Search

Wildland fire-atmosphere interaction generates complex turbulence patterns, organized across multiple scales, which inform fire-spread behaviour, firebrand transport, and smoke dispersion. Here, we utilize wavelet-based techniques to explore the characteristic temporal scales associated with coherent patterns in the measured temperature and the turbulent fluxes during a prescribed wind-driven (heading) surface fire beneath a forest canopy. We use temperature and velocity measurements from tower-mounted sonic anemometers at multiple heights. Patterns in the wavelet-based energy density of the measured temperature plotted on a time-frequency plane indicate the presence of fire-modulated ramp-cliff structures in the low-to-mid-frequency band (0.01-0.33 Hz), with mean ramp durations approximately 20% shorter and ramp slopes that are an order of magnitude higher compared to no-fire conditions. We then investigate heat- and momentum-flux events near the canopy top through a cross-wavelet coherence analysis. Briefly before the fire-front arrives at the tower base, momentum-flux events are relatively suppressed and turbulent fluxes are chiefly thermally-driven near the canopy top, owing to the tilting of the flame in the direction of the wind. Fire-induced heat-flux events comprising warm updrafts and cool downdrafts are coherent down to periods of a second, whereas ambient heat-flux events operate mainly at higher periods (above 17 s). Later, when the strongest temperature fluctuations are recorded near the surface, fire-induced heat-flux events occur intermittently at shorter scales and cool sweeps start being seen for periods ranging from 8 to 35 s near the canopy top, suggesting a diminishing influence of the flame and increasing background atmospheric variability thereat. The improved understanding of the characteristic time scales associated with fire-induced turbulence features, as the fire-front evolves, will help develop more reliable fire behaviour and scalar transport models.

Abstract Large language models (LLMs) can optimize clinical workflows; however, the economic and computational challenges of their utilization at the health system scale are underexplored. We evaluated how concatenating queries with multiple clinical notes and tasks simultaneously affects model performance under increasing computational loads. We assessed ten LLMs of different capacities and sizes utilizing real-world patient data. We conducted >300,000 experiments of various task sizes and configurations, measuring accuracy in question-answering and the ability to properly format outputs. Performance deteriorated as the number of questions and notes increased. High-capacity models, like Llama-3–70b, had low failure rates and high accuracies. GPT-4-turbo-128k was similarly resilient across task burdens, but performance deteriorated after 50 tasks at large prompt sizes. After addressing mitigable failures, these two models can concatenate up to 50 simultaneous tasks effectively, with validation on a public medical question-answering dataset. An economic analysis demonstrated up to a 17-fold cost reduction at 50 tasks using concatenation. These results identify the limits of LLMs for effective utilization and highlight avenues for cost-efficiency at the enterprise scale.

Summary: Genotype imputation is crucial for genome-wide association studies (GWASs), but reference panels and existing benchmarking studies prioritize European individuals. Consequently, it is unclear which publicly available reference panel should be used for Pakistani individuals, and whether ancestry composition or sample size of the panel matters more for imputation accuracy. Our study compared different reference panels to impute genotype data in 1,814 Pakistani individuals, finding the best performance balancing accuracy and coverage with meta-imputation with TOPMed and the expanded 1000 Genomes (ex1KG) reference. Imputation accuracy of ex1KG outperformed TOPMed for common variants despite its 30-fold smaller sample size, supporting efforts to create future panels with diverse populations.

Abstract: Importance: SARS-CoV-2 infection can result in ongoing, relapsing, or new symptoms or other health effects after the acute phase of infection; termed post-acute sequelae of SARS-CoV-2 infection (PASC), or long COVID. The characteristics, prevalence, trajectory and mechanisms of PASC are ill-defined. The objectives of the Researching COVID to Enhance Recovery (RECOVER) Multi-site Observational Study of PASC in Adults (RECOVER-Adult) are to: (1) characterize PASC prevalence; (2) characterize the symptoms, organ dysfunction, natural history, and distinct phenotypes of PASC; (3) identify demographic, social and clinical risk factors for PASC onset and recovery; and (4) define the biological mechanisms underlying PASC pathogenesis. Methods: RECOVER-Adult is a combined prospective/retrospective cohort currently planned to enroll 14,880 adults aged ≥18 years. Eligible participants either must meet WHO criteria for suspected, probable, or confirmed infection; or must have evidence of no prior infection. Recruitment occurs at 86 sites in 33 U.S. states, Washington, DC and Puerto Rico, via facility– and community-based outreach. Participants complete quarterly questionnaires about symptoms, social determinants, vaccination status, and interim SARS-CoV-2 infections. In addition, participants contribute biospecimens and undergo physical and laboratory examinations at approximately 0, 90 and 180 days from infection or negative test date, and yearly thereafter. Some participants undergo additional testing based on specific criteria or random sampling. Patient representatives provide input on all study processes. The primary study outcome is onset of PASC, measured by signs and symptoms. A paradigm for identifying PASC cases will be defined and updated using supervised and unsupervised learning approaches with cross– validation. Logistic regression and proportional hazards regression will be conducted to investigate associations between risk factors, onset, and resolution of PASC symptoms. Discussion: RECOVER-Adult is the first national, prospective, longitudinal cohort of PASC among US adults. Results of this study are intended to inform public health, spur clinical trials, and expand treatment options.

ObjectivesInterprofessional feedback and teamwork skills training are important in graduate medical education. Critical event debriefing is a unique interprofessional team training opportunity in the emergency department. While potentially educational, these varied, high-stakes events can threaten psychological safety for learners. This is a qualitative study of emergency medicine resident physicians' experience of interprofessional feedback during critical event debriefing to characterize factors that impact their psychological safety.MethodsThe authors conduced semistructured interviews with resident physicians who were the physician team leader during a critical event debriefing. Interviews were coded and themes were generated using a general inductive approach and concepts from social ecological theory.ResultsEight residents were interviewed. The findings suggest that cultivating a safe learning environment for residents during debriefings involves the following: (1) allowing space for validating statements, (2) supporting strong interprofessional relationships, (3) providing structured opportunities for interprofessional learning, (4) encouraging attendings to model vulnerability, (5) standardizing the process of debriefing, (6) rejecting unprofessional behavior, and (7) creating the time and space for the process in the workplace.ConclusionsGiven the numerous intrapersonal, interpersonal, and institutional factors at play, educators should be sensitive to times when a resident cannot engage due to unaddressed threats to their psychological safety. Educators can address these threats in real time and over the course of a resident's training to enhance psychological safety and the potential educational impact of critical event debriefing.

BackgroundEmpathy, a fundamental aspect of human interaction, is characterized as the ability to experience another being’s emotions within oneself. In health care, empathy is a fundamental for health care professionals and patients’ interaction. It is a unique quality to humans that large language models (LLMs) are believed to lack. ObjectiveWe aimed to review the literature on the capacity of LLMs in demonstrating empathy. MethodsWe conducted a literature search on MEDLINE, Google Scholar, PsyArXiv, medRxiv, and arXiv between December 2022 and February 2024. We included English-language full-length publications that evaluated empathy in LLMs’ outputs. We excluded papers evaluating other topics related to emotional intelligence that were not specifically empathy. The included studies’ results, including the LLMs used, performance in empathy tasks, and limitations of the models, along with studies’ metadata were summarized. ResultsA total of 12 studies published in 2023 met the inclusion criteria. ChatGPT-3.5 (OpenAI) was evaluated in all studies, with 6 studies comparing it with other LLMs such GPT-4, LLaMA (Meta), and fine-tuned chatbots. Seven studies focused on empathy within a medical context. The studies reported LLMs to exhibit elements of empathy, including emotions recognition and emotional support in diverse contexts. Evaluation metric included automatic metrics such as Recall-Oriented Understudy for Gisting Evaluation and Bilingual Evaluation Understudy, and human subjective evaluation. Some studies compared performance on empathy with humans, while others compared between different models. In some cases, LLMs were observed to outperform humans in empathy-related tasks. For example, ChatGPT-3.5 was evaluated for its responses to patients’ questions from social media, where ChatGPT’s responses were preferred over those of humans in 78.6% of cases. Other studies used subjective readers’ assigned scores. One study reported a mean empathy score of 1.84-1.9 (scale 0-2) for their fine-tuned LLM, while a different study evaluating ChatGPT-based chatbots reported a mean human rating of 3.43 out of 4 for empathetic responses. Other evaluations were based on the level of the emotional awareness scale, which was reported to be higher for ChatGPT-3.5 than for humans. Another study evaluated ChatGPT and GPT-4 on soft-skills questions in the United States Medical Licensing Examination, where GPT-4 answered 90% of questions correctly. Limitations were noted, including repetitive use of empathic phrases, difficulty following initial instructions, overly lengthy responses, sensitivity to prompts, and overall subjective evaluation metrics influenced by the evaluator’s background. ConclusionsLLMs exhibit elements of cognitive empathy, recognizing emotions and providing emotionally supportive responses in various contexts. Since social skills are an integral part of intelligence, these advancements bring LLMs closer to human-like interactions and expand their potential use in applications requiring emotional intelligence. However, there remains room for improvement in both the performance of these models and the evaluation strategies used for assessing soft skills.

Host genetics is a key determinant of COVID-19 outcomes. Previously, the COVID-19 Host Genetics Initiative genome-wide association study used common variants to identify multiple loci associated with COVID-19 outcomes. However, variants with the largest impact on COVID-19 outcomes are expected to be rare in the population. Hence, studying rare variants may provide additional insights into disease susceptibility and pathogenesis, thereby informing therapeutics development. Here, we combined whole-exome and whole-genome sequencing from 21 cohorts across 12 countries and performed rare variant exome-wide burden analyses for COVID-19 outcomes. In an analysis of 5,085 severe disease cases and 571,737 controls, we observed that carrying a rare deleterious variant in the SARS-CoV-2 sensor toll-like receptor TLR7 (on chromosome X) was associated with a 5.3-fold increase in severe disease (95% CI: 2.75-10.05, p = 5.41x10-7). This association was consistent across sexes. These results further support TLR7 as a genetic determinant of severe disease and suggest that larger studies on rare variants influencing COVID-19 outcomes could provide additional insights.

The ambient atmospheric environment affects the growth and spread of wildland fires, whereas heat and moisture released from the fires and the reduction of the surface drag in the burned areas can significantly alter local atmospheric conditions. Observational studies on fire–atmosphere interactions have used instrumented towers to collect data during prescribed fires, but a few towers in an operational-scale burn plot (usually > 103 m2) have made it extremely challenging to capture the myriad of factors controlling fire–atmosphere interactions, many of which exhibit strong spatial variability. Here, we present analyses of atmospheric turbulence data collected using a 4 × 4 array of fast-response sonic anemometers during a fire experiment on a 10 m × 10 m burn plot. In addition to confirming some of the previous findings on atmospheric turbulence associated with low-intensity surface fires, our results revealed substantial heterogeneity in turbulent intensity and heat and momentum fluxes just above the combustion zone. Despite the small plot (100 m2), fire-induced atmospheric turbulence exhibited strong dependence on the downwind distance from the initial line fire and the relative position specific to the fire front as the surface fire spread through the burn plot. This result highlights the necessity for coupled atmosphere–fire behavior models to have 1–2 m grid spacing to resolve heterogeneities in fire–atmosphere interactions that operate on spatiotemporal scales relevant to atmospheric turbulence. The findings here have important implications for modeling smoke dispersion, as atmospheric dispersion characteristics in the vicinity of a wildland fire are directly affected by fire-induced turbulence.

Mesendodermal specification is one of the earliest events in embryogenesis, where cells first acquire distinct identities. Cell differentiation is a highly regulated process that involves the function of numerous transcription factors (TFs) and signaling molecules, which can be described with gene regulatory networks (GRNs). Cell differentiation GRNs are difficult to build because existing mechanistic methods are low throughput, and high-throughput methods tend to be non-mechanistic. Additionally, integrating highly dimensional data composed of more than two data types is challenging. Here, we use linked self-organizing maps to combine chromatin immunoprecipitation sequencing (ChIP-seq)/ATAC-seq with temporal, spatial, and perturbation RNA sequencing (RNA-seq) data from Xenopus tropicalis mesendoderm development to build a high-resolution genome scale mechanistic GRN. We recover both known and previously unsuspected TF-DNA/TF-TF interactions validated through reporter assays. Our analysis provides insights into transcriptional regulation of early cell fate decisions and provides a general approach to building GRNs using highly dimensional multi-omic datasets.

Abstract The United States Medical Licensing Examination (USMLE) has been a subject of performance study for artificial intelligence (AI) models. However, their performance on questions involving USMLE soft skills remains unexplored. This study aimed to evaluate ChatGPT and GPT-4 on USMLE questions involving communication skills, ethics, empathy, and professionalism. We used 80 USMLE-style questions involving soft skills, taken from the USMLE website and the AMBOSS question bank. A follow-up query was used to assess the models’ consistency. The performance of the AI models was compared to that of previous AMBOSS users. GPT-4 outperformed ChatGPT, correctly answering 90% compared to ChatGPT’s 62.5%. GPT-4 showed more confidence, not revising any responses, while ChatGPT modified its original answers 82.5% of the time. The performance of GPT-4 was higher than that of AMBOSS's past users. Both AI models, notably GPT-4, showed capacity for empathy, indicating AI's potential to meet the complex interpersonal, ethical, and professional demands intrinsic to the practice of medicine.

BackgroundWith their unmatched ability to interpret and engage with human language and context, large language models (LLMs) hint at the potential to bridge AI and human cognitive processes. This review explores the current application of LLMs, such as ChatGPT, in the field of psychiatry.MethodsWe followed PRISMA guidelines and searched through PubMed, Embase, Web of Science, and Scopus, up until March 2024.ResultsFrom 771 retrieved articles, we included 16 that directly examine LLMs’ use in psychiatry. LLMs, particularly ChatGPT and GPT-4, showed diverse applications in clinical reasoning, social media, and education within psychiatry. They can assist in diagnosing mental health issues, managing depression, evaluating suicide risk, and supporting education in the field. However, our review also points out their limitations, such as difficulties with complex cases and potential underestimation of suicide risks.ConclusionEarly research in psychiatry reveals LLMs’ versatile applications, from diagnostic support to educational roles. Given the rapid pace of advancement, future investigations are poised to explore the extent to which these models might redefine traditional roles in mental health care.

BackgroundHeart rate variability (HRV) biofeedback is often performed with structured education, laboratory-based assessments, and practice sessions. It has been shown to improve psychological and physiological function across populations. However, a means to remotely use and monitor this approach would allow for wider use of this technique. Advancements in wearable and digital technology present an opportunity for the widespread application of this approach. ObjectiveThe primary aim of the study was to determine the feasibility of fully remote, self-administered short sessions of HRV-directed biofeedback in a diverse population of health care workers (HCWs). The secondary aim was to determine whether a fully remote, HRV-directed biofeedback intervention significantly alters longitudinal HRV over the intervention period, as monitored by wearable devices. The tertiary aim was to estimate the impact of this intervention on metrics of psychological well-being. MethodsTo determine whether remotely implemented short sessions of HRV biofeedback can improve autonomic metrics and psychological well-being, we enrolled HCWs across 7 hospitals in New York City in the United States. They downloaded our study app, watched brief educational videos about HRV biofeedback, and used a well-studied HRV biofeedback program remotely through their smartphone. HRV biofeedback sessions were used for 5 minutes per day for 5 weeks. HCWs were then followed for 12 weeks after the intervention period. Psychological measures were obtained over the study period, and they wore an Apple Watch for at least 7 weeks to monitor the circadian features of HRV. ResultsIn total, 127 HCWs were enrolled in the study. Overall, only 21 (16.5%) were at least 50% compliant with the HRV biofeedback intervention, representing a small portion of the total sample. This demonstrates that this study design does not feasibly result in adequate rates of compliance with the intervention. Numerical improvement in psychological metrics was observed over the 17-week study period, although it did not reach statistical significance (all P>.05). Using a mixed effect cosinor model, the mean midline-estimating statistic of rhythm (MESOR) of the circadian pattern of the SD of the interbeat interval of normal sinus beats (SDNN), an HRV metric, was observed to increase over the first 4 weeks of the biofeedback intervention in HCWs who were at least 50% compliant. ConclusionsIn conclusion, we found that using brief remote HRV biofeedback sessions and monitoring its physiological effect using wearable devices, in the manner that the study was conducted, was not feasible. This is considering the low compliance rates with the study intervention. We found that remote short sessions of HRV biofeedback demonstrate potential promise in improving autonomic nervous function and warrant further study. Wearable devices can monitor the physiological effects of psychological interventions.

IntroductionLittle is known about the relationship between moral distress and mental health problems. We examined moral distress in 2579 frontline healthcare workers (FHCWs) caring for coronavirus disease 2019 (COVID-19) patients during the height of the spring 2020 pandemic surge in New York City. The goals of the study were to identify common dimensions of COVID-19 moral distress; and to examine the relationship between moral distress, and positive screen for COVID-19-related posttraumatic stress disorder (PTSD) symptoms, burnout, and work and interpersonal functional difficulties.MethodData were collected in spring 2020, through an anonymous survey delivered to a purposively-selected sample of 6026 FHCWs at Mount Sinai Hospital; 2579 endorsed treating COVID-19 patients and provided complete survey responses. Physicians, house staff, nurses, physician assistants, social workers, chaplains, and clinical dietitians comprised the sample.ResultsThe majority of the sample (52.7%-87.8%) endorsed moral distress. Factor analyses revealed three dimensions of COVID-19 moral distress: negative impact on family, fear of infecting others, and work-related concerns. All three factors were significantly associated with severity and positive screen for COVID-19-related PTSD symptoms, burnout, and work and interpersonal difficulties. Relative importance analyses revealed that concerns about work competencies and personal relationships were most strongly related to all outcomes.ConclusionMoral distress is prevalent in FHCWs and includes family-, infection-, and work-related concerns. Prevention and treatment efforts to address moral distress during the acute phase of potentially morally injurious events may help mitigate risk for PTSD, burnout, and functional difficulties.