Individual illness dynamics: An analysis of children with sepsis admitted to the pediatric intensive care unit

Abstract

Illness dynamics and patterns of recovery may be essential features in understanding the critical illness course. We propose a method to characterize individual illness dynamics in patients who experienced sepsis in the pediatric intensive care unit. We defined illness states based on illness severity scores generated from a multi-variable prediction model. For each patient, we calculated transition probabilities to characterize movement among illness states. We calculated the Shannon entropy of the transition probabilities. Using the entropy parameter, we determined phenotypes of illness dynamics based on hierarchical clustering. We also examined the association between individual entropy scores and a composite variable of negative outcomes. Entropy-based clustering identified four illness dynamic phenotypes in a cohort of 164 intensive care unit admissions where at least one sepsis event occurred. Compared to the low-risk phenotype, the high-risk phenotype was defined by the highest entropy values and had the most ill patients as defined by a composite variable of negative outcomes. Entropy was significantly associated with the negative outcome composite variable in a regression analysis. Information-theoretical approaches to characterize illness trajectories offer a novel way of assessing the complexity of a course of illness. Characterizing illness dynamics with entropy offers additional information in conjunction with static assessments of illness severity. Additional attention is needed to test and incorporate novel measures representing the dynamics of illness.

Prospective validation of clinical deterioration predictive models prior to intensive care unit transfer among patients admitted to acute care cardiology wards

“…The rise in risk score by duration, representing a cumulative impact to the severity of illness, therefore offers a novel approach to predictive analytics monitoring in real-world use. This points to the need for additional study focusing on person-centered modeling approaches that rely on the change from a patient's own baseline risk (Keim-Malpass et al 2020, Kausch et al 2022, Keim-Malpass andKausch 2023) We conclude that signatures of cardiorespiratory and cardiovascular illness are present in the continuous cardiorespiratory monitoring, vital signs, and laboratory data in patients hospitalized in an acute care cardiology ward. These statistical predictive models, developed five years previously, had good predictive performance despite the passage of time and the impact of the COVID-19 pandemic.…”

“…The rise in risk score by duration, representing a cumulative impact to the severity of illness, therefore offers a novel approach to predictive analytics monitoring in real-world use. This points to the need for additional study focusing on person-centered modeling approaches that rely on the change from a patient’s own baseline risk (Keim-Malpass et al 2020, Kausch et al 2022, Keim-Malpass and Kausch 2023)…”

Explainable Artificial Intelligence for Prediction of Complete Surgical Cytoreduction in Advanced-Stage Epithelial Ovarian Cancer

“…They did not appear neither significant nor of relative importance when building the AI model. Temporal recovery-related features may be more insightful than those derived from measures of disease severity at a single point in time [48]. Another limitation is the lack of prospective quality-of-life data.…”

A National Leadership Incubator to Promote Equity in Diagnostic Excellence

“…6 Another scholar showcased how pragmatic implementation of real-time pediatric intensive care unit data monitoring and predictive analytics can identify early patient deterioration. 7 Finally, given the emerging role of data science in health care, one of the scholar's projects centered on developing a competency-based medical curriculum focused on using machine learning models to inform diagnostic decision-making. 8…”

“…One scholar applied network-based machine learning methods to discern common patterns of diagnostic delay and drove the discovery of underrecognized disease subtypes, thus improving early diagnosis . Another scholar showcased how pragmatic implementation of real-time pediatric intensive care unit data monitoring and predictive analytics can identify early patient deterioration . Finally, given the emerging role of data science in health care, one of the scholar’s projects centered on developing a competency-based medical curriculum focused on using machine learning models to inform diagnostic decision-making …”