Profiling Delirium Progression in Elderly Patients via Continuous-Time Markov Multi-State Transition Models

Abstract

Poor recognition of delirium among hospitalized elderlies is a typical challenge for health care professionals. Considering methodological insufficiency for assessing time-varying diseases, a continuous-time Markov multi-state transition model (CTMMTM) was used to investigate delirium evolution in elderly patients. This is a longitudinal observational study performed in September 2016 in an Italian hospital. Change of delirium states was modeled according to the 4AT score. A Cox model (CM) and a CTMMTM were used for identifying factors affecting delirium onset both with a two-state and three-state model. In this study, 78 patients were enrolled and evaluated for 5 days. Both the CM and the CTMMTM show that urine catheter (UC), aging, drugs, and invasive devices (ID) are risk factors for delirium onset. The CTMMTM model shows that transition from no-delirium/cognitive impairment to delirium was associated with aging (HR = 1.14; 95%CI, 1.05, 1.23) and neuroleptics (HR = 4.3; 1.57, 11.77), dopaminergic drugs (HR = 3.89; 1.2, 12.6), UC (HR = 2.92; 1.09, 7.79) and ID (HR = 1.67; 103, 2.71). These results are confirmed by the multivariable model. Aging, ID, antibiotics, drugs affecting the central nervous system, and absence of moving ability are identified as the significant predictors of delirium. Additionally, it seems that modeling with CTMMTM may show associations that are not directly detectable with the traditional CM.

A Machine Learning Approach for Investigating Delirium as a Multifactorial Syndrome

“…In our study, we have developed the RF algorithm accounting for all the patient’s records observed from the admission to the end of the study. In literature, age is one of the most predictive variables in delirium onset using MLT, regardless of the kind of algorithm [ 28 , 57 , 59 , 61 ] as also shown in our results.…”

“…The present results show that MLT can identify complex relationship among data, so in the future it would be interesting to use those techniques to define delirium risk factors instead of traditional approaches. Moreover, it would be important to consider delirium as a “dynamic” condition influenced by different factors that are working in different moments as also theorized by Fan et al [ 60 ] and applied in a recent work of our group [ 61 ].…”

Factores de riesgo para el desarrollo del delirio en pacientes en una unidad de cuidados intensivos

“…10 11 12 Dentro de estos factores se destaca la alteración cognitiva que es un fuerte factor de riesgo para la aparición de delirio (20%). 13 Factores demográficos: ser mayor de 65 años de edad y ser de género masculino. 14 El bajo nivel educativo también se asocia con el delirio, mientras que la educación superior es protectora.…”