Development of a prediction model for infant hospitalisation and death using clinical features assessed by community health workers during routine postnatal home visits in Dhaka, Bangladesh - Takeaways - MDSpire

Development of a prediction model for infant hospitalisation and death using clinical features assessed by community health workers during routine postnatal home visits in Dhaka, Bangladesh

  • By

  • Alastair Fung

  • Marimuthu Sappani

  • Cole Heasley

  • Chun-Yuan Chen

  • Shaun K Morris

  • Peter J Gill

  • Diego G Bassani

  • Davidson H Hamer

  • Prakesh S Shah

  • S M Abdul Gaffar

  • Sultana Yeasmin

  • Shafiqul A Sarker

  • Shamima Sultana

  • Joseph Beyene

  • Daniel E Roth

  • June 25, 2026

  • 0 min

Share

  • 1

    A predictive model for infant hospitalization and mortality was developed using clinical indicators assessed by community health workers during home visits.

  • 2

    The study analyzed data from 1906 infants, with 9.2% experiencing hospitalization or death during the assessment period.

  • 3

    The best-performing Cox model included baseline covariates and visit-specific features, achieving a C-statistic of 0.71.

  • 4

    Random forest and aggregative predictors did not outperform the Cox model in predicting infant hospitalization and mortality.

  • 5

    Adding four visit-specific clinical features to WHO danger signs improved prediction accuracy for identifying infants needing referral.

Original Source(s)

Development of a prediction model for infant hospitalisation and death using clinical features assessed by community health workers during routine postnatal home visits in Dhaka, Bangladesh

  • by Alastair Fung, Marimuthu Sappani, Cole Heasley, Chun-Yuan Chen, Shaun K Morris, Peter J Gill, Diego G Bassani, Davidson H Hamer, Prakesh S Shah, S M Abdul Gaffar, Sultana Yeasmin, Shafiqul A Sarker, Shamima Sultana, Joseph Beyene, Daniel E Roth

  • June 25, 2026

Related Content

A Case Study of Severe Sepsis Due to Methicillin-Resistant Staphylococcus aureus (MRSA) with Pulmonary Abscesses and Humeral Osteomyelitis in a Previously Healthy Pediatric Patient

NPs Top US Jobs List Again

The nurse practitioner profession claims the No. 1 spot across three categories in the U.S. News & World Report 2026 Best Jobs rankings for the third consecutive year.

AI Scribes Lag Clinicians on Note Quality

A VHA study across 11 vendors finds AI-generated primary care notes score lower than clinician-written notes, with the largest deficits in thoroughness, organization, and usefulness