×

Segmented linear regression models for assessing change in retrospective studies in healthcare. (English) Zbl 1423.92121

Summary: Introduction. In retrospective studies, the effect of a given intervention is usually evaluated by using statistical tests to compare data from before and after the intervention. A problem with this approach is that the presence of underlying trends can lead to incorrect conclusions. This study aimed to develop a rigorous mathematical method to analyse temporal variation and overcome these limitations. Methods. We evaluated hip fracture outcomes (time to surgery, length of stay, and mortality) from a total of 2777 patients between April 2011 and September 2016, before and after the introduction of a dedicated hip fracture unit (HFU). We developed a novel modelling method that fits progressively more complex linear sections to the time series using least squares regression. The method was used to model the periods before implementation, after implementation, and of the whole study period, comparing goodness of fit using \(F\)-tests. Results. The proposed method offered reliable descriptions of the temporal evolution of the time series and augmented conclusions that were reached by mere group comparisons. Reductions in time to surgery, length of stay, and mortality rates that group comparisons would have credited to the hip fracture unit appeared to be due to unrelated underlying trends. Conclusion. Temporal analysis using segmented linear regression models can reveal secular trends and is a valuable tool to evaluate interventions in retrospective studies.

MSC:

92C50 Medical applications (general)
62P10 Applications of statistics to biology and medical sciences; meta analysis

Software:

MedCalc; Matlab
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] AHRQ, National Healthcare Quality and Disparities Report and 5th Anniversary Update On the National Quality Strategy, 40 (2015), Rockville, MD, USA
[2] Fowkes, F. G. R., Medical audit cycle, Medical Education, 16, 4, 227-238 (1982) · doi:10.1111/j.1365-2923.1982.tb01254.x
[3] Portela, M. C.; Pronovost, P. J.; Woodcock, T.; Carter, P.; Dixon-Woods, M., How to study improvement interventions: a brief overview of possible study types: table 1, BMJ Quality and Safety, 24, 5, 325-336 (2015) · doi:10.1136/bmjqs-2014-003620
[4] Harris, A. D.; McGregor, J. C.; Perencevich, E. N., The use and interpretation of quasi-experimental studies in medical informatics, Journal of the American Medical Informatics Association, 13, 1, 16-23 (2006) · doi:10.1197/jamia.m1749
[5] Shadish, W. R.; Cook, T. D.; Campbell, D. T., Experimental and quasi-experimental for generalized designs causal inference, Handbook of Industrial and Organizational Psychology, 223, 623 (2002)
[6] Khan, N.; Abboudi, H.; Khan, M. S.; Dasgupta, P.; Ahmed, K., Measuring the surgical “learning curve”: methods, variables and competency, BJU International, 113, 3, 504-508 (2013) · doi:10.1111/bju.12197
[7] Aminikhanghahi, S.; Cook, D. J., A survey of methods for time series change point detection, Knowledge and Information Systems, 51, 2, 339-367 (2016) · doi:10.1007/s10115-016-0987-z
[8] 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, 77 (2014) · doi:10.1186/1748-5908-9-77
[9] Valsamis, E. M.; Golubic, R.; Glover, T. E.; Husband, H.; Hussain, A.; Jenabzadeh, A. R., Modeling learning in surgical practice, Journal of Surgical Education, 75, 1, 78-87 (2018) · doi:10.1016/j.jsurg.2017.06.015
[10] The Mathworks Inc, MATLAB-MathWorks, http://www.mathworks.com/products/matlab
[11] Lumley, T.; Diehr, P.; Emerson, S.; Chen, L., The importance of the normality assumption in large public health data sets, Annual Review of Public Health, 23, 1, 151-169 (2002) · doi:10.1146/annurev.publhealth.23.100901.140546
[12] Schoonjans, F.; Zalata, A.; Depuydt, C. E., MedCalc: a new computer program for medical statistics, Computer Methods and Programs in Biomedicine, 48, 3, 257-262 (1995) · doi:10.1016/0169-2607(95)01703-8
[13] 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
[14] Lomax, R. G.; Hahs-Vaughn, D. L., Statistical Concepts: A Second Course (2013)
[15] NHS Best Practice Tariff (BPT) for Fragility Hip Fracture Care User Guide, http://www.nhfd.co.uk/20/hipfractureR.nsf/0/9b0c5ea2e986ff56802577af0046b1df/\) FILE/Best_Practice_Tariff_User_Guide.pdf
[16] Lindisfarne, E.; Dawe, E.; Stott, P., Unipolar modular exeter hemiarthroplasty reduces length of stay and allows faster rehabilitation after hip fracture: a retrospective study of 117 patients, European Surgical Research, 50, 205-206 (2013)
[17] Lindisfarne, E. A. O.; Dawe, E. J. C.; Willis, C.; White, S.; Stott, P. M., Improving the clinical assessment of patients with fractured neck of femur: audit and loop closure of clerking practice after introduction of a clerking proforma, Injury Extra, 43, 10, 117 (2012) · doi:10.1016/j.injury.2012.07.333
[18] Fretheim, A.; Tomic, O., Statistical process control and interrupted time series: a golden opportunity for impact evaluation in quality improvement, BMJ Quality and Safety, 24, 12, 748-752 (2015) · doi:10.1136/bmjqs-2014-003756
[19] 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, 348-355 (2016) · doi:10.1093/ije/dyw098
[20] Weiss, D.; Dunn, S. I.; Sprague, A. E., Effect of a population-level performance dashboard intervention on maternal-newborn outcomes: an interrupted time series study, BMJ Quality and Safety, 27, 6, 425-436 (2017) · doi:10.1136/bmjqs-2017-007361
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.