Dharma is a novel, interpretable machine learning based clinical
decision support system, designed to address the diagnostic and
prognostic challenges of pediatric appendicitis by integrating
easily obtainable clinical, laboratory, and radiological data
into a unified, real-time predictive framework.
SHAP Explanations:
The model uses SHAP (SHapley Additive exPlanations) values to interpret predictions. Each SHAP value
quantifies the contribution of a specific input feature to the model’s output, relative to a base value.
The base value represents the model’s expected output,
and the sum of the SHAP values shows how much each feature pushes the prediction above or below this baseline.
Note: Input 0 if the value is not available or not applicable.
If appendix not visualized or USG unavailable:
AUC-ROC: 0.95 Threshold: 47% | High Likelihood
Specificity: 97% | PPV: 90% Threshold: 37% | Probable
Specificity: 92% | NPV: 93% Threshold: 30% | Possible
Sensitivity: 92% Less than 30%: Low Likelihood
NPV: 95% For Complications Prediction:
Sensitivity: 96% | NPV: 98%
Conceptualized, Designed, and Developed by: Dr. Anup Thapa, MBBS
Founder: DharmaAI
Sincere gratitude to the team of DharmaAI and my dear friends:
Er. Subash Pahari:
Web-app Development and Deployment
Thank you for introducing me to the wonders of coding and AI,
and for your invaluable mentorship and support.
You are not just a great friend, but also a guiding force in
this project.
