Indian American researcher Shreya Parchure is leveraging cutting-edge technology to improve treatment for stroke survivors suffering from aphasia. A bioengineering MD-PhD candidate at the University of Pennsylvania’s Perelman School of Medicine and the School of Engineering and Applied Science, Parchure’s work aims to personalize speech therapy using “explainable AI.” This novel approach could significantly enhance recovery prospects for the estimated one-third of stroke survivors who experience impaired speech.
Parchure’s interest in language ability as a vital component of quality of life was cultivated through her experiences growing up across two continents and further solidified during her clinical rotations in a neurocritical care unit. Observing patients struggling to regain their speech after strokes sparked her commitment to advancing research and care in this area. “One patient was initially unable to speak, but gradually, through speech therapy, began regaining words day by day,” she said, recounting the emotional journey of her patient who found renewed hope as she made progress.
Standardized speech therapies currently dominate the treatment landscape for post-stroke aphasia. However, Parchure and her team at the Laboratory for Cognition and Neural Stimulation (LCNS) are exploring the use of explainable AI to tailor treatment plans by predicting the most effective routes to language recovery. While previous models have utilized neuroimaging and the duration of time since a stroke to assess aphasia severity, Parchure’s research takes a more comprehensive approach by incorporating how language is constructed and processed within the brain.
Explainable AI, as Parchure describes it, integrates clinically available data—including age, education, and stroke size—with linguistic complexity. This multifaceted approach enables AI models to predict recovery times and recommend personalized treatments while providing clinicians with clear rationale based on individual patient circumstances. “When we have an AI making a prediction, we really want to know why,” she asserted, highlighting the critical importance of transparency in AI-driven healthcare solutions.
To create her AI-powered tool, Parchure collected speech samples from patients with post-stroke aphasia. This data was utilized to train an explainable AI algorithm capable of making predictions based on a diverse array of clinically relevant factors. The tool even accounted for personal attributes, such as social support and stroke size, allowing it to predict speech performance on a word-by-word basis. Parchure points out that this level of detail can help clinicians uncover the underlying factors influencing a patient’s speech abilities, leading to more nuanced treatment recommendations.
The AI-powered app developed by Parchure and her team features an innovative “digital twin” for each patient, serving as a predictive model for language recovery. This digital counterpart offers clinicians the ability to simulate various treatment scenarios, enhancing the efficiency of clinical trials by allowing for comparisons between projected and actual recovery outcomes. “The goal of my MD-PhD training has been to translate advances in research in a way that will benefit patients,” said Parchure, whose research earned her the Best Poster award at the 2025 PSOM Student Research Symposium.
Looking to the future, Parchure is optimistic about the role of AI in personalizing speech therapy. She anticipates a significant shift over the next decade toward leveraging technology to ensure that every stroke survivor with aphasia can reconnect with the joy of language. As healthcare increasingly embraces AI-driven solutions, Parchure’s work stands as a testament to the potential of technology to transform patient care and improve quality of life for those affected by stroke.
See also
Autonomous AI Powered Ophthalmology Screening Market Reaches $2.7B by 2035, Growing at 8.4% CAGR
AI Study Reveals Generated Faces Indistinguishable from Real Photos, Erodes Trust in Visual Media
Gen AI Revolutionizes Market Research, Transforming $140B Industry Dynamics
Researchers Unlock Light-Based AI Operations for Significant Energy Efficiency Gains
Tempus AI Reports $334M Earnings Surge, Unveils Lymphoma Research Partnership
