AI Applications in Healthcare

Fellowship Learning Experience 

​

In this rotation, the Fellow would delve into the exciting field of healthcare artificial intelligence (AI) and its applications in pharmacy practice. They would explore how AI algorithms and machine learning techniques can be leveraged to improve patient care, optimize medication management, and enhance healthcare decision-making. The rotation would include additional rotations if emphasis is desired in this area:

​

• AI in Clinical Decision Support: The Fellow would learn about the use of AI algorithms in clinical decision support systems. They would understand how AI can analyze patient data, identify patterns, and provide recommendations for medication dosing, adverse event prediction, drug-drug interactions, and personalized treatment plans. The Fellow would explore the integration of AI-driven clinical decision support tools within pharmacy practice. This aspect would focus on the role of AI in medication management processes, including medication reconciliation, prescription optimization, and medication adherence. The Fellow would learn about AI-enabled technologies that assist in medication error detection, medication reconciliation algorithms, and predictive modeling for medication adherence.

• AI in Medication Management: The Fellow would gain insights into the use of NLP technologies in pharmacy practice. They would explore how AI algorithms can process and analyze textual information from electronic health records, medical literature, and patient notes to extract relevant information, facilitate data mining, and support clinical decision-making.

• Natural Language Processing (NLP): The healthcare artificial intelligence rotation aims to provide the Fellow with a deep understanding of the potential of AI in pharmacy practice. It equips them with the knowledge and skills to leverage AI algorithms, machine learning techniques, and data-driven insights to enhance patient care, optimize medication management, and drive innovation in healthcare.

  • Further training focus will explore:

    • ​Best Practices in AI Model Training: The Fellow would gain insights into selecting appropriate AI models for healthcare applications. They would learn about various algorithms, architectures, and frameworks commonly used in healthcare AI, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers. The Fellow would explore evaluation metrics and techniques to assess the performance and generalization of AI models. Model

    • Selection and Evaluation: This section would cover preprocessing techniques and feature engineering approaches specific to healthcare data. The Fellow would learn methods to handle missing data, normalize variables, and extract relevant features from healthcare datasets. They would gain an understanding of how preprocessing and feature engineering impact AI model performance.

    • Preprocessing and Feature Engineering:  The Fellow would explore regularization techniques and optimization algorithms to enhance the performance and generalization of AI models in healthcare. They would learn about approaches such as dropout, batch normalization, and hyperparameter tuning to prevent overfitting and improve model robustness.

    • Regularization and Optimization: The Fellow would explore regularization techniques and optimization algorithms to enhance the performance and generalization of AI models in healthcare. They would learn about approaches such as dropout, batch normalization, and hyperparameter tuning to prevent overfitting and improve model robustness.

• Ethical Considerations and Bias in AI: This rotation would also cover ethical considerations associated with AI in healthcare. The Fellow would explore topics such as data privacy, patient consent, transparency, and potential biases in AI algorithms. They would gain an understanding of the importance of ethical AI implementation and ensuring fairness and equity in healthcare AI applications.