About Siddhu Pachipala
Siddhu aimed to develop a machine learning tool to gauge patients’ suicide risk and the best course of treatment based on their diary entries. One of his models found correlations between semantics, suicide risk and course of treatment to be more accurate than a second model that looked at syntax. He believes that using semantics to gauge psychological health is worthy of future study.
SuiSensor: A Novel, Low-Cost Machine Learning System for Real-Time Suicide Risk Identification and Treatment Optimization via Computational LinguisticsView Poster
Siddhu Pachipala, 18, of The Woodlands, aimed to develop a machine-learning tool that uses patients’ writing to assess their suicide risk and best course of treatment for his Regeneron Science Talent Search behavioral and social sciences project. Treating high-risk patients has been shown to reduce suicide attempts, but existing assessments have led to under-detection. Using linguistic analysis, Siddhu evaluated diary entries from existing suicidality assessment data. He then wrote code to predict someone’s suicide risk based on two language properties. One is syntax – or grammatical qualities – and the other is semantics, or meaning. Of his two models, the one that found correlations between semantics, suicide risk and course of treatment appeared to be more accurate than the one looking at syntax. He believes this suggests that using semantics to gauge psychological health merits future study.
Siddhu attends The Woodlands College Park High School. The son of Sharmila Naidu and Krishna Pachipala, he also works as a research intern for the University of California’s EdgeLab. He has researched political party affiliation and belief polarization, and has also developed an ASL interpreter that accounts for ethnic dialects.
Beyond the Project
Siddhu organized a hackathon for Stanford University in which he taught K-12 students human-centered design – problem-solving by listening to people’s concerns.
FUN FACTS: Active in a varsity a cappella choir, Siddhu loves music but dislikes dancing in public. However, he has been known to get down to Bollywood hits in the privacy of his home.