Predicting Hospital Readmission among Patients with Sepsis using Clinical and Wearable Data - PubMed (original) (raw)

Predicting Hospital Readmission among Patients with Sepsis using Clinical and Wearable Data

Fatemeh Amrollahi et al. medRxiv. 2023.

Update in

• Predicting Hospital Readmission among Patients with Sepsis Using Clinical and Wearable Data.
  Amrollahi F, Shashikumar SP, Boussina A, Yhdego H, Nayebnazar A, Yung N, Wardi G, Nemati S. Amrollahi F, et al. Annu Int Conf IEEE Eng Med Biol Soc. 2023 Jul;2023:1-4. doi: 10.1109/EMBC40787.2023.10341165. Annu Int Conf IEEE Eng Med Biol Soc. 2023. PMID: 38083775 Free PMC article.

Abstract

Sepsis is a life-threatening condition that occurs due to a dysregulated host response to infection. Recent data demonstrate that patients with sepsis have a significantly higher readmission risk than other common conditions, such as heart failure, pneumonia and myocardial infarction and associated economic burden. Prior studies have demonstrated an association between a patient's physical activity levels and readmission risk. In this study, we show that distribution of activity level prior and post-discharge among patients with sepsis are predictive of unplanned rehospitalization in 90 days (P-value<1e-3). Our preliminary results indicate that integrating Fitbit data with clinical measurements may improve model performance on predicting 90 days readmission.

Keywords: Activity level; Clinical relevance Sepsis; Hospital readmission; Wearable data.

PubMed Disclaimer

Figures

Fig. 1.

An illustrative example of assessing feature distribution among patients with sepsis re-admitted vs non readmitted. Upper panels show the histogram of the sedentary hours of every day ,recorded every minute, for readmitted vs non readmitted patients with sepsis. The lower panel shows the CDF for both population cohorts and the kolmogorov–Smirnov test (KS test) reveals that the distribution of activity hours for re-admitted vs non readmitted patients are dissimilar.

Fig. 2.

Shapley values of the top 5 predictive features in readmission risk. (A): Post discharge day 1 (B): Post discharge day 10. CRP = C-reactive protein, Sedentary= Sedentary minutes per day (Activity level).

References

1. 1. Singer M. et al. , “The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3),” JAMA, vol. 315, no. 8, pp. 801–810, Feb. 2016, doi: 10.1001/jama.2016.0287. -DOI -PMC -PubMed
2. 1. Fleischmann-Struzek C. et al. , “Incidence and mortality of hospital- and ICU-treated sepsis: results from an updated and expanded systematic review and meta-analysis,” Intensive Care Med., vol. 46, no. 8, pp. 1552–1562, 2020, doi: 10.1007/s00134-020-06151-x. -DOI -PMC -PubMed
3. 1. Rhee C. et al. , “Incidence and Trends of Sepsis in US Hospitals Using Clinical vs Claims Data, 2009-2014,” JAMA, vol. 318, no. 13, pp. 1241–1249, Oct. 2017, doi: 10.1001/jama.2017.13836. -DOI -PMC -PubMed
4. 1. Prescott H. C. and Angus D. C., “Enhancing Recovery From Sepsis: A Review,” JAMA, vol. 319, no. 1, pp. 62–75, Jan. 2018, doi: 10.1001/jama.2017.17687. -DOI -PMC -PubMed
5. 1. Donnelly J. P., Hohmann S. F., and Wang H. E., “Unplanned Readmissions After Hospitalization for Severe Sepsis at Academic Medical Center-Affiliated Hospitals,” Crit. Care Med., vol. 43, no. 9, pp. 1916–1927, Sep. 2015, doi: 10.1097/CCM.0000000000001147. -DOI -PMC -PubMed

Publication types

Grants and funding

• K23 GM146092/GM/NIGMS NIH HHS/United States
• R01 HL157985/HL/NHLBI NIH HHS/United States
• R01 LM013998/LM/NLM NIH HHS/United States
• R35 GM143121/GM/NIGMS NIH HHS/United States

LinkOut - more resources

• Full Text Sources

  • Cold Spring Harbor Laboratory
  • Europe PMC
  • PubMed Central