Artificial intelligence-generated feedback on social signals in patient-provider communication: technical performance, feedback usability, and impact.

Objectives: Implicit bias perpetuates health care inequities and manifests in patient-provider interactions, particularly nonverbal social cues like dominance. We investigated the use of artificial intelligence (AI) for automated communication assessment and feedback during primary care visits to raise clinician awareness of bias in patient interactions. Materials and Methods: (1) Assessed the technical performance of our AI models by building a machine-learning pipeline that automatically detects social signals in patient-provider interactions from 145 primary care visits. (2) Engaged 24 clinicians to design usable AI-generated communication feedback for their workflow. (3) Evaluated the impact of our AI-based approach in a prospective cohort of 108 primary care visits. Results: Findings demonstrate the feasibility of AI models to identify social signals, such as dominance, warmth, engagement, and interactivity, in nonverbal patient-provider communication. Although engaged clinicians preferred feedback delivered in personalized dashboards, they found nonverbal cues difficult to interpret, motivating social signals as an alternative feedback mechanism. Impact evaluation demonstrated fairness in all AI models with better generalizability of provider dominance, provider engagement, and patient warmth. Stronger clinician implicit race bias was associated with less provider dominance and warmth. Although clinicians expressed overall interest in our AI approach, they recommended improvements to enhance acceptability, feasibility, and implementation in telehealth and medical education contexts. Discussion and Conclusion: Findings demonstrate promise for AI-driven communication assessment and feedback systems focused on social signals. Future work should improve the performance of this approach, personalize models, and contextualize feedback, and investigate system implementation in educational workflows. This work exemplifies a systematic, multistage approach for evaluating AI tools designed to raise clinician awareness of implicit bias and promote patient-centered, equitable health care interactions.

Beyond the here and now: hunter-gatherer socio-spatial complexity and the evolution of language.

Human evolutionary ecology stands to benefit by integrating theory and methods developed in movement ecology, and in turn, to make contributions to the broader field of movement ecology by leveraging our species' distinct attributes. In this paper, we review data and evolutionary models suggesting that major changes in socio-spatial behaviour accompanied the evolution of language. To illustrate and explore these issues, we present a comparison of GPS measures of the socio-spatial behaviour of Hadza hunter-gatherers of northern Tanzania to those of olive baboons (Papio anubis), a comparatively small-brained primate that is also savanna-adapted. While standard spatial metrics show modest differences, measures of spatial diversity, landscape exploration and spatiotemporal displacement between individuals differ markedly. Groups of Hadza foragers rapidly accumulate a vast, diverse knowledge pool about places and things over the horizon, contrasting with the baboon's narrower and more homogeneous pool of ecological information. The larger and more complex socio-spatial world illustrated by the Hadza is one where heightened cognitive abilities for spatial and episodic memory, navigation, perspective taking and communication about things beyond the here and now all have clear value.This article is part of the theme issue 'The spatial-social interface: a theoretical and empirical integration'.

Hadza Landscape Burning.

We present the first published ethnographic description of landscape burning by Hadza hunter-gatherers of northern Tanzania and identify environmental, social, and cultural influences on Hadza landscape burning, thereby broadening the ethnographic record of anthropogenic burning practices described for hunter-gatherer communities. We report interview data collected in 2022 and 2023, describing their practices and attitudes regarding the causes and consequences of burning. We provide context by comparing our observations with those recorded for hunting and gathering populations in Africa, Australia, and North America. Hadza landscape burning is generally a solitary and male-dominated activity, contrary to ethnographic accounts of Indigenous landscape burning from North America and Australia. The primary goals stated by Hadza for landscape burning were improved hunting, reduced hazards from dangerous animals, and to reduce the density of livestock. Firsthand observations suggest that landscape burning has decreased over the past 20 years, and this historical trend is supported by interviews. Satellite imagery also suggests an overall decrease in burning activity in the region from 2001 to 2022. Among the Hadza, landscape burning is a culturally influenced and strongly gender-biased activity that is rapidly disappearing. Because burning can radically transform landscapes, these practices often generate or amplify conflicts of interest between groups with different land use strategies. Hadza report serious social conflict with pastoralists over landscape burning, and our study suggests this tension has constrained the practice in the past two decades.

Interhospital variability in hospital admissions for patients with low-risk syncope presenting to the emergency department.

Background: Guidelines and risk scores have sought to standardize the management of syncope in the emergency department (ED), but variation in practice remains. Objective: The purpose of this study was to explore factors associated with admission for patients presenting to the ED with low-risk syncope. Methods: Our study population included adult patients in the Nationwide Emergency Department Sample between 2006 and 2019 who presented to an ED with a primary diagnosis of syncope. Multivariable hierarchical logistic regression analyses determined the association of patient or hospital factors with admission. Reference effect measures methodology assessed the relative contributions of patient, hospital, and unmeasured hospital factors. Results: Of the 3,206,739 qualifying encounters during the study period, 804,398 (25.1%) met low-risk criteria. Of these patients, 20,260 were admitted to the hospital (2.5%). Factors associated with increased odds of admission included increasing age and weekend presentation to the hospital, while female sex, lack of medical insurance, hospital region, teaching status, and higher ED volume decile were associated with lower odds of admission. Reference effect measures methodology demonstrated that unmeasured site variability contributed the widest range of odds for admission (odds ratio [OR] 5th percentile vs 95th percentile 0.23-4.38) compared with the composite patient (OR 0.33-3.68) or hospital (OR 0.65-1.30) factors. Conclusion: Admission patterns for low-risk syncope varies widely across institutions. Unmeasured site variation contributes significantly to the variability in admission rates, suggesting which hospital a patient presents to plays a disproportionate role in admission decisions. Further guidance to reduce practice variation in syncope care in the ED is needed.

ConverSense: An Automated Approach to Assess Patient-Provider Interactions using Social Signals.

Patient-provider communication influences patient health outcomes, and analyzing such communication could help providers identify opportunities for improvement, leading to better care. Interpersonal communication can be assessed through "social-signals" expressed in non-verbal, vocal behaviors like interruptions, turn-taking, and pitch. To automate this assessment, we introduce a machine-learning pipeline that ingests audio-streams of conversations and tracks the magnitude of four social-signals: dominance, interactivity, engagement, and warmth. This pipeline is embedded into ConverSense, a web-application for providers to visualize their communication patterns, both within and across visits. Our user study with 5 clinicians and 10 patient visits demonstrates ConverSense's potential to provide feedback on communication challenges, as well as the need for this feedback to be contextualized within the specific underlying visit and patient interaction. Through this novel approach that uses data-driven self-reflection, ConverSense can help providers improve their communication with patients to deliver improved quality of care.

Designing Communication Feedback Systems To Reduce Healthcare Providers' Implicit Biases In Patient Encounters.

Healthcare providers' implicit bias, based on patients' physical characteristics and perceived identities, negatively impacts healthcare access, care quality, and outcomes. Feedback tools are needed to help providers identify and learn from their biases. To incorporate providers' perspectives on the most effective ways to present such feedback, we conducted semi-structured design critique sessions with 24 primary care providers. We found that providers seek feedback designed with transparent metrics indicating the quality of their communication with a patient and trends in communication patterns across visits. Based on these metrics and trends, providers want this feedback presented in a dashboard paired with actionable, personalized tips about how to improve their communication behaviors. Our study provides new insights for interactive systems to help mitigate the impact of implicit biases in patient-provider communication. New systems that build upon these insights could support providers in making healthcare more equitable, particularly for patients from marginalized communities.

Impact of EASO/ESPEN-Defined Sarcopenic Obesity Following a Technology-Based Weight Loss Intervention.

BACKGROUND: Sarcopenic Obesity is the co-existence of increased adipose tissue (obesity) and decreased muscle mass or strength (sarcopenia) and is associated with worse outcomes than obesity alone. The new EASO/ESPEN consensus provides a framework to standardize its definition. This study sought to evaluate whether there are preliminary differences observed in weight loss or physical function in older adults with and without sarcopenic obesity taking part in a multicomponent weight loss intervention using these new definitions. METHODS: A 6-month, non-randomized, non-blinded, single-arm pilot study was conducted from 2018 to 2020 in adults ≥ 65 years with a body mass index (BMI) ≥ 30 kg/m2. Weekly dietitian visits and twice-weekly physical therapist-led exercise classes were delivered using telemedicine. We conducted a secondary retrospective analysis of the parent study (n = 53 enrolled, n = 44 completers) that investigated the feasibility of a technology-based weight management intervention in rural older adults with obesity. Herein, we applied five definitions of sarcopenic obesity (outlined in the consensus) to ascertain whether the response to the intervention differed among those with and without sarcopenic obesity. Primary outcomes evaluated included weight loss and physical function (30-s sit-to-stand). RESULTS: In the parent study, mean weight loss was - 4.6 kg (95% CI - 3.6, - 5.6; p < 0.001). Physical function measures of 30-s sit-to-stand showed a mean increase of 3.1 in sit-to-stand repetitions (+ 1.9, + 4.3; p < 0.001). In this current analysis, there was a significant decrease in weight and an increase in repetitions between baseline and follow-up within each group of individuals with and without sarcopenia for each of the proposed definitions. However, we did not observe any significant differences in the changes between groups from baseline to follow-up. CONCLUSIONS: The potential lack of significant differences in weight loss or physical function between older adults with and without sarcopenic obesity participating in a weight loss intervention may suggest that well-designed, multicomponent interventions can lead to similar outcomes irrespective of sarcopenia status in persons with obesity. Fully powered randomized clinical trials are critically needed to confirm these preliminary results.

Culturally determined interspecies communication between humans and honeyguides.

Species interactions that vary across environments can create geographical mosaics of genetic coevolution. However, traits mediating species interactions are sometimes culturally inherited. Here we show that traditions of interspecies communication between people and wild birds vary in a culturally determined geographical mosaic. Honey hunters in different parts of Africa use different calls to communicate with greater honeyguides (Indicator indicator) that lead them to bees' nests. We show experimentally that honeyguides in Tanzania and Mozambique discriminate among honey hunters' calls, responding more readily to local than to foreign calls. This was not explained by variation in sound transmission and instead suggests that honeyguides learn local human signals. We discuss the forces stabilizing and diversifying interspecies communication traditions, and the potential for cultural coevolution between species.

Demographic and hormonal evidence for menopause in wild chimpanzees.

Among mammals, post-reproductive life spans are currently documented only in humans and a few species of toothed whales. Here we show that a post-reproductive life span exists among wild chimpanzees in the Ngogo community of Kibale National Park, Uganda. Post-reproductive representation was 0.195, indicating that a female who reached adulthood could expect to live about one-fifth of her adult life in a post-reproductive state, around half as long as human hunter-gatherers. Post-reproductive females exhibited hormonal signatures of menopause, including sharply increasing gonadotropins after age 50. We discuss whether post-reproductive life spans in wild chimpanzees occur only rarely, as a short-term response to favorable ecological conditions, or instead are an evolved species-typical trait as well as the implications of these alternatives for our understanding of the evolution of post-reproductive life spans.

Lifestyle and patterns of physical activity in Hadza foragers.

OBJECTIVES: Physically active lifestyles are associated with several health benefits. Physical activity (PA) levels are low in post-industrial populations, but generally high throughout life in subsistence populations. The Hadza are a subsistence-oriented foraging population in Tanzania known for being physically active, but it is unknown how recent increases in market integration may have altered their PA patterns. In this study, we examine PA patterns for Hadza women and men who engage in different amounts of traditional foraging. MATERIALS AND METHODS: One hundred and seventy seven Hadza participants (51% female, 19-87 years) wore an Axivity accelerometer (dominant wrist) for ~6 days during dry season months. We evaluated the effects of age, sex, and lifestyle measures on four PA measures that capture different aspects of the PA profile. RESULTS: Participants engaged in high levels of both moderate-intensity PA and inactivity. Although PA levels were negatively associated with age, older participants were still highly active. We found no differences in PA between participants living in more traditional "bush" camps and those living in more settled "village" camps. Mobility was positively associated with step counts for female participants, and schooling was positively associated with inactive time for male participants. CONCLUSIONS: The similarity in PA patterns between Hadza participants in different camp types suggests that high PA levels characterize subsistence lifestyles generally. The sex-based difference in the effects of mobility and schooling on PA could be a reflection of the Hadza's gender-based division of labor, or indicate that changes to subsistence-oriented lifestyles impact women and men in different ways.

Therapy for HIV-associated cryptococcal meningitis: a case report demonstrating a new treatment approach emphasizing updated treatment guidelines.

Cryptococcal meningitis (CM) remains a significant global health burden, especially for persons living with HIV. Despite effective antiretroviral and antifungal therapy, mortality rates are still approximately 70% in low- and middle-income countries and 20-30% in high-income countries. Central nervous system symptoms range from mild to severe, depending on burden of disease, and prompt and appropriate therapy is critical to reducing mortality. Treatment consists of three phases: induction, consolidation, and maintenance. Although treatment regimens have largely remained unchanged for decades, recent clinical trials have led the World Health Organization to update guidelines to reflect best practices in resource-limited settings. We review the clinical presentation, diagnosis, and standard therapy for CM, present a case with a challenging diagnostic and treatment course complicated by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic, and discuss the benefits of a new treatment dosing strategy highlighting potential advantages of adopting this novel dosing option in high-income countries.

Energetic costs of testosterone in two subsistence populations.

OBJECTIVE: Testosterone plays a role in mediating energetic trade-offs between growth, maintenance, and reproduction. Investments in a high testosterone phenotype trade-off against other functions, particularly survival-enhancing immune function and cellular repair; thus only individuals in good condition can maintain both a high testosterone phenotype and somatic maintenance. While these effects are observed in experimental manipulations, they are difficult to demonstrate in free-living animals, particularly in humans. We hypothesize that individuals with higher testosterone will have higher energetic expenditures than those with lower testosterone. METHODS: Total energetic expenditure (TEE) was quantified using doubly labeled water in n = 40 Tsimane forager-horticulturalists (50% male, 18-87 years) and n = 11 Hadza hunter-gatherers (100% male, 18-65 years), two populations living subsistence lifestyles, high levels of physical activity, and high infectious burden. Urinary testosterone, TEE, body composition, and physical activity were measured to assess potential physical and behavioral costs associated with a high testosterone phenotype. RESULTS: Endogenous male testosterone was significantly associated with energetic expenditure, controlling for fat free mass; a one standard deviation increase in testosterone is associated with the expenditure of an additional 96-240 calories per day. DISCUSSION: These results suggest that a high testosterone phenotype, while beneficial for male reproduction, is also energetically expensive and likely only possible to maintain in healthy males in robust condition.

Reproductive inequality in humans and other mammals.

To address claims of human exceptionalism, we determine where humans fit within the greater mammalian distribution of reproductive inequality. We show that humans exhibit lower reproductive skew (i.e., inequality in the number of surviving offspring) among males and smaller sex differences in reproductive skew than most other mammals, while nevertheless falling within the mammalian range. Additionally, female reproductive skew is higher in polygynous human populations than in polygynous nonhumans mammals on average. This patterning of skew can be attributed in part to the prevalence of monogamy in humans compared to the predominance of polygyny in nonhuman mammals, to the limited degree of polygyny in the human societies that practice it, and to the importance of unequally held rival resources to women's fitness. The muted reproductive inequality observed in humans appears to be linked to several unusual characteristics of our species-including high levels of cooperation among males, high dependence on unequally held rival resources, complementarities between maternal and paternal investment, as well as social and legal institutions that enforce monogamous norms.

A Multidisciplinary Approach for the Management of Portal Vein Thrombosis.

Portal venous thrombosis (PVT) is an uncommon disease associated with highly morbid conditions such as intestinal ischemia and portal hypertension. Patients at higher risk of developing PVT include those with cirrhosis, malignancy, or prothrombotic states. The mainstay of treatment is early initiation of anticoagulation. The first case is a 49-year-old female diagnosed with a cecal mass and PVT. She was started on anticoagulation and underwent a right hemicolectomy with several small bowel resections. She developed portal hypertension that required TIPS and mechanical thrombectomy. The second patient is a 65-year-old female found to have PVT. She was anticoagulated with heparin and given systemic TPA. She developed intestinal ischemia and portal hypertension requiring small bowel resection, TIPS, and mechanical thrombectomy. These cases give insight into the impact of a multidisciplinary team approach to PVT. The role and timing of endovascular treatment is not well established and needs to be further investigated.

Integrating patient voices into the extraction of social determinants of health from clinical notes: ethical considerations and recommendations.

Identifying patients' social needs is a first critical step to address social determinants of health (SDoH)-the conditions in which people live, learn, work, and play that affect health. Addressing SDoH can improve health outcomes, population health, and health equity. Emerging SDoH reporting requirements call for health systems to implement efficient ways to identify and act on patients' social needs. Automatic extraction of SDoH from clinical notes within the electronic health record through natural language processing offers a promising approach. However, such automated SDoH systems could have unintended consequences for patients, related to stigma, privacy, confidentiality, and mistrust. Using Floridi et al's "AI4People" framework, we describe ethical considerations for system design and implementation that call attention to patient autonomy, beneficence, nonmaleficence, justice, and explicability. Based on our engagement of clinical and community champions in health equity work at University of Washington Medicine, we offer recommendations for integrating patient voices and needs into automated SDoH systems.