Reza Hosseini Ghomi

Drewry H. Morris, Luis Valles, Reza Hosseini Ghomi

GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps, a ten-step process with 90% per-step reliability completes successfully only 35% of the time. Existing workflow platforms provide durable execution and observability but offer few semantic correctness guarantees, while agentic systems plan at inference time, making behavior sensitive to prompt variation and difficult to audit. GraphFlow is designed to address this gap by treating workflow diagrams as the executable specification, a single artifact defining data scope, execution semantics, and monitoring. At compile time, a restricted class of diagrams is specified to produce reusable automations whose contracts (preconditions, postconditions, and composition obligations) are intended to be proof-checked before admission to a shared library. At runtime, a durable engine records outcomes in an append-only event log and can enforce contracts at system boundaries, supporting replay, retries, and audit. Swimlanes make trust boundaries explicit, separating verified logic from external systems, human judgment, and AI decisions. A year-long pilot across three clinical sites executed 8,728 cohort-enrolled workflow runs with a 97.08% completion rate under an early prototype without the verified-core subsystem; observed failures were localized primarily to external integrations. The formal semantics and proof-checked admission model described here are specified and under active development. Evaluation of the verified core is reserved for future work.

Larry Zhang, Xiaotong Chen, Abbad Vakil et al.

In recent years, data-driven models have enabled significant advances in medicine. Simultaneously, voice has shown potential for analysis in precision medicine as a biomarker for screening illnesses. There has been a growing trend to pursue voice data to understand neuropsychiatric diseases. In this paper, we present DigiVoice, a comprehensive feature extraction and analysis pipeline for voice data. DigiVoice supports raw .WAV files and text transcriptions in order to analyze the entire content of voice. DigiVoice supports feature extraction including acoustic, natural language, linguistic complexity, and semantic coherence features. DigiVoice also supports machine learning capabilities including data visualization, feature selection, feature transformation, and modeling. To our knowledge, DigiVoice provides the most comprehensive voice feature set for data analysis to date. With DigiVoice, we plan to accelerate research to correlate voice biomarkers with illness to enable data-driven treatment. We have worked closely with our industry partner, NeuroLex Laboratories, to make voice computing open source and accessible. DigiVoice enables researchers to leverage our technology across the domains of voice computing and precision medicine without domain-specific expertise. Our work allows any researchers to use voice as a biomarker in their past, current, or future studies.

Huy Phi, Sanjeev Janarthanan, Larry Zhang et al.

Deep-Brain Stimulation (DBS) is a therapy used in conjunction with medication to help alleviate the motor symptoms of Parkinson's Disease (PD). However, the monitoring and adjustment of DBS settings is tedious and expensive, requiring long programming appointments every few months. We investigated the possible correlation between PD motor score severity and digitally extracted patient voice features to potentially aid clinicians in their monitoring and treatment of PD with DBS, and eventually enable a closed-loop DBS system. 5 DBS PD patients were enrolled. Voice samples were collected for various voice tasks (single phoneme vocalization, free speech task, sentence reading task, counting backward task, categorical fluency task) for DBS ON and OFF states. Motor scores per the Unified Parkinson's Disease Rating Scale (UPDRS) were also collected for DBS ON and OFF states. Voice samples were then analyzed to extract voice features using publicly available voice feature library sets, and statistically compared for DBS ON and OFF. Of the feature categories explored (Acoustic, Prosodic, Linguistic) 6 features from the GeMAPS feature set for acoustic features demonstrated significant differences with DBS ON and OFF (p<0.05). Prosodic features such as pause length/percentage were found to be negatively correlated with increased motor symptom severity. Non-significant differences were found for linguistic features. These findings provide preliminary evidence for acoustic and prosodic speech features to act as potential biomarkers for PD disease severity in DBS patients. We hope to explore further by expanding our data set, identifying other features, applying machine learning models, and working towards a closed-loop DBS system that can auto-tune itself based on changes in a patient's voice.