Download PDF
Methods Inf Med 2017; 56(04): 294-307
DOI: 10.3414/ME16-01-0112
Paper
Schattauer GmbH

A Multi-way Multi-task Learning Approach for Multinomial Logistic Regression[*]

An Application in Joint Prediction of Appointment Miss-opportunities across Multiple Clinics
Adel Alaeddini
1   Department of Mechanical Engineering, University of Texas at San Antonio, San Antonio, TX, USA
,
Seung Hee Hong
1   Department of Mechanical Engineering, University of Texas at San Antonio, San Antonio, TX, USA
› Author Affiliations Funding This research was partially supported by National Institutes of Health (NIH/NIGMS) under Grant No. 1SC2GM118266–01.
Further Information

Publication History

received: 30 September 2016

accepted in revised form: 15 February 2017

Publication Date:
24 January 2018 (online)

    Permissions and Reprints

Summary

Objectives: Whether they have been engineered for it or not, most healthcare systems experience a variety of unexpected events such as appointment miss-opportunities that can have significant impact on their revenue, cost and resource utilization. In this paper, a multi-way multi-task learning model based on multinomial logistic regression is proposed to jointly predict the occurrence of different types of miss-opportunities at multiple clinics.

Methods: An extension of L 1/L 2 regulariza- tion is proposed to enable transfer of information among various types of miss-opportunities as well as different clinics. A proximal algorithm is developed to transform the convex but non-smooth likelihood function of the multi-way multi-task learning model into a convex and smooth optimization problem solvable using gradient descent algorithm.

Results: A dataset of real attendance records of patients at four different clinics of a VA medical center is used to verify the performance of the proposed multi-task learning approach. Additionally, a simulation study, investigating more general data situations is provided to highlight the specific aspects of the proposed approach. Various individual and integrated multinomial logistic regression models with/without LASSO penalty along with a number of other common classification algorithms are fitted and compared against the proposed multi-way multi-task learning approach. Fivefold cross validation is used to estimate comparing models parameters and their predictive accuracy. The multi-way multi-task learning framework enables the proposed approach to achieve a considerable rate of parameter shrinkage and superior prediction accuracy across various types of miss-opportunities and clinics.

Conclusions: The proposed approach provides an integrated structure to effectively transfer knowledge among different miss-opportunities and clinics to reduce model size, increase estimation efficacy, and more importantly improve predictions results. The proposed framework can be effectively applied to medical centers with multiple clinics, especially those suffering from information scarcity on some type of disruptions and/or clinics.

Keywords

Multinomial logistic regression - multi-way multi-task learning - regularization - miss-opportunities prediction - proximal gradient descent

* Supplementary material published on our website https://doi.org/10.3414/ME16-01-0112


 

  • References

  • 1 Rust CT, Gallups NH, Clark WS, Jones DS, Wilcox WD. Patient appointment failures in pediatric resident continuity clinics. Archives of Pediatrics & Adolescent Medicine. 1995; 149 (06) 693-695.
    CrossrefPubMedGoogle Scholar
  • 2 Moore CG, Wilson-Witherspoon P, Probst JC. Time and money: effects of no-shows at a family practice residency clinic. Fam Med. 2001; 33 (07) 522-527.
    PubMedGoogle Scholar
  • 3 Bech M. The economics of non-attendance and the expected effect of charging a fine on non-attendees. Health Policy. 2005; 74 (02) 181-191.
    CrossrefPubMedGoogle Scholar
  • 4 Barron WM. Failed appointments. Who misses them, why they are missed, and what can be done. Primary Care. 1980; 7 (04) 563-574.
    PubMedGoogle Scholar
  • 5 Hixon AL, Chapman RW, Nuovo J. Failure to keep clinic appointments: implications for residency education and productivity. Fam Med. 1999; 31: 627-630.
    PubMedGoogle Scholar
  • 6 Cayirli T, Veral E. Outpatient scheduling in health care: A review of literature. Production and Operations Management. 2003; 12 (04) 519-549.
    PubMedGoogle Scholar
  • 7 Cote MJ. Patient flow and resource utilization in an outpatient clinic. Socio-Economic Planning Sciences. 1999; 33 (03) 231-245.
    CrossrefPubMedGoogle Scholar
  • 8 Ho C-J, Lau H-S. Minimizing total cost in scheduling outpatient appointments. Management Science. 1992; 38 (12) 1750-1764.
    CrossrefPubMedGoogle Scholar
  • 9 Daggy J, Lawley M, Willis D, Thayer D, Suelzer C, DeLaurentis P-C. et al. Using no-show modeling to improve clinic performance. Health Informatics Journal. 2010; 16 (04) 246-259.
    CrossrefPubMedGoogle Scholar
  • 10 Alaeddini A, Yang K, Reeves P, Reddy CK. A hybrid prediction model for no-shows and cancellations of outpatient appointments. IIE Transactions on Healthcare Systems Engineering. 2015; 5 (01) 14-32.
    CrossrefPubMedGoogle Scholar
  • 11 Chakraborty S, Muthuraman K, Lawley M. Sequential clinical scheduling with patient no-shows and general service time distributions. IIE Transactions. 2010; 42 (05) 354-366.
    CrossrefPubMedGoogle Scholar
  • 12 Gupta D, Denton B. Appointment scheduling in health care: Challenges and opportunities. IIE Transactions. 2008; 40 (09) 800-819.
    CrossrefPubMedGoogle Scholar
  • 13 Hassin R, Mendel S. Scheduling arrivals to queues: A single-server model with no-shows. Management Science. 2008; 54 (03) 565-572.
    CrossrefPubMedGoogle Scholar
  • 14 LaGanga LR, Lawrence SR. Clinic overbooking to improve patient access and increase provider productivity. Decision Sciences. 2007; 38 (02) 251-276.
    CrossrefPubMedGoogle Scholar
  • 15 Liu N, Ziya S, Kulkarni VG. Dynamic scheduling of outpatient appointments under patient no- shows and cancellations. Manufacturing & Service Operations Management. 2010; 12 (02) 347-364.
    CrossrefPubMedGoogle Scholar
  • 16 Muthuraman K, Lawley M. A stochastic overbooking model for outpatient clinical scheduling with no-shows. IIE Transactions. 2008; 40 (09) 820-837.
    CrossrefPubMedGoogle Scholar
  • 17 Zeng B, Turkcan A, Lin J, Lawley M. Clinic scheduling models with overbooking for patients with heterogeneous no-show probabilities. Annals of Operations Research. 2010; 178 (01) 121-144.
    CrossrefPubMedGoogle Scholar
  • 18 Bowser DM, Utz S, Glick D, Harmon R. A systematic review of the relationship of diabetes mellitus, depression, and missed appointments in a low-income uninsured population. Archives of Psychiatric Nursing. 2010; 24 (05) 317-329.
    CrossrefPubMedGoogle Scholar
  • 19 Denhaerynck K, Manhaeve D, Dobbels F, Garzoni D, Nolte C, De Geest S. Prevalence and consequences of nonadherence to hemodialysis regimens. American Journal of Critical Care. 2007; 16 (03) 222-235.
    PubMedGoogle Scholar
  • 20 George A, Rubin G. Non-attendance in general practice: a systematic review and its implications for access to primary health care. Family Practice. 2003; 20 (02) 178-184.
    CrossrefPubMedGoogle Scholar
  • 21 Rowett M, Reda S, Makhoul S. Prompts to encourage appointment attendance for people with serious mental illness. Schizophrenia Bulletin. 2010: sbq050.
    PubMedGoogle Scholar
  • 22 Turkcan A, Nuti L, DeLaurentis PC, Tian Z, Daggy J, Zhang L, Lawley M, Sands L. No-show modeling for adult ambulatory clinics. Denton BT. Handbook of Healthcare Operations Management. Volume 184.. New York: Springer; 2013: 251-288.
    Google Scholar
  • 23 Mitchell AJ, Selmes T. A comparative survey of missed initial and follow-up appointments to psychiatric specialties in the United Kingdom. Psychiatric Services. 2007; 58 (06) 868-871.
    CrossrefPubMedGoogle Scholar
  • 24 Cayirli T, Veral E, Rosen H. Designing appointment scheduling systems for ambulatory care services. Health Care Management Science. 2006; 9 (01) 47-58.
    CrossrefPubMedGoogle Scholar
  • 25 Cayirli T, Veral E, Rosen H. Assessment of patient classification in appointment system design. Production and Operations Management. 2008; 17 (03) 338-353.
    CrossrefPubMedGoogle Scholar
  • 26 Corfield L, Schizas A, Williams A, Noorani A. Non-attendance at the colorectal clinic: a prospective audit. Annals of the Royal College of Surgeons of England. 2008; 90 (05) 377.
    CrossrefPubMedGoogle Scholar
  • 27 Gany F, Ramirez J, Chen S, Leng JC. Targeting social and economic correlates of cancer treatment appointment keeping among immigrant Chinese patients. Journal of Urban Health. 2011; 88 (01) 98-103.
    CrossrefPubMedGoogle Scholar
  • 28 Neal RD, Hussain-Gambles M, Allgar VL, Lawlor DA, Dempsey O. Reasons for and consequences of missed appointments in general practice in the UK: questionnaire survey and prospective review of medical records. BMC Family Practice. 2005; 6 (01) 47.
    CrossrefPubMedGoogle Scholar
  • 29 Park WB, Kim JY, Kim S-H, Kim HB, Kim NJ, Oh M-D. et al. Self-reported reasons among HIV-in- fected patients for missing clinic appointments. International Journal of STD & AIDS. 2008; 19 (02) 125-126.
    CrossrefPubMedGoogle Scholar
  • 30 Sarnquist CC, Soni S, Hwang H, Topol BB, Mutima S, Maldonado YA. Rural HIV-infected women’s access to medical care: ongoing needs in California. AIDS Care. 2011; 23 (07) 792-796.
    CrossrefPubMedGoogle Scholar
  • 31 Cashman SB, Savageau JA, Lemay CA, Ferguson W. Patient health status and appointment keeping in an urban community health center. Journal of health Care for the Poor and Underserved. 2004; 15 (03) 474-488.
    CrossrefPubMedGoogle Scholar
  • 32 Alafaireet P, Houghton H, Petroski G, Gong Y, Savage GT. Toward determining the structure of psychiatric visit nonadherence. The Journal of Ambulatory Care Management. 2010; 33 (02) 108-116.
    CrossrefPubMedGoogle Scholar
  • 33 Cohen A, Dreiher J, Vardy D, Weitzman D. Nonat- tendance in a dermatology clinic - a large sample analysis. Journal of the European Academy of Dermatology and Venereology. 2008; 22 (10) 1178-1183.
    CrossrefPubMedGoogle Scholar
  • 34 Lehmann T, Aebi A, Lehmann D, Olivet MB, Stalder H. Missed appointments at a Swiss university outpatient clinic. Public Health. 2007; 121 (10) 790-799.
    CrossrefPubMedGoogle Scholar
  • 35 Schectman JM, Schorling JB, Voss JD. Appointment adherence and disparities in outcomes among patients with diabetes. Journal of General Internal Medicine. 2008; 23 (10) 1685-1687.
    CrossrefPubMedGoogle Scholar
  • 36 Murphy K, Edelstein H, Smith L, Clanon K, Schweitzer B, Reynolds L. et al. Treatment of HIV in outpatients with schizophrenia, schizoaffective disorder and bipolar disease at two county clinics. Community Mental Health Journal. 2011; 47 (06) 668-671.
    CrossrefPubMedGoogle Scholar
  • 37 Bigby J, Pappius E, Cook EF, Goldman L. Medical consequences of missed appointments. Archives of Internal Medicine. 1984; 144 (06) 1163-1166.
    CrossrefPubMedGoogle Scholar
  • 38 Nuti S, Seghieri C, Vainieri M, Zett S. Assessment and improvement of the Italian healthcare system: first evidence from a pilot national performance evaluation system. Journal of Healthcare Management. 2012; 57 (03) 182-198 discussion 198-199.
    CrossrefPubMedGoogle Scholar
  • 39 Obialo CI, Bashir K, Goring S, Robinson B, Quarshie A, Al-Mahmoud A. et al. Dialysis “No-Show” on Saturdays: Implications of the Weekly Hemo- dialysis Schedules on Nonadherence and Outcomes. Journal of the National Medical Association. 2008; 100 (04) 412-419.
    CrossrefPubMedGoogle Scholar
  • 40 Murray M, Tantau C. Same-day appointments: exploding the access paradigm. Family Practice Management. 2000; 7 (08) 45-50.
    PubMedGoogle Scholar
  • 41 LaGanga LR. Lean service operations: reflections and new directions for capacity expansion in outpatient clinics. Journal of Operations Management. 2011; 29 (05) 422-433.
    CrossrefPubMedGoogle Scholar
  • 42 Fischman D. Applying lean six sigma methodologies to improve efficiency, timeliness of care, and quality of care in an internal medicine residency clinic. Quality Management in Healthcare. 2010; 19 (03) 201-210.
    PubMedGoogle Scholar
  • 43 Garuda SR, Javalgi RG, Talluri VS. Tackling no- show behavior: a market-driven approach. Health Marketing Quarterly. 1998; 15 (04) 25-44.
    PubMedGoogle Scholar
  • 44 Guse CE, Richardson L, Carle M, Schmidt K. The effect of exit-interview patient education on no- show rates at a family practice residency clinic. The Journal of the American Board of Family Practice. 2003; 16 (05) 399-404.
    CrossrefPubMedGoogle Scholar
  • 45 Can S, Macfarlane T, O’Brien K. The use of postal reminders to reduce non-attendance at an orthodontic clinic: a randomised controlled trial. British Dental Journal. 2003; 195 (04) 199-201.
    CrossrefPubMedGoogle Scholar
  • 46 Hardy K, O’Brien S, Furlong N. Quality improvement report: Information given to patients before appointments and its effect on non-attendance rate. BMJ. 2001; 323 7324 1298-300.
    CrossrefPubMedGoogle Scholar
  • 47 Kopach R, DeLaurentis P-C, Lawley M, Muthuraman K, Ozsen L, Rardin R. et al. Effects of clinical characteristics on successful open access scheduling. Health Care Management Science. 2007; 10 (02) 111-124.
    CrossrefPubMedGoogle Scholar
  • 48 Glowacka KJ, Henry RM, May JH. A hybrid data mining/simulation approach for modelling outpatient no-shows in clinic scheduling. Journal of the Operational Research Society. 2009; 60 (08) 1056-1068.
    CrossrefPubMedGoogle Scholar
  • 49 Alaeddini A, Yang K, Reddy C, Yu S. A probabilistic model for predicting the probability of no- show in hospital appointments. Health Care Management Science. 2011; 14 (02) 146-157.
    CrossrefPubMedGoogle Scholar
  • 50 Hastie T, Tibshirani R, Friedman J, Franklin J. The elements of statistical learning: data mining, inference and prediction. The Mathematical Intelligencer. 2005; 27 (02) 83-85.
    PubMedGoogle Scholar
  • 51 Caruana R. Multitask learning. Thrun S, Pratt L. Learning to learn.. Springer; 1998: 95-133.
    Google Scholar
  • 52 Ando RK, Zhang T. A framework for learning predictive structures from multiple tasks and unlabeled data. The Journal of Machine Learning Research. 2005; 6: 1817-1853.
    PubMedGoogle Scholar
  • 53 Chapelle O, Shivaswamy P, Vadrevu S, Weinberger K, Zhang Y, Tseng B. Multi-task learning for boosting with application to web search ranking. Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining. 2010. ACM.;
    Google Scholar
  • 54 Bakker B, Heskes T. Task clustering and gating for bayesian multitask learning. The Journal of Machine Learning Research. 2003; 4: 83-99.
    PubMedGoogle Scholar
  • 55 Chari R, Lockwood WW, Coe BP, Chu A, Macey D, Thomson A. et al. SIGMA: a system for integrative genomic microarray analysis of cancer genomes. BMC Genomics. 2006; 7 (01) 324.
    CrossrefPubMedGoogle Scholar
  • 56 Meier L, Van De Geer S, Bühlmann P. The group lasso for logistic regression. Journal of the Royal Statistical Society: Series B (Statistical Methodology). 2008; 70 (01) 53-71.
    PubMedGoogle Scholar
  • 57 Friedman J, Hastie T, Tibshirani R. A note on the group lasso and a sparse group lasso. arXiv preprint arXiv:10010736. 2010
    PubMedGoogle Scholar
  • 58 Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent. Journal of Statistical Software. 2010; 33 (01) 1.
    PubMedGoogle Scholar
  • 59 Obozinski GR, Wainwright MJ, Jordan MI. High-dimensional support union recovery in multivariate regression. Advances in Neural Information Processing Systems. 2008: 1217-1224.
    PubMedGoogle Scholar
  • 60 Beck A, Teboulle M. A fast iterative shrinkage- thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences. 2009; 2 (01) 183-202.
    CrossrefPubMedGoogle Scholar
  • 61 Tseng P. Approximation accuracy, gradient methods, and error bound for structured convex optimization. Mathematical Programming. 2010; 125 (02) 263-295.
    CrossrefPubMedGoogle Scholar
  • 62 Chen X, Lin Q, Kim S, Xing EP. An efficient proximal-gradient method for single and multi-task regression with structured sparsity. stat. 2010; 1050: 26.
    PubMedGoogle Scholar
  • 63 Chen X, Lin Q, Kim S, Carbonell JG, Xing EP. Smoothing proximal gradient method for general structured sparse regression. The Annals of Applied Statistics. 2012; 6 (02) 719-752.
    CrossrefPubMedGoogle Scholar
  • 64 Nesterov Y. A method of solving a convex programming problem with convergence rate O (1/k2). Soviet Mathematics Doklady. 1983; 27 (02) 327-376.
    PubMedGoogle Scholar
  • 65 Nesterov Y. Introductory lectures on convex optimization: A basic course. New York: Springer; 2004
    Google Scholar
  • 66 Aarts E, Korst J. Simulated Annealing and Boltzmann Machines:: A Stochastic Approach to Combinatorial Optimization and Neural Computing. Chichester: Wiley; 1989
    Google Scholar
  • 67 Vaz AIF, Vicente LN. A particle swarm pattern search method for bound constrained global optimization. Journal of Global Optimization. 2007; 39 (02) 197-219.
    CrossrefPubMedGoogle Scholar
  • 68 Wright SJ, Nowak RD, Figueiredo MA. Sparse reconstruction by separable approximation. IEEE Transactions on Signal Processing. 2009; 57 (07) 2479-2493.
    CrossrefPubMedGoogle Scholar
  • 69 Barzilai J, Borwein JM. Two-point step size gradient methods. IMA Journal of Numerical Analysis. 1988; 8 (01) 141-148.
    CrossrefPubMedGoogle Scholar
  • 70 Hand DJ, Daly F, McConway K, Lunn D, Ostrowski E. A handbook of small data sets:. Boca Raton: CRC Press; 1993
    Google Scholar
  • 71 Steyerberg EW, Eijkemans MJ, Harrell FE, Habbema JDF. Prognostic modeling with logistic regression analysis in search of a sensible strategy in small data sets. Medical Decision Making. 2001; 21 (01) 45-56.
    CrossrefPubMedGoogle Scholar
  • 72 James G, Witten D, Hastie T, Tibshirani R. An introduction to statistical learning:. New York: Springer; 2013
    Google Scholar
  • 73 Breiman L. Random forests. Machine Learning. 2001; 45 (01) 5-32.
    CrossrefPubMedGoogle Scholar
  • 74 Friedman N, Geiger D, Goldszmidt M. Bayesian network classifiers. Machine Learning. 1997; 29 2-3 131-163.
    CrossrefPubMedGoogle Scholar
  • 75 Jensen FV. An introduction to Bayesian networks. London: UCL Press; 1996
    Google Scholar
  • 76 Haykin SO. Neural networks and learning machines.. 3rd ed. Upper Saddle River: Pearson Education; 2009
  • 77 Platt JC. 12 fast training of support vector machines using sequential minimal optimization. Advances in Kernel Methods. 1999: 185-208.
    PubMedGoogle Scholar
  • 78 Keerthi SS, Shevade SK, Bhattacharyya C, Murthy KRK. Improvements to Platt’s SMO algorithm for SVM classifier design. Neural Computation. 2001; 13 (03) 637-649.
    CrossrefPubMedGoogle Scholar