Browsing by Subject "risk prediction"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Open Access Derivation of a Risk Assessment Tool for Prediction of Long-Term Pain Intensity Reduction After Physical Therapy.(Journal of pain research, 2021-01) Horn, Maggie E; George, Steven Z; Li, Cai; Luo, Sheng; Lentz, Trevor ARationale
Risk assessment tools can improve clinical decision-making for individuals with musculoskeletal pain, but do not currently exist for predicting reduction of pain intensity as an outcome from physical therapy.Aims and objective
The objective of this study was to develop a tool that predicts failure to achieve a 50% pain intensity reduction by 1) determining the appropriate statistical model to inform the tool and 2) select the model that considers the tradeoff between clinical feasibility and statistical accuracy.Methods
This was a retrospective, secondary data analysis of the Optimal Screening for Prediction of Referral and Outcome (OSPRO) cohort. Two hundred and seventy-nine individuals seeking physical therapy for neck, shoulder, back, or knee pain who completed 12-month follow-up were included. Two modeling approaches were taken: a longitudinal model included demographics, presence of previous episodes of pain, and regions of pain in addition to baseline and change in OSPRO Yellow Flag scores to 12 months; two comparison models included the same predictors but assessed only baseline and early change (4 weeks) scores. The primary outcome was failure to achieve a 50% reduction in pain intensity score at 12 months. We compared the area under the curve (AUC) to assess the performance of each candidate model and to determine which to inform the Personalized Pain Prediction (P3) risk assessment tool.Results
The baseline only and early change models demonstrated lower accuracy (AUC=0.68 and 0.71, respectively) than the longitudinal model (0.79) but were within an acceptable predictive range. Therefore, both baseline and early change models were used to inform the P3 risk assessment tool.Conclusion
The P3 tool provides physical therapists with a data-driven approach to identify patients who may be at risk for not achieving improvements in pain intensity following physical therapy.Item Open Access Machine Learning and Precision Medicine in Emergency Medicine: The Basics.(Cureus, 2021-09) Lee, Sangil; Lam, Samuel H; Hernandes Rocha, Thiago Augusto; Fleischman, Ross J; Staton, Catherine A; Taylor, Richard; Limkakeng, Alexander TAs machine learning (ML) and precision medicine become more readily available and used in practice, emergency physicians must understand the potential advantages and limitations of the technology. This narrative review focuses on the key components of machine learning, artificial intelligence, and precision medicine in emergency medicine (EM). Based on the content expertise, we identified articles from EM literature. The authors provided a narrative summary of each piece of literature. Next, the authors provided an introduction of the concepts of ML, artificial intelligence as an extension of ML, and precision medicine. This was followed by concrete examples of their applications in practice and research. Subsequently, we shared our thoughts on how to consume the existing research in these subjects and conduct high-quality research for academic emergency medicine. We foresee that the EM community will continue to adapt machine learning, artificial intelligence, and precision medicine in research and practice. We described several key components using our expertise.Item Open Access Predicting the Risk of Huntington's Disease with Multiple Longitudinal Biomarkers.(Journal of Huntington's disease, 2019-06-22) Li, Fan; Li, Kan; Li, Cai; Luo, Sheng; PREDICT-HD and ENROLL-HD Investigators of the Huntington Study GroupBACKGROUND:Huntington's disease (HD) has gradually become a public health threat, and there is a growing interest in developing prognostic models to predict the time for HD diagnosis. OBJECTIVE:This study aims to develop a novel prognostic model that leverages multiple longitudinal biomarkers to inform the risk of HD. METHODS:The multivariate functional principal component analysis was used to summarize the essential information from multiple longitudinal markers and to obtain a set of prognostic scores. The prognostic scores were used as predictors in a Cox model to predict the right-censored time to diagnosis. We used cross-validation to determine the best model in PREDICT-HD (n = 1,039) and ENROLL-HD (n = 1,776); external validation was carried out in ENROLL-HD. RESULTS:We considered six commonly measured longitudinal biomarkers in PREDICT-HD and ENROLL-HD (Total Motor Score, Symbol Digit Modalities Test, Stroop Word Test, Stroop Color Test, Stroop Interference Test, and Total Functional Capacity). The prognostic model utilizing these longitudinal biomarkers significantly improved the predictive performance over the model with baseline biomarker information. A new prognostic index was computed using the proposed model, and can be dynamically updated over time as new biomarker measurements become available. CONCLUSION:Longitudinal measurements of commonly measured clinical biomarkers substantially improve the risk prediction of Huntington's disease diagnosis. Calculation of the prognostic index informs the patient's risk category and facilitates patient selection in future clinical trials.