Identifying causal mechanisms in health care interventions using classification tree analysis

A Scoping Review on the Use of Machine Learning in Return-to-Work Studies: Strengths and Weaknesses

PURPOSE

Decisions to increase work participation must be informed and timely to improve return to work (RTW). The implementation of research into clinical practice relies on sophisticated yet practical approaches such as machine learning (ML). The objective of this study is to explore the evidence of machine learning in vocational rehabilitation and discuss the strengths and areas for improvement in the field.

METHODS

We used the PRISMA guidelines and the Arksey and O'Malley framework. We searched Ovid Medline, CINAHL, and PsycINFO; with hand-searching and use of the Web of Science for the final articles. We included studies that are peer-reviewed, published within the last 10 years to consider contemporary material, implemented a form of "machine learning" or "learning health system", undertaken in a vocational rehabilitation setting, and has employment as a specific outcome.

RESULTS

12 studies were analyzed. The most commonly studied population was musculoskeletal injuries or health conditions. Most of the studies came from Europe and most were retrospective studies. The interventions were not always reported or specified. ML was used to identify different work-related variables that were predictive of return to work. However, ML approaches were varied and no standard or predominant ML approach was evident.

CONCLUSIONS

ML offers a potentially beneficial approach to identifying predictors of RTW. While ML uses a complex calculation and estimation, ML complements other elements of evidence-based practice such as the clinician's expertise, the worker's preference and values, and contextual factors around RTW in an efficient and timely manner.

Mobility Analysis of AmpuTees (MAAT 4): classification tree analysis for probability of lower limb prosthesis user functional potential

Purpose: To develop a predictive model to inform the probability of lower limb prosthesis users' functional potential for ambulation.Materials and Methods: A retrospective analysis of a database of outcomes for 2770 lower limb prosthesis users was used to inform a classification and regression tree analysis. Gender, age, height, weight, body mass index adjusted for amputation, amputation level, cause of amputation, comorbid health status and functional mobility score [Prosthetic Limb Users Survey of Mobility (PLUS-M™)] were entered as potential predictive variables. Patient K-Level was used to assign dependent variable status as unlimited community ambulator (i.e., K3 or K4) or limited community/household ambulator (i.e., K1 or K2). The classification tree was initially trained from 20% of the sample and subsequently tested with the remaining sample.Results: A classification tree was successfully developed, able to accurately classify 87.4% of individuals within the model's training group (standard error 1.4%), and 81.6% within the model's testing group (standard error 0.82%). Age, PLUS-M™ T-score, cause of amputation and body weight were retained within the tree logic.Conclusions: The resultant classification tree has the ability to provide members of the clinical care team with predictive probabilities of a patient's functional potential to help assist care decisions.Implications for RehabilitationClassification and regression tree analysis is a simple analytical tool that can be used to provide simple predictive models for patients with a lower limb prosthesis.The resultant classification tree had an 81.6% (standard error 0.82%) accuracy predicting functional potential as an unlimited community ambulator (i.e., K3 or K4) or limited community/ household ambulator (i.e., K1 or K2) in an unknown group of 2770 lower limb prosthesis users.The resultant classification tree can assist with the rehabilitation team's care planning providing probabilities of functional potential for the lower limb prosthesis user.

Estimating causal effects for survival (time-to-event) outcomes by combining classification tree analysis and propensity score weighting

RATIONALE, AIMS AND OBJECTIVES

A common approach to assessing treatment effects in nonrandomized studies with time-to-event outcomes is to estimate propensity scores and compute weights using logistic regression, test for covariate balance, and then estimate treatment effects using Cox regression. A machine-learning alternative-classification tree analysis (CTA)-used to generate propensity scores and to estimate treatment effects in time-to-event data may identify complex relationships between covariates not found using conventional regression-based approaches.

METHOD

Using empirical data, we identify all statistically valid CTA propensity score models and then use them to compute strata-specific, observation-level propensity score weights that are subsequently applied in outcomes analyses. We compare findings obtained using this framework to the conventional method, by evaluating covariate balance and treatment effect estimates obtained using Cox regression and a weighted CTA outcomes model.

RESULTS

All models had some imbalanced covariates. Nevertheless, treatment effect estimates were generally consistent across all weighted models.

CONCLUSIONS

In the study sample, given that all approaches elicited similar results, using CTA increased confidence that bias could not be reduced any further. Because the CTA algorithm identifies all statistically valid propensity score models for a sample, it is most likely to identify a correctly specified propensity score model-and therefore should be used either to confirm results using traditional methods, or to reveal biases that may be missed by traditional methods. Moreover, given that the true treatment effect is never known in observational data, CTA should be considered for estimating outcomes because no statistical assumptions are required.