for Appointment No-show in Community Health Centers , 2018, Journal of primary care & community health.

[75]  Carlos Henggeler Antunes,et al.  Designing time-of-use tariffs in electricity retail markets using a bi-level model – Estimating bounds when the lower level problem cannot be exactly solved , 2020 .

[76]  M. Bech.  The economics of non-attendance and the expected effect of charging a fine on non-attendees. , 2005, Health policy.

[77]  Jihoon Yang,et al.  Feature Subset Selection Using a Genetic Algorithm , 1998, IEEE Intell. Syst..

[78]  Ali Dag,et al.  Measuring the efficiency of hospitals: a fully-ranking DEA–FAHP approach , 2019, Ann. Oper. Res..

[79]  Ali Dag,et al.  A comparative data analytic approach to construct a risk trade-off for cardiac patients' re-admissions , 2019, Ind. Manag. Data Syst..

[80]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[81]  Joanne K. Daggy,et al.  Using no-show modeling to improve clinic performance , 2010, Health Informatics J..

[82]  A. Farrow,et al.  Non-attendance or non-invitation? A case-control study of failed outpatient appointments. , 1989, BMJ.

[83]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[84]  Michele Samorani,et al.  Outpatient Appointment Scheduling Given Individual Day-Dependent No-Show Predictions , 2013 .

[85]  Nan Liu,et al.  Appointment Scheduling Under Patient Preference and No-Show Behavior , 2014, Oper. Res..