JAMIA: Contextualizing, integrated data important for future CDS models
A software application integrated with an EHR might display data to physicians about ambient public health conditions and prompt appropriate management, treatment and reporting processes based on a calculation that considered patient factors in a specific epidemiologic situation could be important for future clinical decision support (CDS) systems, according to a study in the January edition of the Journal of the American Medical informatics Association.
Andrew M. Fine, MD, instructor of pediatrics at Harvard Medical School in Cambridge, Mass., and colleagues conducted a retrospective cohort analysis of 443 infants tested for pertussis from Jan. 1, 2003 to Dec. 31, 2007 to improve identification of pertussis cases by developing a decision model that incorporated recent, local and population-level disease incidence data.
Pertussis, commonly known as whooping cough, is caused by the bacterium Bordetella pertussis.
The study found that incorporating recent, local population-level disease incidence data improved the ability of a decision model to correctly identify infants with pertussis.
“Understanding the epidemiologic context a patient presents may provide critical information about the etiology of the patient’s problem,” wrote the authors, “but currently, this type of information is not formally processed, considered or utilized in clinical decision-making.”
The researchers constructed three decision models:
The contextualized model outperformed the clinical and local disease incidence models across all metrics, according to the authors. "In our analysis, epidemiologic context was stronger than all but one clinical predictor (cyanosis)."
“This study validates a scientific method for integrating incidence data into a clinical decision model and suggests that ‘epidemiologic context’ could be an important component of future CDS systems,” the study concluded.
“This important refinement of clinical decision-making requires communication between public health and clinical settings and programs to enable integration of public health data with clinical environments,” the authors concluded.
Andrew M. Fine, MD, instructor of pediatrics at Harvard Medical School in Cambridge, Mass., and colleagues conducted a retrospective cohort analysis of 443 infants tested for pertussis from Jan. 1, 2003 to Dec. 31, 2007 to improve identification of pertussis cases by developing a decision model that incorporated recent, local and population-level disease incidence data.
Pertussis, commonly known as whooping cough, is caused by the bacterium Bordetella pertussis.
The study found that incorporating recent, local population-level disease incidence data improved the ability of a decision model to correctly identify infants with pertussis.
“Understanding the epidemiologic context a patient presents may provide critical information about the etiology of the patient’s problem,” wrote the authors, “but currently, this type of information is not formally processed, considered or utilized in clinical decision-making.”
The researchers constructed three decision models:
- Clinical only: Candidate predictors included only clinical data based on demographics, history and physical exam;
- Local disease incidence: Candidates predictors included only public health incidence data; and
- Contextualized: All clinical and public health predictors were considered.
The contextualized model outperformed the clinical and local disease incidence models across all metrics, according to the authors. "In our analysis, epidemiologic context was stronger than all but one clinical predictor (cyanosis)."
“This study validates a scientific method for integrating incidence data into a clinical decision model and suggests that ‘epidemiologic context’ could be an important component of future CDS systems,” the study concluded.
“This important refinement of clinical decision-making requires communication between public health and clinical settings and programs to enable integration of public health data with clinical environments,” the authors concluded.