AI and Internet of Things for Chronic Obstructive Pulmonary Disease Remote Monitoring: Systematic Review of Exacerbation Prediction and Key Physiological Variables.

Models and Future Directions As discussed above, most studies rely on ML techniques that require substantial human effort for feature engineering and often fail to capture temporal patterns, which may be significant on their own. van der Heijden et al [ 31 ] showed that dynamic Bayesian networks, learned from small, sparse clinical time series using structural expectation-maximization and bootstrapping, can accurately predict COPD exacerbations and are suitable for use in chronic disease management tools.

also in 13,097 other papers