PREDICTION OF INTER EPISODIC TIME FOR RECURRING MENTAL ILLNESS USING ORDER STATISTICS
Keywords:Mental disorders,, order statistics, recurrent events, time to next episode, waiting time
Recurrent episodes are common across various mental disorders. Information on time to next episode, also referred as inter episodic times, provides a valuable tool for planning and evaluating the health outcomes of treatment in patients and developing effective preventive maintenance therapy. The objective is to obtain the prediction interval for the future inter episodic time when the number of previous episodes for a patient is small and inter episodic times are dependent. A data of 28 patients with a history of 3 or more recurring episodes of illness is extracted from a retrospective data of 146 patients diagnosed with mental and behavioral disorders. The prediction interval for time to occurrence of next episode is obtained using order statistics assuming that it will follow the order followed by previous inter episodic times. The validity of the results is verified using simulation studies with data generated using covariance structure of the real dataset. From the simulation studies, we found that more than 80% of the simulated inter episodic times lie in the simulated prediction intervals. This paper is highly beneficial to medical health professionals to predict time to next episode for patients with few previously known episodes of the concerned disease. The study has an implication to rare diseases where generally small database (patients) is available.
WHO International Consortium in Psychiatric Epidemiology. Cross-national comparisons of the prevalences and correlates of mental disorders. Bulletin of the World Health Organization : the International Journal of Public Health 2000;78(4):413–426. https://pubmed.ncbi.nlm.nih.gov/10885160/
Burcusa SL, Iacono WG. Risk for recurrence in depression. Clinical psychology review 2007;27(8):959-85. doi: 10.1016/j.cpr.2007.02.005.
Kessing LV. Severity of depressive episodes during the course of depressive disorder. The British journal of psychiatry 2008;192:290-293. doi: 10.1192/bjp.bp.107.038935.
Perlis RH, Ostacher MJ, Patel JK, et al. Predictors of recurrence in bipolar disorder: primary outcomes from the Systematic Treatment Enhancement Program for Bipolar Disorder (STEP-BD). The American Journal of Psychiatry 2006;163(2):217–224. doi: 10.1176/appi.ajp.163.2.217.
Amorim LD, Cai J. Modelling recurrent events: a tutorial for analysis in epidemiology. International Journal of Epidemiology 2015;44(1):324-333. doi: 10.1093/ije/dyu222.
Smedinga H, Steyerberg EW, Beukers W, et al. Prediction of Multiple Recurrent Events: A Comparison of Extended Cox Models in Bladder Cancer. American Journal of Epidemiology 2017;186(5):612-623. doi: 10.1093/aje/kwx133.
Cook RJ, Lawless JF. The Statistical Analysis of Recurrent Events (1 ed.). New York: Springer-Verlag New York 2007.
Grover G, Sabharwal A. A Parametric Approach to Estimate Survival Time of Diabetic Nephropathy with Left Truncated and Right Censored Data. International Journal of Statistics and Probability 2012:1(1):128-137. DOI:10.5539/ijsp.v1n1p128.
Arnold BC, Balakrishnan N, Nagaraja HN. A First Course in Order Statistics. Philadelphia: Society for Industrial and Applied Mathematics 1993.
Yang W, Jepson C, et al. Statistical Methods for Recurrent Event Analysis in Cohort Studies of CKD. Clinical Journal of the American Society of Nephrology 2017;12(12):2066-2073. doi: 10.2215/CJN.12841216.
Kessing LV, Olsen EW, Andersen PK. Recurrence in Affective Disorder: Analyses with Frailty Models. American Journal of Epidemiology 1999;149(5):404-411. doi: 10.1093/oxfordjournals.aje.a009827.
Doesschate MC, Bockting CL, Koeter M, et al. Prediction of Recurrence in Recurrent Depression: A 5.5-Year Prospective Study. Journal of clinical psychiatry 2010;71:984-991. doi: 10.4088/JCP.08m04858blu
Lebedev NN. Special Functions and Their Applications. New Jersey: Prentice-Hall 1965.
Ghasem T. Multivariate Log – Normal Distribution. ISI Proceedings. 53rd Session. Seoul: International Statistical Institute 2001:1000-1001. https://2001.isiproceedings.org/pdf/329.PDF.
Halliwell L. The Lognormal Random Multivariate. Casualty Actuarial Society E-Forum 2015:1-5.
Golub GH, Van Loan CF. Matrix Computations (2nd ed.). Baltimore: John Hopkins University Press 1989.
Ince PJ, Buongiorno J. Multivariate stochastic simulation with subjective multivariate normal distributions. Proceedings of the 1991 Symposium on Systems Analysis in Forest Resources : March 3-6, 1991, Charleston, South Carolina. Asheville, NC : Southeastern Forest Experiment Station. General technical report SE 1991;74:143-150. https://www.fs.usda.gov/treesearch/pubs/5784.
Schwarz G. Estimating the dimension of a model. Ann.Statist 1978;6:461–464. https://projecteuclid.org/download/pdf_1/euclid.aos/1176344136.
Stephens MA. EDF Statistics for Goodness of Fit and Some Comparisons. Journal of the American Statistical Association 1974;69:730-737.
Efron B, Tibshirani RJ. An Introduction to the Bootstrap. New York: Chapman & Hall 1993.
Grover G, Sabharwal A, Mittal J. A Bayesian Approach for Estimating Onset Time of Nephropathy for Type 2 Diabetic Patients Under Various Health Conditions. International Journal of Statistics and Probability 2013;2(2):89-101. DOI:10.5539/ijsp.v2n2p89.
Ibrahim JG, Chu H, Chen MH. Missing data in clinical studies: issues and methods. Journal of clinical oncology : official journal of the American Society of Clinical Oncology 2012;30(26):3297-303. DOI: 10.1200/JCO.2011.38.7589