A huge amount of medical information is available online and people refer to it before consulting a health professional. The information may not be reilable and can be cause of misinformation among patients. In order to address this problem a Natural Language Processing(NLP) model is presented which can evaluate quality of health information with help of DISCERN instrument developed by Oxford University. The scores from DISCERN were used as target variable for classifying the quality of information. The data related to Breast Cancer, Arthritis and Depression were mainly used for training the model. The model is based on hierarchical encoder attention-based neural network (HEA) which offers good model explainability.
Input variables : Textual data from web pages based on breast cancer, arthritis, and depression
Output Variables : Quality of Health Information
| Statistical | : | Somers D | Accuracy | Precision and Recall | Confusion Matrix | F1 Score | Roc and Auc | Prevalence | Detection Rate | Balanced Accuracy | Cohen's Kappa | Concordance | Gini Coefficent | KS Statistic | Youden's J Index |
| Infrastructure | : | Log Bytes | Logging/User/IAMPolicy | Logging/User/VPN | CPU Utilization | Memory Usage | Error Count | Prediction Count | Prediction Latencies | Private Endpoint Prediction Latencies | Private Endpoint Response Count |
Visit Model : arxiv.org
Additional links : arxiv.org
| Model Category | : | Public |
| Date Published | : | May, 2020 |
| Healthcare Domain | : | Provider |
| Code | : | github.com |
| Health Risk Management |
| Disease Detection |