Integrating predictive modeling and causal inference for advancing medical science
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Artificial intelligence (AI) is revolutionizing healthcare by providing tools for disease prediction, diagnosis, and patient management. This review focuses on two key AI methodologies in healthcare: predictive modeling and causal inference. Predictive models excel in identifying patterns to forecast outcomes but are limited in explaining the underlying causes. In contrast, causal inference focuses on understanding cause-and-effect relationships, which makes effective medical interventions possible. Although randomized controlled trials (RCTs) are the gold standard for causal inference, they face limitations including cost and ethical concerns. As alternatives, emulated RCTs and advanced machine learning techniques have emerged for estimating causal effects, bridging the gap between prediction and causality. Additionally, Shapley values and Local Interpretable Model-Agnostic Explanations improve the interpretability of complex AI models, making them more actionable in clinical settings. Integrating prediction and causal inference holds great promise for advancing personalized medicine, enhancing patient outcomes, and optimizing healthcare delivery. However, careful application of AI tools is crucial to avoid misinterpretation and maximize their potential.
Abstract
Artificial intelligence (AI) is revolutionizing healthcare by providing tools for disease prediction, diagnosis, and patient management. This review focuses on two key AI methodologies in healthcare: predictive modeling and causal inference. Predictive models excel in identifying patterns to forecast outcomes but are limited in explaining the underlying causes. In contrast, causal inference focuses on understanding cause-and-effect relationships, which makes effective medical interventions possible. Although randomized controlled trials (RCTs) are the gold standard for causal inference, they face limitations including cost and ethical concerns. As alternatives, emulated RCTs and advanced machine learning techniques have emerged for estimating causal effects, bridging the gap between prediction and causality. Additionally, Shapley values and Local Interpretable Model-Agnostic Explanations improve the interpretability of complex AI models, making them more actionable in clinical settings. Integrating prediction and causal inference holds great promise for advancing personalized medicine, enhancing patient outcomes, and optimizing healthcare delivery. However, careful application of AI tools is crucial to avoid misinterpretation and maximize their potential.
참고문헌 (37)
- Alanazi R, "Identification and prediction of chronic diseases using machine learning approach", J Healthc Eng, 2022, pp.2826127~ (2022)
- Kumar A, "Smart healthcare : disease prediction using the cuckoo-enabled deep classifier in IoT framework", Sci Program, 2022, pp.2090681~ (2022)
- Talukdar J, "Early prediction of cardiovascular disease using artificial neural network", Paladyn J Behav Robot, 14, pp.20220107~ (2023)
- Tomasev N, "A clinically applicable approach to continuous prediction of future acute kidney injury", Nature, 572, pp.116~119 (2019)
- Kavitha C, "Early-stage Alzheimer’s disease prediction using machine learning models", Front Public Health, 10, pp.853294~ (2022)
- Basu S, "Detecting heterogeneous treatment effects to guide personalized blood pressure treatment : a modeling study of randomized clinical trials", Ann Intern Med, 166, pp.354~360 (2017)
- Govindaraj M, "Machine learning algorithms for disease prediction analysis", 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT), pp.879~888 (2023)
- Verma VK, "A machine learning-based predictive model for 30-day hospital readmission prediction for COPD patients", 2020IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp.994~999 (2020)
- Anurag, "Chronic kidney disease prediction using robust approach in machine learning", 2023 3rd International Conference on Innovative Sustainable Computational Technologies (CISCT), pp.1~5 (2023)
- Pearl J, "Causal inference in statistics : an overview", Stat Surv, 3, pp.96~146 (2009)
- Prosperi M, "Causal inference and counterfactual prediction in machine learning for actionable healthcare", Nat Mach Intell, 2, pp.369~375 (2020)
- Shen X, "A novel method for causal structure discovery from EHR data and its application to type-2 diabetes mellitus", Sci Rep, 11, pp.21025~ (2021)
- Sanchez P, "Causal machine learning for healthcare and precision medicine", R Soc Open Sci, 9, pp.220638~ (2022)
- Phillips DP, "The Hound of the Baskervilles effect : natural experiment on the influence of psychological stress on timing of death", BMJ, 323, pp.1443~1446 (2001)
- Arif S, "Predictive models aren’t for causal inference", Ecol Lett, 25, pp.1741~1745 (2022)
- Breiman L, "Random forests", Mach Learn, 45, pp.5~32 (2001)
- Freund Y, "A decision-theoretic generalization of online learning and an application to boosting", J Comput Syst Sci, 55, pp.119~139 (1997)
- Cortes C, "Support-vector networks", Mach Learn, 20, pp.273~297 (1995)
- LeCun Y, "Gradient-based learning applied to document recognition", Proc IEEE, 86, pp.2278~2324 (1998)
- Oh TR, "Predictive model for high coronary artery calcium score in young patients with non-dialysis chronic kidney disease", J Pers Med, 11, pp.1372~ (2021)
- Xu Y, "Deep learning predicts lung cancer treatment response from serial medical imaging", Clin Cancer Res, 25, pp.3266~3275 (2019)
- Linardatos P, "Explainable AI : a review of machine learning interpretability methods", Entropy(Basel), 23, pp.18~ (2020)
- Ichimura H, "Propensity-score matching with instrumental variables", Am Econ Rev, 91, pp.119~124 (2001)
- Heckman J, "Using matching, instrumental variables, and control functions to estimate economic choice models", Rev Econ Stat, 86, pp.30~57 (2004)
- Hariton E, "Randomised controlled trials : the gold standard for effectiveness research : Study design : randomised controlled trials", BJOG, 125, pp.1716~ (2018)
- Deaton A, "Understanding and misunderstanding randomized controlled trials", Soc Sci Med, 210, pp.2~21 (2018)
- Rekkas A, "Predictive approaches to heterogeneous treatment effects : a scoping review", BMC Med Res Methodol, 20, pp.264~ (2020)
- Messalas A, "Model-agnostic interpretability with Shapley values", 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), pp.1~7 (2019)
- Li X, "Machine learning algorithm to predict mortality in critically ill patients with sepsis-associated acute kidney injury", Sci Rep, 13, pp.5223~ (2023)
- Raghavan S, "Generalizability of heterogeneous treatment effects based on causal forests applied to two randomized clinical trials of intensive glycemic control", Ann Epidemiol, 65, pp.101~108 (2022)
- Kutcher SA, "Emulating a randomised controlled trial with observational data : an introduction to the target trial framework", Can J Cardiol, 37, pp.1365~1377 (2021)
- Gianicolo EA, "Methods for evaluating causality in observational studies", Dtsch Arztebl Int, 116, pp.101~107 (2020)
- Rasouli B, "Combining high quality data with rigorous methods : emulation of a target trial using electronic health records and a nested case-control design", BMJ, 383, pp.e072346~ (2023)
- Sengupta S, "Emulating randomized controlled trials with hybrid control arms in oncology : a case study", Clin Pharmacol Ther, 113, pp.867~877 (2023)