Related Experiment Videos
Patient-tailored prioritization for a pediatric care decision support system through machine learning
Jeffrey G Klann1, Vibha Anand, Stephen M Downs
1Laboratory of Computer Science, Massachusetts General Hospital, Boston, Massachusetts, USA.
Summary
We developed a new system using Bayesian networks to tailor pediatric preventive care recommendations. This approach prioritizes screenings and guidance based on individual patient needs, improving care delivery.
Area of Science:
- * Computational Health Informatics
- * Clinical Decision Support Systems
- * Bayesian Network Modeling
Background:
- * Developed an innovative computer decision support system over 8 years to enhance pediatric screening and care delivery.
- * System utilizes an electronic health record (EHR) and patient/caregiver input for guideline evaluation.
- * Static prioritization scheme previously used due to recommendations exceeding single visit scope.
Purpose of the Study:
- * To extend prior work by creating a patient-tailored prioritization method for clinical decision support.
- * To develop a dynamic approach for selecting guideline recommendations based on individual patient circumstances.
- * To improve the efficiency and appropriateness of pediatric preventive care.
Main Methods:
- * Employed Bayesian structure learning to construct association networks from historical decision support system data.
- * Utilized area under the receiver-operating characteristic curve (AUC) for discriminability analysis.
- * Analyzed 177 variables from 29,402 patients to identify predictive relationships.
Main Results:
- * Generated a network model encompassing 78 screening questions and anticipatory guidance (107 variables).
- * Achieved an average AUC of 0.65, deemed sufficient for prioritization contingent on population prevalence.
- * Structural analysis confirmed face-validity and uncovered non-intuitive associations among key variables.
Conclusions:
- * Demonstrated the capability of Bayesian structure learning for 'phenotyping' the pediatric primary care population.
- * The resulting network enables patient-tailored posterior probabilities for prioritizing care content.
- * Validated the feasibility of EHR-driven population phenotyping for personalized pediatric preventive care.
Related Concept Videos
01:15Impact of Pharmacokinetic–Pharmacodynamic Models: Regulatory Decisions
PK–PD modeling has significantly influenced FDA regulatory decisions, particularly drug approval, dosage optimization, and labeling. These models integrate pharmacokinetics (PK) and pharmacodynamics (PD) to predict drug behavior and effects, aiding in optimizing dosing regimens and enhancing the probability of clinical trial success.One notable example is Nesiritide (Natrecor®), a recombinant human brain natriuretic peptide for treating acute decompensated congestive heart failure (CHF).
01:13Patient-centered Care
Patient-centered care involves delivering care beyond inpatient hospitalization. Reflective practice can enhance a patient-centered approach. Reflective practice is a process of reasoning that considers all aspects of the present situation, including practicalities, learning from personal practice, and consideration of patient needs. Patients appreciate care decisions made while considering their input. Involving the patient in their care provides the patient with a sense of contribution rather...