5 March 2025 in Journal of Medical Internet Research
Background: With suicide rates in the United States at an all-time high, individuals experiencing suicidal ideation are increasingly turning to large language models (LLMs) for guidance and support. Objective: The objective of this study was to assess the competency of 3 widely used LLMs to distinguish appropriate versus inappropriate responses when engaging individuals who exhibit suicidal ideation. Methods: This observational, cross-sectional study evaluated responses to the revised Suicidal Ideation Response Inventory (SIRI-2) generated by ChatGPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro. Data collection and analyses were conducted in July 2024. A common training module for mental health professionals, SIRI-2 provides 24 hypothetical scenarios in which a patient exhibits depressive symptoms and suicidal ideation, followed by two clinician responses. Clinician responses were scored from –3 (highly inappropriate) to +3 (highly appropriate). All 3 LLMs were provided with a standardized set of instructions to rate clinician responses. We compared LLM responses to those of expert suicidologists, conducting linear regression analyses and converting LLM responses to z scores to identify outliers (z score>1.96 or <–1.96; P<0.05). Furthermore, we compared final SIRI-2 scores to those produced by health professionals in prior studies. Results: All 3 LLMs rated responses as more appropriate than ratings provided by expert suicidologists. The item-level mean difference was 0.86 for ChatGPT (95% CI 0.61-1.12; P<.001), 0.61 for Claude (95% CI 0.41-0.81; P<.001), and 0.73 for Gemini (95% CI 0.35-1.11; P<.001). In terms of z scores, 19% (9 of 48) of ChatGPT responses were outliers when compared to expert suicidologists. Similarly, 11% (5 of 48) of Claude responses were outliers compared to expert suicidologists. Additionally, 36% (17 of 48) of Gemini responses were outliers compared to expert suicidologists. ChatGPT produced a final SIRI-2 score of 45.7, roughly equivalent to master’s level counselors in prior studies. Claude produced an SIRI-2 score of 36.7, exceeding prior performance of mental health professionals after suicide intervention skills training. Gemini produced a final SIRI-2 score of 54.5, equivalent to untrained K-12 school staff. Conclusions: Current versions of 3 major LLMs demonstrated an upward bias in their evaluations of appropriate responses to suicidal ideation; however, 2 of the 3 models performed equivalent to or exceeded the performance of mental health professionals.
15 December 2012 in BMC Systems Biology
Background: Lineage specific differentiation of human embryonic stem cells (hESCs) is largely mediated by specific growth factors and extracellular matrix molecules. Growth factors initiate a cascade of signals which control gene transcription and cell fate specification. There is a lot of interest in inducing hESCs to an endoderm fate which serves as a pathway towards more functional cell types like the pancreatic cells. Research over the past decade has established several robust pathways for deriving endoderm from hESCs, with the capability of further maturation. However, in our experience, the functional maturity of these endoderm derivatives, specifically to pancreatic lineage, largely depends on specific pathway of endoderm induction. Hence it will be of interest to understand the underlying mechanism mediating such induction and how it is translated to further maturation. In this work we analyze the regulatory interactions mediating different pathways of endoderm induction by identifying co-regulated transcription factors. Results: hESCs were induced towards endoderm using activin A and 4 different growth factors (FGF2 (F), BMP4 (B), PI3KI (P), and WNT3A (W)) and their combinations thereof, resulting in 15 total experimental conditions. At the end of differentiation each condition was analyzed by qRT-PCR for 12 relevant endoderm related transcription factors (TFs). As a first approach, we used hierarchical clustering to identify which growth factor combinations favor up-regulation of different genes. In the next step we identified sets of co-regulated transcription factors using a biclustering algorithm. The high variability of experimental data was addressed by integrating the biclustering formulation with bootstrap re-sampling to identify robust networks of co-regulated transcription factors. Our results show that the transition from early to late endoderm is favored by FGF2 as well as WNT3A treatments under high activin. However, induction of late endoderm markers is relatively favored by WNT3A under high activin. Conclusions: Use of FGF2, WNT3A or PI3K inhibition with high activin A may serve well in definitive endoderm induction followed by WNT3A specific signaling to direct the definitive endoderm into late endodermal lineages. Other combinations, though still feasible for endoderm induction, appear less promising for pancreatic endoderm specification in our experiments.
18 June 2013 in Biomacromolecules
1 December 2017 in Journal of Virology
Immunosenescence, an age-related decline in immune function, is a major contributor to morbidity and mortality in the elderly. Older hosts exhibit a delayed onset of immunity and prolonged inflammation after an infection, leading to excess damage and a greater likelihood of death. Our study applies a rule-based model to infer which components of the immune response are most changed in an aged host. Two groups of BALB/c mice (aged 12 to 16 weeks and 72 to 76 weeks) were infected with 2 inocula: a survivable dose of 50 PFU and a lethal dose of 500 PFU. Data were measured at 10 points over 19 days in the sublethal case and at 6 points over 7 days in the lethal case, after which all mice had died. Data varied primarily in the onset of immunity, particularly the inflammatory response, which led to a 2-day delay in the clearance of the virus from older hosts in the sublethal cohort. We developed a Boolean model to describe the interactions between the virus and 21 immune components, including cells, chemokines, and cytokines, of innate and adaptive immunity. The model identifies distinct sets of rules for each age group by using Boolean operators to describe the complex series of interactions that activate and deactivate immune components. Our model accurately simulates the immune responses of mice of both ages and with both inocula included in the data (95% accurate for younger mice and 94% accurate for older mice) and shows distinct rule choices for the innate immunity arm of the model between younger and aging mice in response to influenza A virus infection.IMPORTANCEInfluenza virus infection causes high morbidity and mortality rates every year, especially in the elderly. The elderly tend to have a delayed onset of many immune responses as well as prolonged inflammatory responses, leading to an overall weakened response to infection. Many of the details of immune mechanisms that change with age are currently not well understood. We present a rule-based model of the intrahost immune response to influenza virus infection. The model is fit to experimental data for young and old mice infected with influenza virus. We generated distinct sets of rules for each age group to capture the temporal differences seen in the immune responses of these mice. These rules describe a network of interactions leading to either clearance of the virus or death of the host, depending on the initial dosage of the virus. Our models clearly demonstrate differences in these two age groups, particularly in the innate immune responses.
1 February 2018 in Computers & Chemical Engineering
1 June 2016 in Critical Care Medicine
Objectives: Sepsis therapies have proven to be elusive because of the difficulty of translating biologically sound and effective interventions in animal models to humans. A part of this problem originates from the fact that septic patients present at various times after the onset of sepsis, whereas the exact time of infection is controlled in animal models. We sought to determine whether data mining longitudinal physiologic data in a nonhuman primate model of Escherichia coli–induced sepsis could help inform the time of onset of infection. Design: A nearest-neighbor approach was used to back cast the time of onset of infection in animal models of sepsis. Animal data were censored to simulate prospective monitoring at any moment along the septic infection. This was compared against an uncensored database to find the most similar animal in order to estimate the infection onset time. Leave-one-out cross-validation was used for validation. Biomarker selection was performed based on the criteria of estimation accuracy and/or ease of measurement. Setting: Computational experimental on existing experimental data. Subjects: Retrospective data from 33 septic baboons (Papio ursinus) subjected to Escherichia coli infusion. Validation was performed using 14 pigs that were subjected to surgically induced fecal peritonitis and 22 pigs that were subjected to lipopolysaccharide infusion. Measurements and Main Results: Longitudinal physiologic and serum markers, time of death. The presence of uniquely changing biomarkers during septic infection enabled the estimation of infection onset time in the datasets. Various combinations of temporal biomarkers, such as WBC, oxygen content, mean arterial pressure, and heart rate, yielded estimation accuracies of up to 97.8%. The use of temporal vital signs and a single measurement of serum biomarkers yielded highly accurate estimates without the need for invasive measurements. Validation in the pig data revealed similar results despite the heterogeneity of multiple experimental cohorts. This suggests that the method may be effective if sufficiently similar subjects are present in the database. Conclusions: One nearest-neighbor analysis showed promise in accurately identifying the onset of infection given a database of known infection times and of sufficient breadth. We suggest that this approach is ready for evaluation within the clinical setting using human data.