Segmented linear regression modelling of time-series of binary variables in healthcare. (English) Zbl 1428.92056
Summary: Introduction. In healthcare, change is usually detected by statistical techniques comparing outcomes before and after an intervention. A common problem faced by researchers is distinguishing change due to secular trends from change due to an intervention. Interrupted time-series analysis has been shown to be effective in describing trends in retrospective time-series and in detecting change, but methods are often biased towards the point of the intervention. Binary outcomes are typically modelled by logistic regression where the log-odds of the binary event is expressed as a function of covariates such as time, making model parameters difficult to interpret. The aim of this study was to present a technique that directly models the probability of binary events to describe change patterns using linear sections. Methods. We describe a modelling method that fits progressively more complex linear sections to the time-series of binary variables. Model fitting uses maximum likelihood optimisation and models are compared for goodness of fit using Akaike’s Information Criterion. The best model describes the most likely change scenario. We applied this modelling technique to evaluate hip fracture patient mortality rate for a total of 2777 patients over a 6-year period, before and after the introduction of a dedicated hip fracture unit (HFU) at a Level 1, Major Trauma Centre. Results. The proposed modelling technique revealed time-dependent trends that explained how the implementation of the HFU influenced mortality rate in patients sustaining proximal femoral fragility fractures. The technique allowed modelling of the entire time-series without bias to the point of intervention. Modelling the binary variable of interest directly, as opposed to a transformed variable, improved the interpretability of the results. Conclusion. The proposed segmented linear regression modelling technique using maximum likelihood estimation can be employed to effectively detect trends in time-series of binary variables in retrospective studies.
MSC:
| 92C50 | Medical applications (general) |
| 62P10 | Applications of statistics to biology and medical sciences; meta analysis |
| 62M10 | Time series, auto-correlation, regression, etc. in statistics (GARCH) |
Software:
MatlabReferences:
| [1] | Hilbe, J. M., Data analysis using regression and multilevel/hierarchical models, Journal of Statistical Software, 30, 3 (2009) · doi:10.18637/jss.v030.b03 |
| [2] | Kedem, B.; Fokianos, K., Regression Models for Time Series Analysis (2002), Hoboken, NJ, USA: Wiley, Hoboken, NJ, USA · Zbl 1011.62089 |
| [3] | Valsamis, E. M.; Chouari, T.; O’Dowd-Booth, C.; Rogers, B.; Ricketts, D., Learning curves in surgery: variables, analysis and applications, Postgraduate Medical Journal, 94, 1115, 525-530 (2018) · doi:10.1136/postgradmedj-2018-135880 |
| [4] | Aminikhanghahi, S.; Cook, D. J., A survey of methods for time series change point detection, Knowledge and Information Systems, 51, 2, 339-367 (2017) · doi:10.1007/s10115-016-0987-z |
| [5] | Valsamis, E. M.; Ricketts, D.; Husband, H.; Rogers, B. A., Segmented linear regression models for assessing change in retrospective studies in healthcare, Computational and Mathematical Methods in Medicine, 2019 (2019) · Zbl 1423.92121 · doi:10.1155/2019/9810675 |
| [6] | Dung, V. T.; Tjahjowidodo, T., A direct method to solve optimal knots of B-spline curves: an application for non-uniform B-spline curves fitting, PLoS One, 12, 3 (2017) · doi:10.1371/journal.pone.0173857 |
| [7] | Dimatteo, I.; Genovese, C. R.; Kass, R. E., Bayesian curve-fitting with free-knot splines, Biometrika, 88, 4, 1055-1071 (2001) · Zbl 0986.62026 · doi:10.1093/biomet/88.4.1055 |
| [8] | Cruz, M.; Gilen, D. L.; Bender, M.; Ombao, H., Assessing health care interventions via an interrupted time series model: study power and design considerations, Statistics in Medicine, 38, 10, 1734-1752 (2019) · doi:10.1002/sim.8067 |
| [9] | Zhu, J.; Huang, H. C.; Wu, J., Modeling spatial-temporal binary data using Markov random fields, Journal of Agricultural, Biological, and Environmental Statistics, 10, 2, 212-225 (2005) · doi:10.1198/108571105X46543 |
| [10] | Taljaard, M.; McKenzie, J. E.; Ramsay, C. R.; Grimshaw, J. M., The use of segmented regression in analysing interrupted time series studies: an example in pre-hospital ambulance care, Implementation Science, 9, 1 (2014) · doi:10.1186/1748-5908-9-77 |
| [11] | Lopez Bernal, J.; Cummins, S.; Gasparrini, A., Interrupted time series regression for the evaluation of public health interventions: a tutorial, International Journal of Epidemiology, 46, 1, 1-8 (2016) · doi:10.1093/ije/dyw098 |
| [12] | Eliason, S. R., Maximum likelihood estimation: logic and practice, Journal of the American Statistical Association, 89, 427, 1150 (1994) · doi:10.2307/2290971 |
| [13] | Huang, X.; Sun, J.; Yang, X.; Yang, X., Preface, Optimization Methods and Software, 25, 5 (2010) · doi:10.1080/10556781003755313 |
| [14] | The Mathworks Inc., MATLAB—mathworks, http://www.mathworks.com/products/matlab |
| [15] | Byrd, R. H.; Hribar, M. E.; Nocedal, J., An interior point algorithm for large-scale nonlinear programming, SIAM Journal on Optimization, 9, 4, 877-900 (1999) · Zbl 0957.65057 · doi:10.1137/s1052623497325107 |
| [16] | Lomax, R. G.; Hahs-Vaughn, D. L., Statistical Concepts: A Second Course (2013), Abingdon, UK: Routledge, Abingdon, UK · doi:10.4324/9780203137802 |
| [17] | Vrieze, S. I., Model selection and psychological theory: a discussion of the differences between the Akaike information criterion (AIC) and the Bayesian information criterion (BIC), Psychological Methods, 17, 2, 228-243 (2012) · doi:10.1037/a0027127 |
| [18] | Keith, S. W.; Allison, D. B., A free-knot spline modeling framework for piecewise linear logistic regression in complex samples with body mass index and mortality as an example, Frontiers in Nutrition, 1, 16 (2014) · doi:10.3389/fnut.2014.00016 |
| [19] | Zhang, F.; Wagner, A. K.; Soumerai, S. B.; Ross-Degnan, D., Methods for estimating confidence intervals in interrupted time series analyses of health interventions, Journal of Clinical Epidemiology, 62, 2, 143-148 (2009) · doi:10.1016/j.jclinepi.2008.08.007 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
