Machine learning‐based prediction of heart failure readmission or death: implications of choosing the right model and the right metrics

Awan, Saqib Ejaz; Bennamoun, Mohammed; Sohel, Ferdous; Sanfilippo, Frank M; Dwivedi, Girish

doi:10.1002/ehf2.12419

Cited by 106 publications

(84 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The HF population in China differs from that in Western countries, including notably more stroke and a lower BMI, 1,9,22 making data derived from Western populations likely to be not applicable. In addition, previously published studies on HF readmission or death risk model have mainly depended on cardiac conditions, 5,6,23 whereas they have focused less on the impact of noncardiac factors such as stroke and anaemia, which were the major factors for all‐cause readmission or death in elderly patients with HF.…”

Section: Discussionmentioning

confidence: 99%

“…As many of readmissions and deaths are possibly predictable and preventable, 3,4 an easy‐to‐use and accurate model to predict the risk of all‐cause readmission or death has been noted 5–7 . However, it is suboptimal using a one‐size‐fits‐all approach to predict the risk of readmission or death for all patients with HF.…”

Section: Introductionmentioning

confidence: 99%

“…Although prior studies have suggested that patients are readmitted disproportionately early, no study has rigorously distinguished the weight of risk factors between the precise timing of 30 day and 1 year readmission or death. In addition, prior prediction models using complex methods were only modest discriminative ability 5,6,16 . Hence, these limitations emphasize the need for a user‐friendly model to accurately target elderly patients with multimorbidity.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A novel nomogram to predict all‐cause readmission or death risk in Chinese elderly patients with heart failure

Yang

Tao

et al. 2020

ESC Heart Failure

View full text Add to dashboard Cite

Aims Elderly patients with heart failure (HF) are associated with frequent all-cause readmission or death. The present study sought to develop an accurate and easy-to-use model to predict all-cause readmission or death risk in Chinese elderly patients with HF. Methods and resultsThis was a prospective cohort study in patients with HF aged 65 or older. Demographic, comorbidity, laboratory, and medication data were collected. A Cox regression model was used to identify factors for the prediction of readmission or death at 30 days and 1 year. A nomogram was developed with bootstrap validation. Of the included 854 patients, the cumulative all-cause readmission and mortality rates were 10.5% and 11.6% at 30 days and 34.9% and 19.7% at 1 year, respectively. The independent risk factors associated with both 30 day and 1 year readmission or death were older age, stroke, diastolic blood pressure < 60 mmHg, body mass index ≤ 18.5 kg/m 2 , lower estimated glomerular filtration rate, and BNP > 400 pg/mL (all P < 0.05). Anaemia, abnormal neutrophils, and admission without angiotensin-converting enzyme inhibitors/angiotensin receptor blockers were the specific independent risk factors of 30 day all-cause readmission or death (all P < 0.05), whereas serum sodium ≤ 140 mmol/L and admission without beta-blockers were the specific independent risk factors of 1 year all-cause readmission or death (all P < 0.05). The Cindex of the 30 day and 1 year diagnosis prediction model was 0.778 [95% confidence interval (CI) 0.693-0.862] and 0.738 (95% CI 0.640-0.836), respectively. Conclusions We developed accurate and easy-to-use nomograms to predict all-cause readmission or death in Chinese elderly patients with HF. The nomograms will assist in reducing the all-cause readmission and mortality rates.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel nomogram to predict all‐cause readmission or death risk in Chinese elderly patients with heart failure

Yang

Tao

et al. 2020

ESC Heart Failure

View full text Add to dashboard Cite

show abstract

“…17 An abundance of studies has described the application of AI-based techniques to predict hospital readmission. [18][19][20][21][22][23][24][25][26] Although many studies have concluded that AI-based models are superior to traditional models for risk stratification, other studies have observed otherwise. 14,[27][28][29][30][31][32][33][34][35][36][37][38][39] While clinical factors have primarily been used to predict readmission, there has also been interest in incorporating sociodemographic factors into models to more accurately account for patients' sociopersonal contexts, which are increasingly recognized to affect health-related outcomes.…”

Section: Predictive Analytics For Hospital Readmissionmentioning

confidence: 99%

Implementation of Artificial Intelligence-Based Clinical Decision Support to Reduce Hospital Readmissions at a Regional Hospital

et al. 2020

View full text Add to dashboard Cite

Background Hospital readmissions are a key quality metric, which has been tied to reimbursement. One strategy to reduce readmissions is to direct resources to patients at the highest risk of readmission. This strategy necessitates a robust predictive model coupled with effective, patient-centered interventions. Objective The aim of this study was to reduce unplanned hospital readmissions through the use of artificial intelligence-based clinical decision support. Methods A commercially vended artificial intelligence tool was implemented at a regional hospital in La Crosse, Wisconsin between November 2018 and April 2019. The tool assessed all patients admitted to general care units for risk of readmission and generated recommendations for interventions intended to decrease readmission risk. Similar hospitals were used as controls. Change in readmission rate was assessed by comparing the 6-month intervention period to the same months of the previous calendar year in exposure and control hospitals. Results Among 2,460 hospitalizations assessed using the tool, 611 were designated by the tool as high risk. Sensitivity and specificity for risk assignment were 65% and 89%, respectively. Over 6 months following implementation, readmission rates decreased from 11.4% during the comparison period to 8.1% (p < 0.001). After accounting for the 0.5% decrease in readmission rates (from 9.3 to 8.8%) at control hospitals, the relative reduction in readmission rate was 25% (p < 0.001). Among patients designated as high risk, the number needed to treat to avoid one readmission was 11. Conclusion We observed a decrease in hospital readmission after implementing artificial intelligence-based clinical decision support. Our experience suggests that use of artificial intelligence to identify patients at the highest risk for readmission can reduce quality gaps when coupled with patient-centered interventions.

show abstract

“…Previous studies have modeled risk of hospitalization, long-term survival rates, and mode of death prediction as a result of heart failure [ 16 - 18 ]. Models used features related to clinical status, therapy, and laboratory parameters including home-based physiological telemonitoring [ 19 ].…”

Section: Introductionmentioning

confidence: 99%

Decompensation in Critical Care: Early Prediction of Acute Heart Failure Onset

Essay¹,

Balkan²,

Subbian³

2020

JMIR Med Inform

View full text Add to dashboard Cite

Background Heart failure is a leading cause of mortality and morbidity worldwide. Acute heart failure, broadly defined as rapid onset of new or worsening signs and symptoms of heart failure, often requires hospitalization and admission to the intensive care unit (ICU). This acute condition is highly heterogeneous and less well-understood as compared to chronic heart failure. The ICU, through detailed and continuously monitored patient data, provides an opportunity to retrospectively analyze decompensation and heart failure to evaluate physiological states and patient outcomes. Objective The goal of this study is to examine the prevalence of cardiovascular risk factors among those admitted to ICUs and to evaluate combinations of clinical features that are predictive of decompensation events, such as the onset of acute heart failure, using machine learning techniques. To accomplish this objective, we leveraged tele-ICU data from over 200 hospitals across the United States. Methods We evaluated the feasibility of predicting decompensation soon after ICU admission for 26,534 patients admitted without a history of heart failure with specific heart failure risk factors (ie, coronary artery disease, hypertension, and myocardial infarction) and 96,350 patients admitted without risk factors using remotely monitored laboratory, vital signs, and discrete physiological measurements. Multivariate logistic regression and random forest models were applied to predict decompensation and highlight important features from combinations of model inputs from dissimilar data. Results The most prevalent risk factor in our data set was hypertension, although most patients diagnosed with heart failure were admitted to the ICU without a risk factor. The highest heart failure prediction accuracy was 0.951, and the highest area under the receiver operating characteristic curve was 0.9503 with random forest and combined vital signs, laboratory values, and discrete physiological measurements. Random forest feature importance also highlighted combinations of several discrete physiological features and laboratory measures as most indicative of decompensation. Timeline analysis of aggregate vital signs revealed a point of diminishing returns where additional vital signs data did not continue to improve results. Conclusions Heart failure risk factors are common in tele-ICU data, although most patients that are diagnosed with heart failure later in an ICU stay presented without risk factors making a prediction of decompensation critical. Decompensation was predicted with reasonable accuracy using tele-ICU data, and optimal data extraction for time series vital signs data was identified near a 200-minute window size. Overall, results suggest combinations of laboratory measurements and vital signs are viable for early and continuous prediction of patient decompensation.

show abstract

Machine learning‐based prediction of heart failure readmission or death: implications of choosing the right model and the right metrics

Cited by 106 publications

References 23 publications

A novel nomogram to predict all‐cause readmission or death risk in Chinese elderly patients with heart failure

A novel nomogram to predict all‐cause readmission or death risk in Chinese elderly patients with heart failure

Implementation of Artificial Intelligence-Based Clinical Decision Support to Reduce Hospital Readmissions at a Regional Hospital

Decompensation in Critical Care: Early Prediction of Acute Heart Failure Onset

Contact Info

Product

Resources

About