Hierarchical patient-centric caregiver network method for clinical outcomes study

Area of Science:

• Health Services Research
• Network Science
• Clinical Informatics

Background:

• Traditional clinical outcome studies primarily focus on patient-level factors.
• The influence of provider collaboration and care coordination on patient outcomes is often overlooked.
• Understanding the structure of healthcare provider networks is crucial for improving patient care.

Purpose of the Study:

• To model caregiver networks within a hospital setting.
• To investigate the predictive power of multilevel network features for patient outcomes.
• To assess the impact of provider-level network characteristics on length of hospital stay and in-hospital mortality.

Main Methods:

• Utilized data from intensive care unit patients at a tertiary care hospital.
• Modeled caregivers as patient-centric subnetworks within larger institutional caregiver networks.
• Generated patient-specific caregiver network features at multiple network levels.

Main Results:

• Multilevel network features were found to be significant predictors of patient outcomes.
• Both patient-level and provider-level network features contribute to predicting length of hospital stay.
• Network features also demonstrated predictive value for in-hospital mortality.

Conclusions:

• Provider network structure and collaboration are significant determinants of patient outcomes in intensive care settings.
• Integrating network analysis into clinical outcome studies offers a more comprehensive understanding of care.
• This approach can enhance the prediction of hospital length of stay and mortality by considering the collaborative landscape of care providers.