Critical Care

This study developed a machine learning-based tool for childhood pneumonia prognosis, analyzing data from 437 cases between 2014 and 2020. Using SMOTE-Tomek for dataset balancing and SHAP values for feature selection, the model achieved 77-88% accuracy in predicting pneumonia outcomes, with critical severity indicators identified. The research underscores the potential of data science and machine learning in enhancing pneumonia case management and prognosis, even with limited sample sizes.

In this project, I built a deep-learning model using audio data collected from early preterm neonates in the NICU. Using labels obtained from Echocardiography for the diagnosis of PDA. This project can help in early, non-invasive detection of PDA, leading to timely interventions and better outcomes for preterm neonates. Subsequently, we converted these audio data into spectrograms and classified them using deep learning algorithms as either having PDA or not PDA. Currently, we have reached two hundred patients and the data collection process is ongoing. We will continue expanding our dataset to improve the model’s robustness and reliability.

In conclusion, maintaining healthcare can be challenging, especially after a large-scale disaster. We believe e-health technologies can overcome the hurdles and utilize collaborative and appropriate healthcare where and when needed

During my residency, my most significant project involved building a personalized transfusion strategy for PICU patients. We analyzed historical patient data using machine learning algorithms, focusing on variables that impact transfusion requirements, to develop a predictive model. Our model exhibits high performance, as demonstrated by the ROC curve plot. It allowed for more precise and timely transfusions, reducing unnecessary procedures and potential complications, thereby improving patient care.

This response emphasizes the cautious yet optimistic view on the use of ChatGPT in decision-making, highlighting its potential benefits in crucial situations and advocating for a balanced approach to technological advancement.

This case series highlights the effective use of low-flux hemodialysis (HD) in treating pediatric patients with acute methotrexate (MTX) toxicity following high-dose MTX infusion. The study included patients who experienced acute kidney injury (AKI) and elevated MTX levels, treated between 2012 and 2021. The results showed significant removal of MTX using low-flux HD, with no complications from the treatment, suggesting that conventional HD is a viable option for managing MTX toxicity, especially in resource-limited settings.

A deep learning project for segmenting echocardiography (ECHO) parasternal long-axis (PLAX) view images into six primary heart structures using a U-Net-inspired full convolutional network (FCN) architecture.