Ekanath Srihari Rangan

Ekanath Srihari Rangan

Auto-generated profile, based on publicly available information

Ekanath Srihari Rangan

Department of Medicine, Stanford University, Stanford, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 January 2024 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
TSThomas Savage
Thomas Savage
ANAshwin Nayak
Ashwin Nayak
RGRobert Gallo
Robert Gallo
EREkanath Rangan
Ekanath Rangan
JCJonathan H. Chen
Jonathan H. Chen
One of the major barriers to using large language models (LLMs) in medicine is the perception they use uninterpretable methods to make clinical decisions that are inherently different from the cognitive processes of clinicians. In this manuscript we develop diagnostic reasoning prompts to study whether LLMs can imitate clinical reasoning while accurately forming a diagnosis. We find that GPT-4 can be prompted to mimic the common clinical reasoning processes of clinicians without sacrificing diagnostic accuracy. This is significant because an LLM that can imitate clinical reasoning to provide an interpretable rationale offers physicians a means to evaluate whether an LLMs response is likely correct and can be trusted for patient care. Prompting methods that use diagnostic reasoning have the potential to mitigate the “black box” limitations of LLMs, bringing them one step closer to safe and effective use in medicine.

13 September 2018 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
RPRahul Krishnan Pathinarupothi
Rahul Krishnan Pathinarupothi
PDP Durga
P Durga
EREkanath Srihari Rangan
Ekanath Srihari Rangan
Global health which denotes equitable access to healthcare, particularly in remote-rural-developing regions, is characterized by unique challenges of affordability, accessibility, and availability for which one of the most promising technological interventions that is emerging is the Internet of Things (IoT) based remote health monitoring. We present an IoT based smart edge system for remote health monitoring, in which wearable vital sensors transmit data into two novel software engines, namely Rapid Active Summarization for effective PROgnosis (RASPRO) and Criticality Measure Index (CMI) alerts, both of which we have implemented in the IoT smart edge. RASPRO transforms voluminous sensor data into clinically meaningful summaries called Personalized Health Motifs (PHMs). The CMI alerts engine computes an aggregate criticality score. Our IoT smart edge employs a risk-stratified protocol consisting of rapid guaranteed push of alerts & PHMs directly to the physicians, and best effort pull of detailed data-on-demand (DD-on-D) through the cloud. We have carried out both clinical validation and performance evaluation of our smart edge system. The clinical validation on 183 patients demonstrated that the IoT smart edge is highly effective in remote monitoring, advance warning and detection of cardiac conditions, as quantified by three measures, precision (0.87), recall (0.83), and F1-score (0.85). Furthermore, performance evaluation showed significant reductions in the bandwidth (98%) and energy (90%), thereby making it suitable for emerging narrow-band IoT networks. In the deployment of our system in the cardiology institute of our University hospital, we observed that our IoT smart edge helped to increase the availability of physicians by 59%. Hence, our IoT smart edge system is a significant step towards addressing the requirements for global health.

29 November 2021 in Nature Medicine
Verified
Journal Article
Open access
PDF file
AAArash Alavi
Arash Alavi
GBGireesh K. Bogu
Gireesh K. Bogu
MWMeng Wang
Meng Wang
EREkanath Srihari Rangan
Ekanath Srihari Rangan
ABAndrew W. Brooks
Andrew W. Brooks
MSMichael P Snyder
Michael P Snyder
Early detection of infectious diseases is crucial for reducing transmission and facilitating early intervention. In this study, we built a real-time smartwatch-based alerting system that detects aberrant physiological and activity signals (heart rates and steps) associated with the onset of early infection and implemented this system in a prospective study. In a cohort of 3,318 participants, of whom 84 were infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), this system generated alerts for pre-symptomatic and asymptomatic SARS-CoV-2 infection in 67 (80%) of the infected individuals. Pre-symptomatic signals were observed at a median of 3 days before symptom onset. Examination of detailed survey responses provided by the participants revealed that other respiratory infections as well as events not associated with infection, such as stress, alcohol consumption and travel, could also trigger alerts, albeit at a much lower mean frequency (1.15 alert days per person compared to 3.42 alert days per person for coronavirus disease 2019 cases). Thus, analysis of smartwatch signals by an online detection algorithm provides advance warning of SARS-CoV-2 infection in a high percentage of cases. This study shows that a real-time alerting system can be used for early detection of infection and other stressors and employed on an open-source platform that is scalable to millions of users.

4 June 2025 in Nature Medicine
Verified
Journal Article
Open access
PDF file
YWyue wu
yue wu
BEBen Ehlert
Ben Ehlert
Ahmed MetwallyAhmed Metwally
Ahmed Metwally
DPDalia Perelman
Dalia Perelman
HPHeyjun Park
Heyjun Park
MSMichael P Snyder
Michael P Snyder
Elevated postprandial glycemic responses (PPGRs) are associated with type 2 diabetes and cardiovascular disease. PPGRs to the same foods have been shown to vary between individuals, but systematic characterization of the underlying physiologic and molecular basis is lacking. We measured PPGRs using continuous glucose monitoring in 55 well-phenotyped participants challenged with seven different standard carbohydrate meals administered in replicate. We also examined whether preloading a rice meal with fiber, protein or fat (‘mitigators’) altered PPGRs. We performed gold-standard metabolic tests and multi-omics profiling to examine the physiologic and molecular basis for interindividual PPGR differences. Overall, rice was the most glucose-elevating carbohydrate meal, but there was considerable interindividual variability. Individuals with the highest PPGR to potatoes (potato-spikers) were more insulin resistant and had lower beta cell function, whereas grape-spikers were more insulin sensitive. Rice-spikers were more likely to be Asian individuals, and bread-spikers had higher blood pressure. Mitigators were less effective in reducing PPGRs in insulin-resistant as compared to insulin-sensitive participants. Multi-omics signatures of PPGR and metabolic phenotypes were discovered, including insulin-resistance-associated triglycerides, hypertension-associated metabolites and PPGR-associated microbiome pathways. These results demonstrate interindividual variability in PPGRs to carbohydrate meals and mitigators and their association with metabolic and molecular profiles.

23 September 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
TSThomas Savage
Thomas Savage
SMStephen P Ma
Stephen P Ma
ABAbdessalem Boukil
Abdessalem Boukil
EREkanath Rangan
Ekanath Rangan
VPVishwesh Patel
Vishwesh Patel
JCJonathan Chen
Jonathan Chen
Background: Large language model (LLM) fine-tuning is the process of adjusting out-of-the-box model weights using a dataset of interest. Fine-tuning can be a powerful technique to improve model performance in fields like medicine, where LLMs may have poor out-of-the-box performance. The 2 common fine-tuning techniques are supervised fine-tuning (SFT) and direct preference optimization (DPO); however, little guidance is available for when to apply either method within clinical medicine or health care operations. Objective: This study aims to investigate the benefits of fine-tuning with SFT and DPO across a range of core natural language tasks in medicine to better inform clinical informaticists when either technique should be deployed. Methods: We use Llama3 8B (Meta) and Mistral 7B v2 (Mistral AI) to compare the performance of SFT alone and DPO across 4 common natural language tasks in medicine. The tasks we evaluate include text classification, clinical reasoning, text summarization, and clinical triage. Results: Our results found clinical reasoning accuracy increased from 7% to 22% with base Llama3 and Mistral2, respectively, to 28% and 33% with SFT, and then 36% and 40% with DPO (P=.003 and P=.004, respectively). Summarization quality, graded on a 5-point Likert scale, was 4.11 with base Llama3 and 3.93 with base Mistral2. Performance increased to 4.21 and 3.98 with SFT and then 4.34 and 4.08 with DPO (P<.001). F1-scores for provider triage were 0.55 for Llama3 and 0.49 for Mistral2, which increased to 0.58 and 0.52 with SFT and 0.74 and 0.66 with DPO (P<.001). F1-scores for urgency triage were 0.81 for Llama3 and 0.88 for Mistral2, which decreased with SFT to 0.79 and 0.87, and then experienced mixed results with DPO, achieving 0.91 and 0.85, respectively (P<.001 and P>.99, respectively). Finally, F1-scores for text classification were 0.63 for Llama3 and 0.73 for Mistral2, which increased to 0.98 and 0.97 with SFT, and then essentially did not change with DPO to 0.95 and 0.97, respectively (P=.55 and P>.99, respectively). DPO fine-tuning required approximately 2 to 3 times more compute resources than SFT alone. Conclusions: SFT alone is sufficient for simple tasks such as rule-based text classification, while DPO after SFT improves performance on the more complex tasks of triage, clinical reasoning, and summarization. We postulate that SFT alone is sufficient for simple tasks because SFT strengthens simple word-association reasoning, whereas DPO enables deeper comprehension because it is trained with both positive and negative examples, enabling the model to recognize more complex patterns. Ultimately, our results help inform clinical informaticists when to deploy either fine-tuning method and encourage commercial LLM providers to offer DPO fine-tuning for commonly used proprietary LLMs in medicine.

14 October 2022 in JAMIA Open
Verified
Journal Article
Open access
PDF file
EREkanath Srihari Rangan
Ekanath Srihari Rangan
RPRahul Krishnan Pathinarupothi
Rahul Krishnan Pathinarupothi
KAKanwaljeet J S Anand
Kanwaljeet J S Anand
MSMichael P Snyder
Michael P Snyder
Objective: To carry out exhaustive data-driven computations for the performance of noninvasive vital signs heart rate (HR), respiratory rate (RR), peripheral oxygen saturation (SpO2), and temperature (Temp), considered both independently and in all possible combinations, for early detection of sepsis. Materials and methods: By extracting features interpretable by clinicians, we applied Gradient Boosted Decision Tree machine learning on a dataset of 2630 patients to build 240 models. Validation was performed on a geographically distinct dataset. Relative to onset, predictions were clocked as per 16 pairs of monitoring intervals and prediction times, and the outcomes were ranked. Results: The combination of HR and Temp was found to be a minimal feature set yielding maximal predictability with area under receiver operating curve 0.94, sensitivity of 0.85, and specificity of 0.90. Whereas HR and RR each directly enhance prediction, the effects of SpO2 and Temp are significant only when combined with HR or RR. In benchmarking relative to standard methods Systemic Inflammatory Response Syndrome (SIRS), National Early Warning Score (NEWS), and quick-Sequential Organ Failure Assessment (qSOFA), Vital-SEP outperformed all 3 of them. Conclusion: It can be concluded that using intensive care unit data even 2 vital signs are adequate to predict sepsis upto 6 h in advance with promising accuracy comparable to standard scoring methods and other sepsis predictive tools reported in literature. Vital-SEP can be used for fast-track prediction especially in limited resource hospital settings where laboratory based hematologic or biochemical assays may be unavailable, inaccurate, or entail clinically inordinate delays. A prospective study is essential to determine the clinical impact of the proposed sepsis prediction model and evaluate other outcomes such as mortality and duration of hospital stay.