Kidney Week

Abstract: TH-PO017

Development of Artificial Intelligence for Clinical Decision Support to Optimizes Erythropoietin-Stimulating Agents in Patients with CKD

Session Information

• Augmented Intelligence for Prediction and Image Analysis
  October 24, 2024 | Location: Exhibit Hall, Convention Center
  Abstract Time: 10:00 AM - 12:00 PM

Category: Augmented Intelligence, Digital Health, and Data Science

• 300 Augmented Intelligence, Digital Health, and Data Science

Authors

• Kurathong, Sathit, Faculty of Medicine Vajira Hospital, Bangkok, Thailand

Sathit Kurathong, MD

• Buranasaksathien, Pattanan, Faculty of Medicine Vajira Hospital, Bangkok, Thailand

Pattanan Buranasaksathien, MD

• Pongsitisak, Wanjak, Faculty of Medicine Vajira Hospital, Bangkok, Thailand

Wanjak Pongsitisak, MD

• Trakarnvanich, Thananda, Faculty of Medicine Vajira Hospital, Bangkok, Thailand

Thananda Trakarnvanich, MD

• Ngamvichchukorn, Tanun, Faculty of Medicine Vajira Hospital, Bangkok, Thailand

Tanun Ngamvichchukorn, MD

• Jaturapisanukul, Solos, Faculty of Medicine Vajira Hospital, Bangkok, Thailand

Solos Jaturapisanukul, MD

• Laungchuaychok, Punnawit, Faculty of Medicine Vajira Hospital, Bangkok, Thailand

Punnawit Laungchuaychok, MD

• Suphatheerawatr, Nitcha, Faculty of Medicine Vajira Hospital, Bangkok, Thailand

Nitcha Suphatheerawatr, MD

• Limbutara, Kavee, Faculty of Medicine Vajira Hospital, Bangkok, Thailand

Kavee Limbutara, MD

• Teerawongsakul, Padoemwut, Faculty of Medicine Vajira Hospital, Bangkok, Thailand

Padoemwut Teerawongsakul, MD, MSc

Group or Team Name

• Vajira Big Data and Machine Learning for Applied in Healthcare Research Group.

Background

The application of AI in predicting Hb levels and determining appropriate ESA doses for managing anemia of CKD is a promising development. Previous studies using AI for anemia of CKD treatment have demonstrated positive outcomes, such as increased percentages of patients achieving target Hb levels and reduced ESA dosages. The replication of these findings in the Thai population could have significant implications for managing anemia of CKD in Thailand.

Methods

The development of the AI model included 4 steps: data collection, feature selection, data preparation, and model selection. CKD patients with eGFR <45 ml/min/1.73m² who used ESA were included. The data was cleaned and prepared by removing outlier data and correcting missing values. Variables were used to create time series. Time series were divided into training and test set to create the best models (Decision Tree, Random Forest, XGBoost, and SVM). Finally, the models were evaluated by Pearson r correlation and RMSE. (Fig 1)

Results

A total of 9,935 time series were collected . The median follow-up time was 9 months. The models did not perform well in predicting weekly change of Hb level on the entire dataset (RMSE for Decision Tree was 0.141, for Random Forest was 0.135, for XGBoost was 0.137, and for SVM was 0.135), and the difference in weekly change of Hb ranged from -0.2 to 0.2 g/dL, approximately 0-40%. The best models are Random Forest, XGBoost and SVM with similar results. (Fig 2)

Conclusion

This study showed that AI model can predict weekly change in Hb level. Although the performance may not be able to accurately predict weekly changes in Hb levels. Future studies should aim to include a larger number of participants to improve the performance of the models.

Trial Flow Chart

The Difference of weekly Hb change of the model

Funding

• Government Support – Non-U.S.