Risk prediction of clinical adverse outcomes with machine learning in a cohort of critically ill patients with atrial fibrillation

Abstract

Critically ill patients affected by atrial fibrillation are at high risk of adverse events: however, the actual risk stratification models for haemorrhagic and thrombotic events are not validated in a critical care setting. With this paper we aimed to identify, adopting topological data analysis, the risk factors for therapeutic failure (in-hospital death or intensive care unit transfer), the in-hospital occurrence of stroke/TIA and major bleeding in a cohort of critically ill patients with pre-existing atrial fibrillation admitted to a stepdown unit; to engineer newer prediction models based on machine learning in the same cohort. We selected all medical patients admitted for critical illness and a history of pre-existing atrial fibrillation in the timeframe 01/01/2002–03/08/2007. All data regarding patients’ medical history, comorbidities, drugs adopted, vital parameters and outcomes (therapeutic failure, stroke/TIA and major bleeding) were acquired from electronic medical records. Risk factors for each outcome were analyzed adopting topological data analysis. Machine learning was used to generate three different predictive models. We were able to identify specific risk factors and to engineer dedicated clinical prediction models for therapeutic failure (AUC: 0.974, 95%CI: 0.934–0.975), stroke/TIA (AUC: 0.931, 95%CI: 0.896–0.940; Brier score: 0.13) and major bleeding (AUC: 0.930:0.911–0.939; Brier score: 0.09) in critically-ill patients, which were able to predict accurately their respective clinical outcomes. Topological data analysis and machine learning techniques represent a concrete viewpoint for the physician to predict the risk at the patients’ level, aiding the selection of the best therapeutic strategy in critically ill patients affected by pre-existing atrial fibrillation.

Clusters of Comorbidities in the Short-Term Prognosis of Acute Heart Failure among Elderly Patients: A Retrospective Cohort Study

“…Two of the phenotypes identified with our methods were characterized by metabolic (phenotype 6), vascular (phenotype 10), and metabolic–vascular (phenotype 12) diseases, while the other remaining clusters were depicted by the association of NVAF and dementia in connection with metabolic (phenotype 4), ischemic (phenotype 9), and neoplastic (phenotype 14) diseases. Of note, NVAF is highly prevalent and correlated to a worse prognosis in several phenotypes of this critical illness, as already observed in other studies [ 35 ]. The association of this arrhythmia with dementia, particularly vascular dementia, or Alzheimer’s disease, is well known [ 36 ].…”

Improving the EHMRG Prognostic Evaluation of Acute Heart Failure with TAPSE/PASp: A Sequential Approach

“…Moreover, while cardiologists have already optimized and validated for their environment several prognostic scales for AHF, as ADHERE and OPTIMIZE-HF [ 40 , 41 ], internal medicine specialists lack of scores specifically validated for their populations that are often older and burdened by several comorbidities, and differ substantially from cardiology inpatients [ 42 ]. This issue has already been observed in other pathologies, as for example in subjects with sepsis [ 43 ], as well as subjects with pre-existing atrial fibrillation [ 44 , 45 ] admitted to Internal Medicine departments. EHMRG contains several items that are currently adopted in the prognostication of AHF and other critical illnesses in internal medicine, such as age, systolic blood pressure, creatinine, electrolyte imbalances, and troponin increase.…”

Risk prediction score for clinical outcome in atrial fibrillation and stable coronary artery disease

“…Machine learning has advantages in prediction model development compared with traditional statistical methods that focus on inference and do not require a prior assumption of causality in variable selection and modelling. Many machine-learning-based risk prediction models have been reported for the diagnosis and prognosis of patients with CAD22–25 or AF,26–28 whereas there has only been one previous report of a machine learning-based prediction model for CAD patients complicated with AF 29. However, only one report showed a machine-learning prediction model for all-cause death among these patients.…”