-
PloS One 2024This paper demonstrates how artificial-intelligence language analysis can inform understanding of human-nature relationships and other social phenomena. We demonstrate...
This paper demonstrates how artificial-intelligence language analysis can inform understanding of human-nature relationships and other social phenomena. We demonstrate three techniques by investigating relationships within the popular word2vec word embedding, which is trained on a sample from over 50,000 worldwide news sources. Our first technique investigates what theory-generated analogies are most similar to nature:people. The resource:user analogy is most similar, followed by the playground:child and gift:receiver analogies. Our second technique explores whether nature-related words are affiliated with words that denote race, class, or gender. Nature words tend slightly toward associations with femininity and wealth. Our third technique demonstrates how the relationship between nature and wellbeing compares to other concepts' relationships to wellbeing-e.g., spirituality-wellbeing, social relations-wellbeing. Nature is more semantically connected to wellbeing than money, social relations, and multiple other wellbeing correlates. Findings are consistent with previous social science and humanities research on human-nature relationships, but do not duplicate them exactly; our results thus offer insight into dominant trends and prevalence of associations. Our analysis also offers a model for using word embeddings to investigate a wide variety of topics.
Topics: Humans; Artificial Intelligence; Nature; Female; Male; Language
PubMed: 38885213
DOI: 10.1371/journal.pone.0297294 -
Annals of Surgery Open : Perspectives... Mar 2024We sought to determine if and how providers use elements of shared decision-making (SDM) in the care of surgical patients in the intensive care unit (ICU).
Is Everyone Beating Around the Bush?: A Qualitative Study Examining the Status of Shared Decision-Making Between Veterans Affairs Providers and Surgical Patients in the ICU.
OBJECTIVE
We sought to determine if and how providers use elements of shared decision-making (SDM) in the care of surgical patients in the intensive care unit (ICU).
BACKGROUND
SDM is the gold standard for decision-making in the ICU. However, it is unknown if this communication style is used in caring for critically ill surgical patients.
METHODS
Qualitative interviews were conducted with providers who provide ICU-level care to surgical patients in Veterans Affairs hospitals. Interviews were designed to examine end-of-life care among veterans who have undergone surgery and require ICU-level care.
RESULTS
Forty-eight providers across 14 Veterans Affairs hospitals were interviewed. These participants were diverse with respect to age, race, and sex. Participant dialogue was deductively mapped into 8 established SDM components: describing treatment options; determining roles in the decision-making process; fostering partnerships; health care professional preferences; learning about the patient; patient preferences; supporting the decision-making process; and tailoring the information. Within these components, participants shared preferred tools and tactics used to satisfy a given SDM component. Participants also noted numerous barriers to achieving SDM among surgical patients.
CONCLUSIONS
Providers use elements of SDM when caring for critically ill surgical patients. Additionally, this work identifies facilitators that can be leveraged and barriers that can be addressed to facilitate better communication and decision-making through SDM. These findings are of value for future interventions that seek to enhance SDM among surgical patients both in the ICU and in other settings.
PubMed: 38883948
DOI: 10.1097/AS9.0000000000000403 -
Research Square Jun 2024Permanent supportive housing (PSH) is an evidence-based practice for reducing homelessness that subsidizes permanent, independent housing and provides case...
BACKGROUND
Permanent supportive housing (PSH) is an evidence-based practice for reducing homelessness that subsidizes permanent, independent housing and provides case management-including linkages to health services. Substance use disorders (SUDs) are common contributing factors towards premature, unwanted ("negative") PSH exits; little is known about racial/ethnic differences in negative PSH exits among residents with SUDs. Within the nation's largest PSH program at the Department of Veterans Affairs (VA), we examined relationships among SUDs and negative PSH exits (for up to five years post-PSH move-in) across racial/ethnic subgroups.
METHODS
We used VA administrative data to identify a cohort of homeless-experienced Veterans (HEVs) (n = 2,712) who were housed through VA Greater Los Angeles' PSH program from 2016-2019. We analyzed negative PSH exits by HEVs with and without SUDs across racial/ethnic subgroups (i.e., African American/Black, Non-Hispanic White, Hispanic/Latino, and Other/Mixed [Asian, American Indian or Alaskan Native, and Native Hawaiian or Other Pacific Islander, and multi-race]) in controlled models and accounting for competing risk of death.
RESULTS
In competing risk models, HEVs with at least one SUD had 1.3 times the hazard of negative PSH exits compared to those without SUDs (95% CI: 1.00, 1.61). When stratifying by race/ethnicity, Other/Mixed race residents with at least one SUD had 6.4 times the hazard of negative PSH exits compared to their peers without SUDs (95% CI: 1.61-25.50). Hispanic/Latino residents with at least one SUD had 1.9 times the hazard compared to those without SUDs, also indicating a strong relationship with negative PSH exits; however, this association was not statistically significant (95% CI: 0.85-4.37). Black residents with at least one SUD had 1.2 times the hazard compared to those without SUDs (95% CI: 0.85-1.64), indicating no evidence of an association with negative PSH exits. Similarly, Non-Hispanic White residents with at least one SUD had 1.1 times the hazard compared to those without SUDs (95% CI: 0.75-1.66).
CONCLUSIONS
These findings suggest relationships between SUDs and negative PSH exits differ between race/ethnic groups and suggest there may be value in culturally specific tailoring and implementation of SUD services for these subgroups.
PubMed: 38883791
DOI: 10.21203/rs.3.rs-4442590/v1 -
MedRxiv : the Preprint Server For... Jun 2024Late predictions of hospitalized patient deterioration, resulting from early warning systems (EWS) with limited data sources and/or a care team's lack of shared...
IMPORTANCE
Late predictions of hospitalized patient deterioration, resulting from early warning systems (EWS) with limited data sources and/or a care team's lack of shared situational awareness, contribute to delays in clinical interventions. The COmmunicating Narrative Concerns Entered by RNs (CONCERN) Early Warning System (EWS) uses real-time nursing surveillance documentation patterns in its machine learning algorithm to identify patients' deterioration risk up to 42 hours earlier than other EWSs.
OBJECTIVE
To test our a priori hypothesis that patients with care teams informed by the CONCERN EWS intervention have a lower mortality rate and shorter length of stay (LOS) than the patients with teams not informed by CONCERN EWS.
DESIGN
One-year multisite, pragmatic controlled clinical trial with cluster-randomization of acute and intensive care units to intervention or usual-care groups.
SETTING
Two large U.S. health systems.
PARTICIPANTS
Adult patients admitted to acute and intensive care units, excluding those on hospice/palliative/comfort care, or with Do Not Resuscitate/Do Not Intubate orders.
INTERVENTION
The CONCERN EWS intervention calculates patient deterioration risk based on nurses' concern levels measured by surveillance documentation patterns, and it displays the categorical risk score (low, increased, high) in the electronic health record (EHR) for care team members.
MAIN OUTCOMES AND MEASURES
Primary outcomes: in-hospital mortality, LOS; survival analysis was used. Secondary outcomes: cardiopulmonary arrest, sepsis, unanticipated ICU transfers, 30-day hospital readmission.
RESULTS
A total of 60 893 hospital encounters (33 024 intervention and 27 869 usual-care) were included. Both groups had similar patient age, race, ethnicity, and illness severity distributions. Patients in the intervention group had a 35.6% decreased risk of death (adjusted hazard ratio [HR], 0.644; 95% confidence interval [CI], 0.532-0.778; P<.0001), 11.2% decreased LOS (adjusted incidence rate ratio, 0.914; 95% CI, 0.902-0.926; P<.0001), 7.5% decreased risk of sepsis (adjusted HR, 0.925; 95% CI, 0.861-0.993; P=.0317), and 24.9% increased risk of unanticipated ICU transfer (adjusted HR, 1.249; 95% CI, 1.093-1.426; P=.0011) compared with patients in the usual-care group.
CONCLUSIONS AND RELEVANCE
A hospital-wide EWS based on nursing surveillance patterns decreased in-hospital mortality, sepsis, and LOS when integrated into the care team's EHR workflow.
TRIAL REGISTRATION
ClinicalTrials.gov Identifier: NCT03911687 https://clinicaltrials.gov/ct2/show/NCT03911687.
KEY POINTS
Do patients whose care team receive the CONCERN Early Warning System (EWS) intervention have a lower mortality rate and shorter length of stay than patients in the usual-care group? In this multisite, pragmatic cluster-randomized controlled clinical trial that included 60 893 hospital patient encounters, patients whose care team received the CONCERN EWS intervention had a 35.6% decreased risk of death and 11.2% shorter length of stay compared with those in the usual-care group. A machine learning-based EWS modeled on nursing surveillance patterns significantly decreased the risk of inpatient deterioration events.
PubMed: 38883706
DOI: 10.1101/2024.06.04.24308436 -
Factors associated with incomplete resection for large, locally invasive non-small cell lung cancer.Journal of Thoracic Disease May 2024Large, node-negative but locally invasive non-small cell lung cancer (NSCLC) is associated with increased perioperative risk but improved survival if a complete...
BACKGROUND
Large, node-negative but locally invasive non-small cell lung cancer (NSCLC) is associated with increased perioperative risk but improved survival if a complete resection is obtained. Factors associated with positive margins in this population are not well-studied.
METHODS
We performed a retrospective cohort study using National Cancer Database (NCDB) for adult patients with >5 cm, clinically node-negative NSCLC with evidence of invasion of nearby structures [2006-2015]. Patients were classified as having major structure involvement (azygous vein, pulmonary artery/vein, vena cava, carina/trachea, esophagus, recurrent laryngeal/vagus nerve, heart, aorta, vertebrae) or chest wall invasion (rib pleura, chest wall, diaphragm). Our primary outcome was to evaluate factors associated with incomplete resection (microscopic: R1, macroscopic: R2). Kaplan-Meier analysis and cox multivariable regression models were used to evaluate overall survival (OS), 90-day mortality, and factors associated with positive margins.
RESULTS
Among 2,368 patients identified, the median follow-up was 33.8 months [interquartile range (IQR), 12.6-66.5 months]. Most patients were white (86.9%) with squamous cell histology (47.3%). Major structures were involved in 26.4% of patients and chest wall invasion was seen in 73.6%. Four hundred and seventy-eight patients (20.2%) had an incomplete resection. Multivariable analysis revealed that black race [hazard ratio (HR) 1.568, 95% confidence interval (CI): 1.109-2.218] and major structure involvement (HR 1.412, 95% CI: 1.091-1.827) was associated with increased risk of incomplete resection and surgery at an academic hospitals (HR 0.773, 95% CI: 0.607-0.984), adenocarcinoma histology (HR 0.672, 95% CI: 0.514-0.878), and neoadjuvant chemotherapy (HR 0.431, 95% CI: 0.316-0.587) were associated with decreased risk of incomplete resection. The 5-year OS was 43.7% in the entire cohort and 28.8% in patients with positive margins and 47.5% in patients with an R0 resection. Positive margin was also associated with a significantly higher 90-day mortality rate (9.9% versus 6.7%).
CONCLUSIONS
For patients with large, node-negative NSCLC invading nearby structures, R0 resection portends better survival. Treatment at academic centers, adenocarcinoma histology, and receipt of neoadjuvant chemotherapy are associated with R0 resection in this high-risk cohort.
PubMed: 38883676
DOI: 10.21037/jtd-23-989 -
American Journal of Men's Health 2024Men aged 27 to 45 are eligible for human papillomavirus (HPV) vaccination as of 2019, yet relatively little is known about whether they have received or intend to...
Men aged 27 to 45 are eligible for human papillomavirus (HPV) vaccination as of 2019, yet relatively little is known about whether they have received or intend to receive it. We conducted a cross-sectional, online survey among fathers aged 27 to 45 between March and April 2022, to assess associations between HPV vaccination awareness, behaviors, intentions, and psychosocial constructs from the Health Belief Model. We examined the characteristics of those who had (a) heard of the HPV vaccine, (b) already received ≥ 1 dose, and (c) intentions for future vaccination among those who had never been vaccinated. Among 400 men who completed the survey, 32% were not aware of the HPV vaccine. Among those who were aware, 41% had received ≥ 1 dose. Sixty-three percent of unvaccinated men reported that they intended to get vaccinated in the future. Multivariable logistic regression analyses revealed that age and race/ethnicity were associated with having been vaccinated previously. Among the unvaccinated, multivariable logistic regression analyses revealed that those with a higher perceived risk of HPV-associated cancer had 3.73 greater odds of reporting they would seek vaccination compared to those with lower perceived risk (95% confidence interval [CI] = [1.28, 12.3]). We did not find perceived benefits, barriers, or decision self-efficacy to be related to future vaccine intentions. Since recommendations for this group include shared clinical decision-making, public health efforts should focus on raising awareness of vaccine eligibility, emphasizing risk factors for HPV-associated cancers so that individuals have an accurate perception of risk, and encouraging conversation between men and their providers.
Topics: Humans; Male; Papillomavirus Vaccines; Adult; Cross-Sectional Studies; Middle Aged; Fathers; Health Knowledge, Attitudes, Practice; Intention; Papillomavirus Infections; Surveys and Questionnaires; Vaccination
PubMed: 38879825
DOI: 10.1177/15579883241258823 -
Scientific Reports Jun 2024Recent advancements in machine learning and deep learning have revolutionized various computer vision applications, including object detection, tracking, and...
Recent advancements in machine learning and deep learning have revolutionized various computer vision applications, including object detection, tracking, and classification. This research investigates the application of deep learning for cattle lameness detection in dairy farming. Our study employs image processing techniques and deep learning methods for cattle detection, tracking, and lameness classification. We utilize two powerful object detection algorithms: Mask-RCNN from Detectron2 and the popular YOLOv8. Their performance is compared to identify the most effective approach for this application. Bounding boxes are drawn around detected cattle to assign unique local IDs, enabling individual tracking and isolation throughout the video sequence. Additionally, mask regions generated by the chosen detection algorithm provide valuable data for feature extraction, which is crucial for subsequent lameness classification. The extracted cattle mask region values serve as the basis for feature extraction, capturing relevant information indicative of lameness. These features, combined with the local IDs assigned during tracking, are used to compute a lameness score for each cattle. We explore the efficacy of various established machine learning algorithms, such as Support Vector Machines (SVM), AdaBoost and so on, in analyzing the extracted lameness features. Evaluation of the proposed system was conducted across three key domains: detection, tracking, and lameness classification. Notably, the detection module employing Detectron2 achieved an impressive accuracy of 98.98%. Similarly, the tracking module attained a high accuracy of 99.50%. In lameness classification, AdaBoost emerged as the most effective algorithm, yielding the highest overall average accuracy (77.9%). Other established machine learning algorithms, including Decision Trees (DT), Support Vector Machines (SVM), and Random Forests, also demonstrated promising performance (DT: 75.32%, SVM: 75.20%, Random Forest: 74.9%). The presented approach demonstrates the successful implementation for cattle lameness detection. The proposed system has the potential to revolutionize dairy farm management by enabling early lameness detection and facilitating effective monitoring of cattle health. Our findings contribute valuable insights into the application of advanced computer vision methods for livestock health management.
Topics: Animals; Cattle; Lameness, Animal; Cattle Diseases; Algorithms; Support Vector Machine; Image Processing, Computer-Assisted; Deep Learning; Machine Learning; Video Recording
PubMed: 38877097
DOI: 10.1038/s41598-024-64664-7 -
American Journal of Preventive Medicine Jun 2024Youth experience significant mental health (MH) needs, and gender- and racially/ethnically-diverse youth are less likely than peers to receive care. School-based health...
INTRODUCTION
Youth experience significant mental health (MH) needs, and gender- and racially/ethnically-diverse youth are less likely than peers to receive care. School-based health centers (SBHCs) are a healthcare delivery model that may decrease disparities. This study examined the role of SBHCs in reducing disparities in MH care receipt among SBHC clients.
METHODS
Data from electronic health records of 5,396 youth ages 12 to 21 years who visited 14 SBHCs in one California county from 2021-2023 were analyzed in 2023-2024 using multiple logistic regression to assess disparities in MH care receipt and depression screenings.
RESULTS
Receipt of MH care from SBHCs varied significantly by gender but not age, sexual orientation, or race/ethnicity. Compared to female clients, males had reduced odds (AOR: 0.50) and gender-diverse clients had higher odds (AOR: 2.70) of receiving MH care. For receipt of depression screenings, male clients had reduced odds (AOR: 0.86); Latino clients had higher odds than white clients (AOR: 1.80); and older adolescents and young adults had higher odds than younger adolescents (AORs: 1.44 and 1.45, respectively). Receipt of follow-up MH care after a positive depression result varied only by gender, with male clients having reduced odds (AOR: 0.63).
CONCLUSIONS
SBHCs may reach youth who are traditionally less likely to seek care in other settings, including racially/ethnically- and gender-diverse youth. As in other settings, engaging males in healthcare is an area for improvement. These findings help to demonstrate the potential of SBHCs for decreasing disparities in mental health care.
PubMed: 38876296
DOI: 10.1016/j.amepre.2024.06.004 -
Revista Brasileira de Psiquiatria (Sao... Jun 2024This is the first part of two documents prepared by experts for the Brazilian S20 mental health report. These reports outline strategies aimed at addressing the...
This is the first part of two documents prepared by experts for the Brazilian S20 mental health report. These reports outline strategies aimed at addressing the exacerbated mental health challenges arising from a post-pandemic world. Ongoing psychiatric epidemiology research has yielded evidence linking mental health with intricate social determinants, including gender, race/ethnicity, racism, socioeconomic status, social deprivation, and employment, among others. More recently, the focus has expanded to also encompass violence and social oppression. By prioritizing prevention and early intervention, harnessing technology, and fostering community support, we can mitigate the long-term impact of mental disorders emerging in life. Utilizing evidence-based practices and forging partnerships between the health and education sectors, S20 countries can promote health and safety of their student population, thereby paving the way for a more promising future for the next generations. The first document focuses on addressing the mental health concerns of vulnerable populations, catering to the needs of children, youth, and aging populations, assessing the current state of alcohol and drug addictions, scaling up psychosocial interventions in primary care, exploring the potential integration of health and educational systems, and emphasizing the imperative adoption of human rights in mental health policies.
PubMed: 38874935
DOI: 10.47626/1516-4446-2024-3706 -
JAMA Network Open Jun 2024Little nationally representative research has examined Papanicolaou testing rates from before the pandemic in 2019 through the COVID-19 pandemic in 2022. Papanicolaou...
IMPORTANCE
Little nationally representative research has examined Papanicolaou testing rates from before the pandemic in 2019 through the COVID-19 pandemic in 2022. Papanicolaou testing rates among rural females are a concern as they have historically had lower screening rates than their urban counterparts.
OBJECTIVE
To examine the receipt of a Papanicolaou test in the past year among US females overall and females residing in rural and urban areas in 2019, 2020, and 2022.
DESIGN, SETTING, AND PARTICIPANTS
This repeated cross-sectional study used data from 3 years of the Health Information National Trends Survey (HINTS), a nationally representative survey that asks respondents about cancer screenings, sources of health information, and health and health care technologies. Study participants were females aged 21 to 65 years. Individuals who received a Papanicolaou test more than 1 to 3 years prior to a HINTS interview were excluded as they were likely not due for a Papanicolaou test.
EXPOSURES
Survey year (2019, 2020, and 2022) and rural or urban residence were the main exposure variables.
MAIN OUTCOMES AND MEASURES
Self-reported receipt of a Papanicolaou test within the past year.
RESULTS
Among the 188 243 531 (weighted; 3706 unweighted) females included in the analysis, 12.5% lived in rural areas and 87.5% in urban areas. Participants had a mean (SE) age of 43.7 (0.27) years and were of Hispanic (18.8%), non-Hispanic Asian (5.2%), non-Hispanic Black (12.2%), non-Hispanic White (59.6%), or non-Hispanic other (4.1%) race and ethnicity. In 2022, unadjusted past-year Papanicolaou testing rates were significantly lower among rural vs urban residents (48.6% [95% CI, 39.2%-58.1%] vs 64.0% [95% CI, 60.0%-68.0%]; P < .001). Adjusted odds of past-year Papanicolaou testing were lower in 2022 than 2019 (odds ratio, 0.70; 95% CI, 0.52-0.95; P = .02).
CONCLUSIONS AND RELEVANCE
This repeated cross-sectional study found that past-year Papanicolaou testing rates were lower in 2022 than 2019, pointing to a need to increase access to screenings to prevent an uptick in cervical cancer incidence. Rural-vs-urban differences in 2022 indicate a need to specifically target rural females.
Topics: Humans; Female; Uterine Cervical Neoplasms; Middle Aged; Adult; Early Detection of Cancer; Cross-Sectional Studies; Rural Population; Papanicolaou Test; Urban Population; Aged; United States; COVID-19; Young Adult; Vaginal Smears; SARS-CoV-2
PubMed: 38874926
DOI: 10.1001/jamanetworkopen.2024.17094