Geoffrey Siwo

Mercy Asiedu, Nenad Tomasev, Chintan Ghate et al.

While large language models (LLMs) have shown promise for medical question answering, there is limited work focused on tropical and infectious disease-specific exploration. We build on an opensource tropical and infectious diseases (TRINDs) dataset, expanding it to include demographic and semantic clinical and consumer augmentations yielding 11000+ prompts. We evaluate LLM performance on these, comparing generalist and medical LLMs, as well as LLM outcomes to human experts. We demonstrate through systematic experimentation, the benefit of contextual information such as demographics, location, gender, risk factors for optimal LLM response. Finally we develop a prototype of TRINDs-LM, a research tool that provides a playground to navigate how context impacts LLM outputs for health.

Taeho Jung, Ryan Karl, Geoffrey H. Siwo

DNA fingerprinting is a cornerstone for human identification in forensics, where the sequence of highly polymorphic short tandem repeats (STRs) from an individual is compared against a DNA database. This presents significant privacy risks to individuals with DNA profiles in the database due to hacking by malicious attackers who may access the data and misuse it for secondary purposes. In this paper, we propose a novel cryptographic framework for jointly encrypting DNA-based fingerprints (STRs) with other biometric data, for example, facial images, such that the STRs and biometrics information of an individual are revealed only when a positive match is found, i.e. the STRs act as decryption keys. Specifically, when a search is performed on the encrypted database using STR sequences of an individual in the database, a perfect match generates the facial image and/ or other biometrics of the individual while the lack of a match returns a null result. By jointly encrypting DNA fingerprints and other biometrics using the unique STRs generated keys, our approach ensures perfect privacy of the encrypted information with decryption of only the record with STRs matching the query. This safeguards the information of other individuals in the same database. The proposed approach can also be used to securely authenticate the identity of individuals or biological material in scenarios beyond forensics including tracking the identity of samples for clinical genetics and cell therapies.