Developing a Parsimonious Frailty Index for Older, Multimorbid Adults With Heart Failure Using Machine Learning

https://doi.org/10.1016/j.amjcard.2022.11.044Get rights and content

Frailty is associated with adverse outcomes in heart failure (HF). A parsimonious frailty index (FI) that predicts outcomes of older, multimorbid patients with HF could be a useful resource for clinicians. A retrospective study of veterans hospitalized from October 2015 to October 2018 with HF, aged ≥50 years, and discharged home developed a 10-item parsimonious FI using machine learning from diagnostic codes, laboratory results, vital signs, and ejection fraction (EF) from outpatient encounters. An unsupervised clustering technique identified 5 FI strata: severely frail, moderately frail, mildly frail, prefrail, and robust. We report hazard ratios (HRs) of mortality, adjusting for age, gender, race, and EF and odds ratios (ORs) for 30-day and 1-year emergency department visits and all-cause hospitalizations after discharge. We identified 37,431 veterans (age, 73 ± 10 years; co-morbidity index, 5 ± 3; 43.5% with EF ≤40%). All frailty groups had a higher mortality than the robust group: severely frail (HR 2.63, 95% confidence interval [CI] 2.42 to 2.86), moderately frail (HR 2.04, 95% CI 1.87 to 2.22), mildly frail (HR 1.60, 95% CI 1.47 to 1.74), and prefrail (HR 1.18, 95% CI: 1.07 to 1.29). The associations between frailty and mortality remained unchanged in the stratified analysis by age or EF. The combined (severely, moderately, and mildly) frail group had higher odds of 30-day emergency visits (OR 1.62, 95% CI 1.43 to 1.83), all-cause readmission (OR, 1.75, 95% CI 1.52 to 2.02), 1-year emergency visits (OR 1.70, 95% CI 1.53 to 1.89), rehospitalization (OR 2.18, 95% CI 1.97 to 2.41) than the robust group. In conclusion, a 10-item FI is associated with postdischarge outcomes among patients discharged home after a hospitalization for HF. A parsimonious FI may aid clinical prediction at the point of care.

Section snippets

Methods

The design was a retrospective cohort study of veterans using VHA to assemble the cohort and extract variables. The Supplementary Methods provides further details on the design, methods, and analysis.

The cohort included all patients admitted to any VHA medical center with a principal diagnosis of HF from October 2015 to October 2018. The International Classification of Diseases (ICD) 10th Revision hospital discharge codes were used to identify patients with a principal diagnosis of HF (I09.9,

Results

Our development cohort included 37,431 participants (Supplementary Figure 1). The average age of the participants was 73.4 ± 10.3 years, most were men (98%), and 26,046 were White (69.6%). About 47.6% of population were obese with BMIs >30 and 43.5% had EF ≤40% (Table 1). The mortality rate during the follow-up interval was 63.1% (n = 23,614), with an average time to death of 3.0 ± 2.1 (median 2.6, interquartile range 0.9 to 5.5) years after discharge.

We started with 76 variables (laboratory

Discussion

The present study provides evidence for the predictive validity of a novel pFI for older patients admitted to the hospital with HF. Notably, the pFI is exclusively developed for patients with HF. The pFI is robust because it uses a national sample that integrates baseline outpatient data from the previous 12 months, follows patients after hospitalization for multiple years, and it uses an innovative cascade of machine learning techniques. The pFI only requires 10 variables and can thus improve

Conclusions

A pFI with 10 variables has a similar predictive validity as the VA-FI. The pFI is thus a feasible and practical tool that can be incorporated into routine practice and provides clinically useful insights that are distinct from existing mortality prediction models,38 especially for older adults with multiple co-morbidities. The pFI index applied at the point of care could guide clinical decisions regarding care transitions, urgency of interventions to reduce readmissions, and appropriateness of

Competency in medical knowledge

We propose a pFI with 10 specific deficits derived from full breadth of electronic medical records from outpatient settings using machine learning algorithm. The pFI has better predictive validity than previous approaches, independent of age and EF in predicting mortality and healthcare utilization after hospital discharge for congestive HF.

Translational Outlook

The pFI is a practical clinical decision support tool for day-to-day inpatient use.

Disclosures

The study is funded partially by the Center for Innovations in Quality, Effectiveness and Safety (VA HSRD CIN 13-413), Michael E. DeBakey VA Medical Center, Houston, Texas, USA and CSP 2010A. Dr. Razjouyan is supported by NIH-NHLBI award 1K25HL152006-01. Dr. Horstman is supported by VA HSR&D CDA-2 award IK2-HX003163. Dr. Orkaby is supported by VA CSR&D CDA-2 award IK2-CX001800. Dr. Virani is supported by research grants from The Department of Veterans Affairs Health Services Research and

Acknowledgment

The authors are grateful to the VA Informatics and Computing Infrastructure.

References (38)

  • GE Caughey et al.

    Co-morbidity and potential treatment conflicts in elderly heart failure patients: a retrospective, cross-sectional study of administrative claims data

    Drugs Aging

    (2011)
  • I Uchmanowicz et al.

    Coexisting frailty with heart failure

    Front Physiol

    (2019)
  • M Singh et al.

    Importance of frailty in patients with cardiovascular disease

    Eur Heart J

    (2014)
  • P Bosco-Lévy et al.

    Diagnostic accuracy of the International Classification of Diseases, Tenth Revision, codes of heart failure in an administrative database

    Pharmacoepidemiol Drug Saf

    (2019)
  • AR Orkaby et al.

    The burden of frailty among U.S. Veterans and its association with mortality, 2002–2012

    J Gerontol A Biol Sci Med Sci

    (2019)
  • JH Garvin et al.

    Automated extraction of ejection fraction for quality measurement using regular expressions in Unstructured Information Management Architecture (UIMA) for heart failure

    J Am Med Inform Assoc

    (2012)
  • VIReC Factbook Corporate Data Warehouse (CDW) Patient 2.0 Domain

    (2016)
  • VIReC. Calculating a Comorbidity Index for Risk Adjustment Using VA or Medicare Data. Available at:...
  • J Razjouyan et al.

    Smoking Status and Factors associated with COVID-19 In-hospital Mortality among US Veterans

    Nicotine Tob Res

    (2022)
  • Cited by (1)

    The analysis was partly supported by the use of facilities and resources at the Center for Innovations in Quality, Effectiveness and Safety, CIN 13-413, Michael E. DeBakey VA Medical Center, Houston, Texas and a National Institutes of Health, National Heart, Lung, and Blood Institute, Bethesda, Maryland, K25 funding, number 1K25HL152006-01, to Dr. Razjouyan.

    View full text