Services on Demand
Journal
Article
English (pdf)
Article in xml format
Article references
Automatic translation
Send this article by e-mailIndicators
-
Cited by SciELO -
Access statistics
Related links
-
Cited by Google -
Similars in
SciELO -
Similars in Google
Share
Permalink
Revista Colombiana de Estadística
Print version ISSN 0120-1751
Rev.Colomb.Estad. vol.45 no.2 Bogotá July/Dec. 2022 Epub Feb 01, 2023
https://doi.org/10.15446/rce.v45n2.101597
Artículos originales de investigación
Measuring Individual Benefits of Medical Treatments Using Longitudinal Hospital Data with Non-Ignorable Missing Responses Caused by Patient Discharge: Application to the Study of Benefits of Pain Management Post Spinal Fusion
Medición de los beneficios individuales de tratamientos médicos a partir de datos hospitalarios longitudinales con respuestas faltantes no ignorables causadas por la alta del paciente: Aplicación al estudio de los beneficios del tratamiento contra el dolor después de una fusión espinal
1 Boston Strategic Partners, Inc., Boston, MA, United States
2 Department of Hygiene, Epidemiology and Medical Statistics, National and Kapodistrian University of Athens, Medical School, Athens, Greece
3 Mental Health Research Center at Eastern State Hospital, University of Kentucky, Lexington, KY, United States
4 Department of Biostatistics & Data Science, The University of Kansas Medical Center, Kansas City, KS, United States
Electronic health records (EHR) provide valuable resources for longitudinal studies and understanding risk factors associated with poor clinical outcomes. However, they may not contain complete follow-ups, and the missing data may not be at random since hospital discharge may depend in part on expected but unrecorded clinical outcomes that occur after patient discharge. These non-ignorable missing data requires appropriate analysis methods. Here, we are interested in measuring and analyzing individual treatment benefits of medical treatments in patients recorded in EHR databases. We present a method for predicting individual benefits that handles non-ignorable missingness due to hospital discharge. The longitudinal clinical outcome of interest is modeled simultaneously with the hospital length of stay using a joint mixed-effects model, and individual benefits are predicted through a frequentist approach: the empirical Bayesian approach. We illustrate our approach by assessing individual pain management benefits to patients who underwent spinal fusion surgery. By calculating sample percentiles of empirical Bayes predictors of individual benefits, we examine the evolution of individual benefits over time. We additionally compare these percentiles with percentiles calculated with a Monte Carlo approach. We showed that empirical Bayes predictors of individual benefits do not only allow examining benefits in specific patients but also reflect overall population trends reliably.
Key words: Electronic health records; Empirical Bayesian prediction; Joint mixed models; Non-ignorable missing data; Observational data; Random effects
Los registros de salud electrónicos (RSE) suministran recursos valiosos para estudios longitudinales y para comprender los factores de riesgo asociados con pobres resultados clínicos. Sin embargo, estos podrían no contener seguimientos completos, y los datos faltantes podrían no ser al azar, debido a que el alta hospitalaria puede depender en parte de resultados clínicos esperados pero no registrados que ocurren después de dar de alta al paciente. Esta ausencia de datos no ignorables requiere métodos apropiados de análisis. Aquí estamos interesados en medir y analizar beneficios individuales de tratamientos médicos en pacientes consignados en bases de datos RSE. Proponemos un método para predecir beneficios individuales el cual maneja los datos faltantes debidos al alta hospitalaria. La respuesta clínica longitudinal de interés se modela junto con el tiempo de estadía en el hospital usando un modelo conjunto de efectos mixtos, y los beneficios individuales se predicen por medio de un enfoque frecuentista: el enfoque Bayesiano empírico. Nuestro enfoque es ilustrado evaluando los beneficios individuales del tratamiendo para el dolor en pacientes que fueron sometidos a cirugía de fusión espinal. Aquí examinamos la evolución de los beneficios individuales a través del tiempo mediante el cálculo de los percentiles muéstrales de los predictores de Bayes empíricos de los beneficios individuales. También comparamos estos percentiles con percentiles calculados mediante un enfoque Monte Cario. Los resultados mostraron que los predictores de Bayes empíricos de beneficios individuales no sólo permiten examinar beneficios en pacientes específicos sino que también reflejan confiablemente las tendencias poblacionales globales.
Palabras clave: Datos faltantes no ignorables; Datos observacionales; Efectos aleatorios; Modelos mixtos conjuntos; Predicción Bayesiana empírica;Registros de salud electrónicos
References
Adogwa, O., Parker, S. L., Shau, D. N., Mendenhall, S. K., Bydon, A., Cheng, J. S., Asher, A. L. & McGirt, M. J. (2013), 'Preoperative Zung depression scale predicts patient satisfaction independent of the extent of improvement after revision lumbar surgery', The Spine Journal 13, 501-506. [ Links ]
Albers, D. J., Elhadad, N., Claassen, J., Perotte, R., Goldstein, A. & Hripcsak, G. (2018), 'Estimating summary statistics for electronic health record laboratory data for use in high-throughput phenotyping algorithms', Journal of Biomedical Informatics 78, 87-101. [ Links ]
Anderson, J. T., Haas, A. R., Percy, R., Woods, S. T., Ahn, U. M. & Ahn, N. U. (2015), 'Clinical depression is a strong predictor of poor lumbar fusion outcomes among workers' compensation subjects', Spine 40, 748-756. [ Links ]
Andrews, N. & Cho, H. (2018), 'Validating effectiveness of subgroup identification for longitudinal data', Statistics in Medicine 37, 98-106. [ Links ]
Armero, C, Forte, A., Perpiñan, H., Sanahuja, M. J. & Agusti, S. (2018), 'Bayesian joint modeling for assessing the progression of chronic kidney disease in children', Statistical Methods in Medical Research 27, 298-311. [ Links ]
Arnold, L. M., Palmer, R. H., Gendreau, R. M. & Chen, W. (2012), 'Relationships among pain, depressed mood, and global status in fibromyalgia patients: post hoc analyses of a randomized, placebo-controlled trial of milnacipran', Psychosomatics 53, 371-379. [ Links ]
Botts, S., Diaz, F. J., Santoro, V., Spina, E., Muscatello, M. R., Cogollo, M., Castro, F. E. & de Leon, J. (2008), 'Estimating the effects of co-medications on plasma olanzapine concentrations by using a mixed model', Progress in Neuro-Psychopharmacology & Biological Psychiatry 32, 1453-1458. [ Links ]
Cho, H., Wang, P. & Qu, A. (2017), 'Personalized treatment for longitudinal data using unspecified random-effects model', Statistica Sinica 27, 187-205. [ Links ]
Crowther, M. J., Abrams, K. R. & Lambert, P. C. (2012), 'Flexible parametric joint modelling of longitudinal and survival', Statistics in Medicine 31, 4456 -4471. [ Links ]
De Gruttola, V. & Tu, X. M. (1994), 'Modelling progression of CD4-lymphocyte count and its relationship to survival time', Biometrics 50, 1003-1014. [ Links ]
de Leon, J. (2012), 'Evidence-based medicine versus personalized medicine: are they enemies?', Journal of Clinical Psychopharmacology 32, 153-164. [ Links ]
Diaz, F. J. (2016), 'Measuring the individual benefit of a medical or behavioral treatment using generalized linear mixed-effects models', Statistics in Medicine 35, 4077-4092. [ Links ]
Diaz, F. J. (2018), 'Construction of the design matrix for generalized linear mixed-effects models in the context of clinical trials of treatment sequences', Revista Colombiana de Estadística 41, 191-233. [ Links ]
Diaz, F. J. (2019), 'Estimating individual benefits of medical or behavioral treatments in severely ill patients', Statistical Methods in Medical Research 28, 911-927. [ Links ]
Diaz, F. J. (2021), 'Using population crossover trials to improve the decision process regarding treatment individualization in N-of-1 trials', Statistics in Medicine 40, 4345-4361. [ Links ]
Diaz, F. J., Berg, M. J., Krebill, R., Well, v. T., Gidal, B. E., Alloway, R. & Privitera, M. (2013), 'Random-effects linear modeling and sample size tables for two special crossover designs of average bioequivalence studies: the four-period, two-sequence, two-formulation and six-period, three-sequence, three-formulation designs', Clinical Pharmacokinetics 52, 1033-1043. [ Links ]
Diaz, F. J., Cogollo, M. R., Spina, E., Santoro, V., Rendon, D. M. & de Leon, J. (2012b), 'Drug Dosage Individualization Based on a Random-Effects Linear Model', Journal of Biopharmaceutical Statistics 22, 463-484. [ Links ]
Diaz, F. J. & de Leon, J. (2013), 'The mathematics of drug dose individualization should be built with random effects linear models', Therapeutic Drug Monitoring 35, 276-277. [ Links ]
Diaz, F. J., Eap, C. B., Ansermot, N., Crettol, S., Spina, E. & de Leon, J. (2014), 'Can valproic acid be an inducer of clozapine metabolism?', Pharmacopsychiatry 47, 89-96. [ Links ]
Diaz, F. J., Rivera, T. E., Josiassen, R. C. & de Leon, J. (2007), 'Individualizing drug dosage by using a random intercept linear model', Statistics in Medicine 26, 2052-2073. [ Links ]
Diaz, F. J., Santoro, V., Spina, E., Cogollo, M., Rivera, T. E., Botts, S. & de Leon, J. (2008), 'Estimating the size of the effects of co-medications on plasma clozapine concentrations using a model that controls for clozapine doses and confounding variables', Pharmacopsychiatry 41, 81-91. [ Links ]
Diaz, F. J., Yeh, H.-W. & de Leon, J. (2012a), 'Role of Statistical Random-Effects Linear Models in Personalized Medicine', Current Pharmacogenomics and Personalized Medicine 10, 22-32. [ Links ]
Edelstein, C. L. (2008), 'Biomarkers of acute kidney injury', Advances in Chronic Kidney Disease 15, 222-234. [ Links ]
Frees, E. W. (2004), Longitudinal and Panel Data, Cambridge University Press, Cambridge. [ Links ]
Gaudin, D., Krafcik, B. M., Mansour, T. R. & Alnemari, A. (2017), 'Considerations in spinal fusion surgery for chronic lumbar pain: psychosocial factors, rating scales, and perioperative patient education-a review of the literature', World Neurosurgery 98, 21-27. [ Links ]
Gerbershagen, H. J., Pogatzki-Zahn, E., Aduckathil, S., Peelen, L. M., Kappen, T. H., van Wijck, A. J., Kalkman, C. J. & Meissner, W. (2014), 'Procedure-specific risk factor analysis for the development of severe postoperative pain', Anesthesiology 120, 1237-1245. [ Links ]
Gewandter, J. S., McDermott, M. P., He, H., Gao, S., Cai, X., Farrar, J. T., Katz, N. P., Markman, J. D., Senn, S., Turk, D. C. & Dworkin, R. H. (2019), 'Demonstrating heterogeneity of treatment effects among patients: an overlooked but important step toward precision medicine', Clinical Pharmacology & Therapeutics 106, 204-210. [ Links ]
Greden, J. F. (2009), 'Treating depression and pain', Journal of Clinical Psychiatry 70(6), e16. [ Links ]
Gronski, L., Martinson, W., Singh, K. P. & Ryan, J. (2012), 'Utility of daily troponin orders for identifying acute myocardial infarction patients for quality improvement', Critical Pathway in Cardiology 11, 74-76. [ Links ]
Hedeker, D. & Gibbons, R. D. (2006), Longitudinal Data Analysis, Wiley-Interscience, Hoboken, NJ. [ Links ]
Hickey, G. L., Philipson, P., Jorgensen, A. & Kolamunnage-Dona, R. (2018), 'joineRML: a joint model and software package for time-to-event and multivariate longitudinal outcomes', BMC Medical Research Methodology 18, 50. [doi.org/10.1186/sl2874-018-0502-l]. [ Links ]
Ibrahim, J. G. & Molenberghs, G. (2009), 'Missing data methods in longitudinal studies: a review', Test (Madr) 18, 1-43. [ Links ]
Johnson, N. L. (1949), 'Systems of Frequency Curves Generated by Methods of Translation', Biometrika 36, 149-176. [ Links ]
Laird, N. M. (1998), 'Missing data in longitudinal studies', Statistics in Medicine 7, 305-315. [ Links ]
Lesaffre, E., Rizopoulos, D. & Tsonaka, R. (2007), 'The logistic transform for bounded outcome scores', Biostatistics 8, 72-85. [ Links ]
Little, R. J. A. & Rubin, D. B. (2002), Statistical Analysis with Missing Data, Second Edition, Wiley, New York. [ Links ]
Lotzke, H., Jakobsson, M., Brisby, H., Gutke, A., Hágg, O., Smeets, R., den Hollander, M., Olsson, L. E. & Lundberg, M. (2016), 'Use of the PREPARE (PREhabilitation, Physical Activity and exeRcisE) program to improve outcomes after lumbar fusion surgery for severe low back pain: a study protocol of a person-centred randomised controlled trial', BMC Musculoskeletal Disorders 17(1), 349. doi: [10.1186/sl2891-016-1203-8]. [ Links ]
Miksad, R. A. & Abernethy, A. P. (2018), 'Harnessing the power of real-world evidence (RWE): A checklist to ensure regulatory-grade Data Quality', Clinical Pharmacology & Therapeutics 103, 202-205. [ Links ]
Pantazis, N. & Touloumi, G. (2010), 'Analyzing longitudinal data in the presence of informative drop-out: The jmrel command', Stata Journal 10, 226-251. [ Links ]
Papageorgiou, G., Mauff, K., Tomer, A. & Rizopoulos, D. (2019), 'An overview of joint modeling of time-to-event and longitudinal outcomes', Annual Review of Statistics and its Application 6, 223-240. [ Links ]
Ruberg, S. J., Chen, L. & Wang, Y. (2010), 'The mean does not mean as much anymore: finding sub-groups for tailored therapeutics', Clinical Trials 7, 574-583. [ Links ]
Schluchter, M. D. (1992), 'Methods for the analysis of informatively censored longitudinal data', Statistics in Medicine 11, 1861-1870. [ Links ]
Schluchter, M. D. & Piccorelli, A. V. (2019), 'Shared parameter models for joint analysis of longitudinal and survival data with left truncation due to delayed entry - Applications to cystic fibrosis', Statistical Methods in Medical Research 28, 1489-1507. [ Links ]
Senn, S. (2016), 'Mastering variation: variance components and personalised medicine', Statistics in Medicine 35, 966-977. [ Links ]
Shardell, M. & Ferrucci, L. (2018), 'Joint mixed-effects models for causal inference with longitudinal data', Statistics in Medicine 37, 829-846. [ Links ]
Shaw, A. D., Mythen, M. G., Shook, D., Hayashida, D. K., Zhang, X., Skaar, J. R., Iyengar, S. S. & Munson, S. H. (2018), 'Pulmonary artery catheter use in adult patients undergoing cardiac surgery: a retrospective, cohort study', Perioperative Medicine (Lond) 7, 24. [doi.org/10.1186/sl3741-018-0103-x]. [ Links ]
Shirafkan, H., Mahmoudi-Gharaei, J., Fotouhi, A., Mozaffarpur, S. A., Yaseri, M. & Hoseini, M. (2020), 'Individualizing the dosage of Methylphenidate in children with attention deficit hyperactivity disorder', BMC Medical Research Methodology 20, 56. [doi.org/10.1186/sl2874-020-00934-y]. [ Links ]
Touloumi, G., Pocock, S. J., Babiker, A. G. & Darbyshire, J. H. (1999), 'Estimation and comparison of rates of change in longitudinal studies with informative drop-outs', Statistics in Medicine 18, 1215-1233. [ Links ]
Trivedi, M. H. (2004), 'The link between depression and physical symptoms', Primary Care Companion of the Journal of Clinical Psychiatry 6(Suppl 1), 12 -16. [ Links ]
Urman, R. D., Boing, E. A., Pham, A. T., Khangulov, V., Fain, R., Nathanson, B. H., Zhang, X., Wan, G. J., Lovelace, B. & Chillo, J. (2018), 'Improved outcomes associated with the use of intravenous acetaminophen for management of acute post-surgical pain in cesarean sections and hysterectomies', Journal of Clinical Medicine Research 10, 499-507. [ Links ]
Wang, Z. & Diaz, F. J. (2020), 'A graphical approach to assess the goodness-of-fit of random-effects linear models when the goal is to measure individual benefits of medical treatments in severely ill patients', BMC Medical Research Methodology 20, 193. [doi.org/10.1186/sl2874-020-01054-3]. [ Links ]
Weinmann, C, Komann, M. & Meissner, W. (2017), 'Tough cookies: the older the patients, the more pain tolerating?', European Journal of Anesthesiology 34(Suppl 55), 215. [ Links ]
Woodward, M. (2014), Epidemiology: Study Design and Data Analysis, Third Edition, Chapman & Hall/CRC, Boca Raton, FL. [ Links ]
Zhang, X., de Leon, J., Crespo-Facorro, B. & Diaz, F. J. (2020), 'Measuring individual benefits of psychiatric treatment using longitudinal binary outcomes: Application to antipsychotic benefits in non-cannabis and cannabis users', Journal of Biopharmaceutical Statistics 30, 916-940. [ Links ]
Zhu, X. & Qu, A. (2016), 'Individualizing drug dosage with longitudinal data', Statistics in Medicine 35, 4474-4488. [ Links ]
Received: June 2021; Accepted: February 2022
This is an open-access article distributed under the terms of the Creative Commons Attribution License
