TY - JOUR
T1 - Machine learning provides evidence that stroke risk is not linear
T2 - The non-linear Framingham stroke risk score
AU - Orfanoudaki, Agni
AU - Chesley, Emma
AU - Cadisch, Christian
AU - Stein, Barry
AU - Nouh, Amre
AU - Alberts, Mark J.
AU - Bertsimas, Dimitris
N1 - Funding Information:
Study was funded by a grant to the Massachusetts Institute of Technology from Hartford HealthCare. The resources partially covered the research stipends of the students who were engaged in the study. There was no additional external funding received for this study.
Publisher Copyright:
© 2020 Orfanoudaki et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
PY - 2020/5
Y1 - 2020/5
N2 - Current stroke risk assessment tools presume the impact of risk factors is linear and cumulative. However, both novel risk factors and their interplay influencing stroke incidence are difficult to reveal using traditional additive models. The goal of this study was to improve upon the established Revised Framingham Stroke Risk Score and design an interactive Non-Linear Stroke Risk Score. Leveraging machine learning algorithms, our work aimed at increasing the accuracy of event prediction and uncovering new relationships in an interpretable fashion. A two-phase approach was used to create our stroke risk prediction score. First, clinical examinations of the Framingham offspring cohort were utilized as the training dataset for the predictive model. Optimal Classification Trees were used to develop a tree-based model to predict 10-year risk of stroke. Unlike classical methods, this algorithm adaptively changes the splits on the independent variables, introducing non-linear interactions among them. Second, the model was validated with a multi-ethnicity cohort from the Boston Medical Center. Our stroke risk score suggests a key dichotomy between patients with history of cardiovascular disease and the rest of the population. While it agrees with known findings, it also identified 23 unique stroke risk profiles and highlighted new non-linear relationships; such as the role of T-wave abnormality on electrocardiography and hematocrit levels in a patient’s risk profile. Our results suggested that the non-linear approach significantly improves upon the baseline in the c-statistic (training 87.43% (CI 0.85–0.90) vs. 73.74% (CI 0.70–0.76); validation 75.29% (CI 0.74–0.76) vs 65.93% (CI 0.64–0.67), even in multi-ethnicity populations. The clinical implications of the new risk score include prioritization of risk factor modification and personalized care at the patient level with improved targeting of interventions for stroke prevention.
AB - Current stroke risk assessment tools presume the impact of risk factors is linear and cumulative. However, both novel risk factors and their interplay influencing stroke incidence are difficult to reveal using traditional additive models. The goal of this study was to improve upon the established Revised Framingham Stroke Risk Score and design an interactive Non-Linear Stroke Risk Score. Leveraging machine learning algorithms, our work aimed at increasing the accuracy of event prediction and uncovering new relationships in an interpretable fashion. A two-phase approach was used to create our stroke risk prediction score. First, clinical examinations of the Framingham offspring cohort were utilized as the training dataset for the predictive model. Optimal Classification Trees were used to develop a tree-based model to predict 10-year risk of stroke. Unlike classical methods, this algorithm adaptively changes the splits on the independent variables, introducing non-linear interactions among them. Second, the model was validated with a multi-ethnicity cohort from the Boston Medical Center. Our stroke risk score suggests a key dichotomy between patients with history of cardiovascular disease and the rest of the population. While it agrees with known findings, it also identified 23 unique stroke risk profiles and highlighted new non-linear relationships; such as the role of T-wave abnormality on electrocardiography and hematocrit levels in a patient’s risk profile. Our results suggested that the non-linear approach significantly improves upon the baseline in the c-statistic (training 87.43% (CI 0.85–0.90) vs. 73.74% (CI 0.70–0.76); validation 75.29% (CI 0.74–0.76) vs 65.93% (CI 0.64–0.67), even in multi-ethnicity populations. The clinical implications of the new risk score include prioritization of risk factor modification and personalized care at the patient level with improved targeting of interventions for stroke prevention.
UR - http://www.scopus.com/inward/record.url?scp=85085155938&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085155938&partnerID=8YFLogxK
U2 - 10.1371/journal.pone.0232414
DO - 10.1371/journal.pone.0232414
M3 - Article
C2 - 32437368
AN - SCOPUS:85085155938
SN - 1932-6203
VL - 15
JO - PloS one
JF - PloS one
IS - 5
M1 - e0232414
ER -