Hierarchical patient-centric caregiver network method for clinical outcomes study

Abstract

In clinical outcome studies, analysis has traditionally been performed using patient-level factors, with minor attention given to provider-level features. However, the nature of care coordination and collaboration between caregivers (providers) may also be important in determining patient outcomes. Using data from patients admitted to intensive care units at a large tertiary care hospital, we modeled the caregivers that provided medical service to a specific patient as patient-centric subnetwork embedded within larger caregiver networks of the institute. The caregiver networks were composed of caregivers who treated either a cohort of patients with particular disease or any patient regardless of disease. Our model can generate patient-specific caregiver network features at multiple levels, and we demonstrate that these multilevel network features, in addition to patient-level features, are significant predictors of length of hospital stay and in-hospital mortality.

Data Science Methods for Nursing-Relevant Patient Outcomes and Clinical Processes

“…Ten papers noted the use of more contemporary methods for prediction: random forests, 12,24,78,81,82,87 gradient boosting, 12,24,77,81,82,86 naïve Bayes, 82 SVMs, 12,87 and neural networks 24,73,78,87 . Interestingly, one paper conducted a network analysis of healthcare providers and used the network characteristics to serve as predictors 84 . Another paper used regular expressions to extract features for a prediction model 78 …”

“…Variables serving as predictors primarily comprised demographic information, vital signs, laboratory values, and diagnoses/comorbidities/procedures. Less commonly included but notable predictor variables comprised physical assessments, 72 physiological status scores, 68,74,77,81,84 and medication exposures. 77,82,84 One study included a nutrition score, 74 one study included census-tract-level socioeconomic status, 83 and one study included nursing diagnoses.…”

“…Study populations included hospitalized adults from the following countries: Australia, 72 Brazil, 74 China, 71,75,76 Israel, 77 Ireland, 72 Italy, 70 Korea, 78,79 Singapore, 12 Spain, 68 Switzerland, 69 and the United States. 24,[80][81][82][83][84][85] Several studies focused on specific admission diagnoses or surgical procedures, which resulted in a trend toward better model performance compared to models including all-cause hospitalizations. Variables serving as predictors primarily comprised demographic information, vital signs, laboratory values, and diagnoses/comorbidities/procedures.…”

“…Less commonly included but notable predictor variables comprised physical assessments, 72 physiological status scores, 68,74,77,81,84 and medication exposures. 77,82,84 One study included a nutrition score, 74 one study included census-tract-level socioeconomic status, 83 and one study included nursing diagnoses. 70 The majority of the works used regression (with or without additional methods) for making predictions.…”

“…70 The majority of the works used regression (with or without additional methods) for making predictions. 24,[68][69][70][71][72][73][74][75][76][78][79][80][81][82][83][84][85][86] The regression models primarily leveraged logistic regression; however, two papers applied Cox proportional hazards regression. 76,86 Ten papers noted the use of more contemporary methods for prediction: random forests, 12,24,78,81,82,87 gradient boosting, 12,24,77,81,82,86 naïve Bayes, 82 SVMs, 12,87 and neural networks.…”