-
Journal For Immunotherapy of Cancer May 2024Artificial intelligence (AI) chatbots have become a major source of general and medical information, though their accuracy and completeness are still being assessed....
BACKGROUND
Artificial intelligence (AI) chatbots have become a major source of general and medical information, though their accuracy and completeness are still being assessed. Their utility to answer questions surrounding immune-related adverse events (irAEs), common and potentially dangerous toxicities from cancer immunotherapy, are not well defined.
METHODS
We developed 50 distinct questions with answers in available guidelines surrounding 10 irAE categories and queried two AI chatbots (ChatGPT and Bard), along with an additional 20 patient-specific scenarios. Experts in irAE management scored answers for accuracy and completion using a Likert scale ranging from 1 (least accurate/complete) to 4 (most accurate/complete). Answers across categories and across engines were compared.
RESULTS
Overall, both engines scored highly for accuracy (mean scores for ChatGPT and Bard were 3.87 vs 3.5, p<0.01) and completeness (3.83 vs 3.46, p<0.01). Scores of 1-2 (completely or mostly inaccurate or incomplete) were particularly rare for ChatGPT (6/800 answer-ratings, 0.75%). Of the 50 questions, all eight physician raters gave ChatGPT a rating of 4 (fully accurate or complete) for 22 questions (for accuracy) and 16 questions (for completeness). In the 20 patient scenarios, the average accuracy score was 3.725 (median 4) and the average completeness was 3.61 (median 4).
CONCLUSIONS
AI chatbots provided largely accurate and complete information regarding irAEs, and wildly inaccurate information ("hallucinations") was uncommon. However, until accuracy and completeness increases further, appropriate guidelines remain the gold standard to follow.
Topics: Humans; Artificial Intelligence; Immunotherapy; Neoplasms; Drug-Related Side Effects and Adverse Reactions
PubMed: 38816231
DOI: 10.1136/jitc-2023-008599 -
BMJ Open May 2024Prevention of necrotising enterocolitis (NEC) is vital for improving neonatal outcomes. Feeding own mother's milk helps prevent NEC. Rates of own mother's milk feeding...
Effects of implementation of a care bundle on rates of necrotising enterocolitis and own mother's milk feeding in the East Midlands: protocol for a mixed methods impact and process evaluation study.
INTRODUCTION
Prevention of necrotising enterocolitis (NEC) is vital for improving neonatal outcomes. Feeding own mother's milk helps prevent NEC. Rates of own mother's milk feeding in the East Midlands are lower than the national average and the incidence of NEC is higher. The East Midlands Neonatal Operational Delivery Network (EMNODN) has created a care bundle to improve these in babies born at <32 weeks' gestation, the group at the highest risk of NEC. The bundle was introduced in September 2022 and embedded by December 2022. We will evaluate its effectiveness and conduct a process evaluation to understand barriers and facilitators to implementation.
METHODS AND ANALYSIS
We will conduct a retrospective cohort study (workstream 1) using data from the National Neonatal Research Database (NNRD). We will identify infants receiving any own mother's milk on day 14 and at discharge, and cases of severe NEC. We will aggregate outcomes by birth month and use interrupted time series analysis to estimate an incidence rate ratio for changes after the care bundle was embedded, relative to pre-implementation. We will model data from all other NNRD units and assess whether there are any concurrent changes to exclude confounding due to other events.We will apply the RE-AIM framework (workstream 2), supplemented by the Consolidated Framework for Implementation Research and Framework for Implementation Fidelity, to conduct a mixed methods evaluation in EMNODN units. We will triangulate data from several sources, including questionnaires and semistructured interviews with parents and healthcare professionals, and data from patient records.
ETHICS AND DISSEMINATION
The study has approval from the South East Scotland Research Ethics Committee 01 and the Health Research Authority and Health and Care Research Wales (IRAS 323099). Results will be disseminated via scientific journals and conferences, to neonatal service commissioners and through public-facing infographics.
TRIAL REGISTRATION NUMBER
NCT05934123.
Topics: Enterocolitis, Necrotizing; Humans; Infant, Newborn; Retrospective Studies; Patient Care Bundles; Female; Milk, Human; Breast Feeding; Infant, Premature; Research Design; Incidence
PubMed: 38816042
DOI: 10.1136/bmjopen-2023-078633 -
BMJ Open Quality May 2024Previous work found referrals for end-of-life care are made late in the dying process and assessment processes for care funding, through continuing healthcare fast-track...
Previous work found referrals for end-of-life care are made late in the dying process and assessment processes for care funding, through continuing healthcare fast-track funding often inhibit people being able to die at home. The average time to discharge was 6.3 days and 29% died in hospital, as median survival was only 15 days.We aimed to support discharge to home within 1 day by December 2023 for patients, wishing to die at home, referred to the end-of-life discharge team in a medium-sized district general hospital in Southwest England.In phase 1, we identified 13 people on a patient-by-patient basis, learning from obstacles. Barriers identified included sourcing of equipment, communication between teams and clunky paperwork. Median time to discharge was 2 days (range within 24 hours to 8 days) with 2/13 (15.4%) dying prior to discharge. In phase 2, we extended the pilot, and 104 patients were identified; 94 people were discharged to home, with a median of wait of 1 day (range 0-7) to discharge, and 10 (9.6%) died prior to discharge (median 1 day; range 0-4). Median survival from discharge for the 94 who achieved their wishes to go home to die was 9 days (range 1-205 days). Only 26/94 (27.7%) people survived more than 30 days.Rapid decision-making and structures to support home-based end-of-life care can support more people to die in their preferred place of care, by using a community-based rapid response team instead of, or in parallel with continuing healthcare fast-track funding referral applications. Current pathways and funding models are not fit for purpose in an urgent care scenario when we have only one chance to get it right.
Topics: Humans; Terminal Care; Quality Improvement; Home Care Services; Female; England; Male; Aged; Aged, 80 and over; Middle Aged; Patient Discharge
PubMed: 38816007
DOI: 10.1136/bmjoq-2024-002790 -
Journal of the International... 2024Recent studies have shown social determinants of health (SDOH) to impact HIV care engagement. This cross-sectional study (Oct 20-Apr 21) assessed the impact of a range...
Recent studies have shown social determinants of health (SDOH) to impact HIV care engagement. This cross-sectional study (Oct 20-Apr 21) assessed the impact of a range of SDOH on HIV care engagement using data from HIV Care Connect, a consortium of three HIV care facility-led programs (Alabama, Florida, Mississippi). The exposures were captured using the PRAPARE (Protocol for Responding to and Assessing Patient Assets, Risks, and Experiences) scale. The outcome was captured using the Index of Engagement in HIV Care scale. Participants (n = 132) were predominantly non-White (87%) and male (52%) with a median age of 41 years. Multivariable logistic regression adjusted for various sociodemographics showed lower HIV care engagement to be associated with being uninsured/publicly insured, having 1-3 unmet needs, socially integrating ≤five times/week, and having stable housing. Factors such as unmet needs, un-/underinsurance, and social integration may be addressed by healthcare and community organizations.
Topics: Humans; Cross-Sectional Studies; Male; HIV Infections; Adult; Social Determinants of Health; Female; Middle Aged; Southeastern United States; Young Adult; Patient Acceptance of Health Care
PubMed: 38816001
DOI: 10.1177/23259582241251728 -
JMIR Human Factors May 2024Studies evaluating the usability of mobile-phone assessments in older adults are limited.
BACKGROUND
Studies evaluating the usability of mobile-phone assessments in older adults are limited.
OBJECTIVE
This study aims to identify design-based barriers and facilitators to mobile app survey completion among 2 samples of older adults; those in the Framingham Heart Study and a more diverse sample from a hospital-based setting.
METHODS
We used mixed methods to identify challenging and beneficial features of the mobile app in participants from the electronic Framingham Heart Study (n=15; mean age of 72 years; 6/15, 40% women; 15/15, 100% non-Hispanic and White) and among participants recruited from a hospital-based setting (n=15; mean age of 71 years; 7/15, 47% women; 3/15, 20% Hispanic; and 8/15, 53% non-White). A variety of app-based measures with different response formats were tested, including self-reported surveys, pictorial assessments (to indicate body pain sites), and cognitive testing tasks (eg, Trail Making Test and Stroop). Participants completed each measure using a think-aloud protocol, while being audio- and video-recorded with a qualitative interview conducted at the end of the session. Recordings were coded for participant usability errors by 2 pairs of coders. Participants completed the Mobile App Rating Scale to assess the app (response range 1=inadequate to 5=excellent).
RESULTS
In electronic Framingham Heart Study participants, the average total Mobile App Rating Scale score was 7.6 (SD 1.1), with no significant differences in the hospital-based sample. In general, participants were pleased with the app and found it easy to use. A large minority had at least 1 navigational issue, most committed only once. Most older adults did not have difficulty completing the self-reported multiple-choice measures unless it included lengthy instructions but participants had usability issues with the Stroop and Trail Making Test.
CONCLUSIONS
Our methods and results help guide app development and app-based survey construction for older adults, while also giving consideration to sociodemographic differences.
Topics: Humans; Mobile Applications; Aged; Female; Male; Smartphone; Surveys and Questionnaires; Aged, 80 and over
PubMed: 38815261
DOI: 10.2196/56653 -
PloS One 2024Motor Competence (MC) is related to the development of healthy lifestyles in children and adolescents, and many studies have compared it with different variables,...
INTRODUCTION
Motor Competence (MC) is related to the development of healthy lifestyles in children and adolescents, and many studies have compared it with different variables, including sports participation. This investigation aimed to characterize the components and total scores of MC regarding different physical activity practices, such as physical education (PE) classes, futsal, volleyball, and ballet, and to compare MC regarding sports, sex, and age-groups.
METHODS
Using a cross-sectional study, 398 Portuguese children and adolescents (398 participants: 200 boys and 198 girls; 12.649±3.46 years) were conveniently chosen between 2022 and 2023. Four groups of different sports were created: PE classes (n = 187), futsal (n = 80), volleyball (n = 101) and ballet (n = 30), and four different age groups: 7 to 9 years old (n = 117); 10 to 12 years old (n = 65), 13 to 15 years old (n = 96) and, 16 to 19 years old (n = 120). All participants reported to participate in at least two training sessions per week (1 hour each) for at least two years. MC was assessed with Motor Competence Assessment (MCA) comprising three components with six tests (two tests for each component). Participants' total MC was calculated as the average of the three components of the MCA. Data were analyzed by applying ANOVA one-way with LSD post-hoc.
RESULTS
Differences were found in MC among groups, where futsal participants showed better scores in general. Sex comparison showed that boys have a higher MC when practicing futsal, especially compared to volleyball players. Age-group analysis showed that younger participants had better MC levels compared to older ones.
CONCLUSION
The whole group showed the 50th percentile of MC, but volleyball adolescents showed results below this reference. MC is intrinsically linked to an individual's motor experiences and motivations rather than depending directly on the specific practice of the sport.
Topics: Humans; Male; Adolescent; Female; Child; Cross-Sectional Studies; Motor Skills; Sports; Portugal; Physical Education and Training; Movement; Young Adult; Exercise
PubMed: 38814979
DOI: 10.1371/journal.pone.0304524 -
PloS One 2024Internal displacement of populations due to armed conflicts can substantially impact a region's Land Use and Land Cover (LULC) and the efforts towards the achievement of...
Assessment of the environmental impacts of conflict-driven Internally Displaced Persons: A sentinel-2 satellite based analysis of land use/cover changes in the Kas locality, Darfur, Sudan.
Internal displacement of populations due to armed conflicts can substantially impact a region's Land Use and Land Cover (LULC) and the efforts towards the achievement of Sustainable Development Goals (SDGs). The objective of this study was to determine the effects of conflict-driven Internally Displaced Persons (IDPs) on vegetation cover and environmental sustainability in the Kas locality of Darfur, Sudan. Supervised classification and change analysis were performed on Sentinel-2 satellite images for the years 2016 and 2022 using QGIS software. The Sentinel-2 Level 2A data were analysed using the Random Forest (RF) Machine Learning (ML) classifier. Five land cover types were successfully classified (agricultural land, vegetation cover, built-up area, sand, and bareland) with overall accuracies of more than 86% and Kappa coefficients greater than 0.74. The results revealed a 35.33% (-10.20 km2) decline in vegetation cover area over the six-year study period, equivalent to an average annual loss rate of -5.89% (-1.70 km2) of vegetation cover. In contrast, agricultural land and built-up areas increased by 17.53% (98.12 km2) and 60.53% (5.29 km2) respectively between the two study years. The trends of the changes among different LULC classes suggest potential influences of human activities especially the IDPs, natural processes, and a combination of both in the study area. This study highlights the impacts of IDPs on natural resources and land cover patterns in a conflict-affected region. It also offers pertinent data that can support decision-makers in restoring the affected areas and preventing further environmental degradation for sustainability.
Topics: Sudan; Humans; Refugees; Armed Conflicts; Satellite Imagery; Agriculture; Conservation of Natural Resources; Environment; Environmental Monitoring
PubMed: 38814969
DOI: 10.1371/journal.pone.0304034 -
PloS One 2024DNA barcoding is used to identify cryptic species, survey environmental samples, and estimate phyletic and genetic diversity. Armored scale insects are phytophagous...
DNA barcoding is used to identify cryptic species, survey environmental samples, and estimate phyletic and genetic diversity. Armored scale insects are phytophagous insects and are the most species-rich taxa in the Coccoidea superfamily. This study developed a DNA barcode library for armored scale insect species collected from southern China during 2021-2022. We sequenced a total of 239 specimens, recognized as 50 morphological species, representing two subfamilies and 21 genera. Sequencing analysis revealed that the average G + C content of the cytochrome oxidase subunit I (COI) gene sequence was very low (~18.06%) and that the average interspecific divergence was 10.07% while intraspecific divergence was 3.20%. The intraspecific divergence value was inflated by the high intraspecific divergence in ten taxa, which may indicate novel species overlooked by current taxonomic treatments. All the Automated Barcode Gap Discovery, Assemble Species by Automatic Partitioning, Taxon DNA analysis and Bayesian Poisson Tree Process methods yielded largely consistent results, indicating a robust and credible species delimitation. Based on these results, an intergeneric distance threshold of ≤ 5% was deemed appropriate for the differentiation of armored scale insect species in China. This study establishes a comprehensive barcode library for the identification of armored scale insects, future research, and application.
Topics: Animals; DNA Barcoding, Taxonomic; China; Hemiptera; Phylogeny; Electron Transport Complex IV; Genetic Variation; Gene Library; Bayes Theorem
PubMed: 38814962
DOI: 10.1371/journal.pone.0301499 -
PloS One 2024Depending on the degree of fracture, pelvic fracture can be accompanied by vascular damage, and in severe cases, it may progress to hemorrhagic shock. Pelvic radiography...
Depending on the degree of fracture, pelvic fracture can be accompanied by vascular damage, and in severe cases, it may progress to hemorrhagic shock. Pelvic radiography can quickly diagnose pelvic fractures, and the Association for Osteosynthesis Foundation and Orthopedic Trauma Association (AO/OTA) classification system is useful for evaluating pelvic fracture instability. This study aimed to develop a radiomics-based machine-learning algorithm to quickly diagnose fractures on pelvic X-ray and classify their instability. data used were pelvic anteroposterior radiographs of 990 adults over 18 years of age diagnosed with pelvic fractures, and 200 normal subjects. A total of 93 features were extracted based on radiomics:18 first-order, 24 GLCM, 16 GLRLM, 16 GLSZM, 5 NGTDM, and 14 GLDM features. To improve the performance of machine learning, the feature selection methods RFE, SFS, LASSO, and Ridge were used, and the machine learning models used LR, SVM, RF, XGB, MLP, KNN, and LGBM. Performance measurement was evaluated by area under the curve (AUC) by analyzing the receiver operating characteristic curve. The machine learning model was trained based on the selected features using four feature-selection methods. When the RFE feature selection method was used, the average AUC was higher than that of the other methods. Among them, the combination with the machine learning model SVM showed the best performance, with an average AUC of 0.75±0.06. By obtaining a feature-importance graph for the combination of RFE and SVM, it is possible to identify features with high importance. The AO/OTA classification of normal pelvic rings and pelvic fractures on pelvic AP radiographs using a radiomics-based machine learning model showed the highest AUC when using the SVM classification combination. Further research on the radiomic features of each part of the pelvic bone constituting the pelvic ring is needed.
Topics: Humans; Machine Learning; Pelvic Bones; Fractures, Bone; Male; Adult; Female; Middle Aged; Radiography; Algorithms; ROC Curve; Aged; Area Under Curve; Radiomics
PubMed: 38814948
DOI: 10.1371/journal.pone.0304350 -
PloS One 2024This study investigates head nods in natural dyadic German Sign Language (DGS) interaction, with the aim of finding whether head nods serving different functions vary in...
This study investigates head nods in natural dyadic German Sign Language (DGS) interaction, with the aim of finding whether head nods serving different functions vary in their phonetic characteristics. Earlier research on spoken and sign language interaction has revealed that head nods vary in the form of the movement. However, most claims about the phonetic properties of head nods have been based on manual annotation without reference to naturalistic text types and the head nods produced by the addressee have been largely ignored. There is a lack of detailed information about the phonetic properties of the addressee's head nods and their interaction with manual cues in DGS as well as in other sign languages, and the existence of a form-function relationship of head nods remains uncertain. We hypothesize that head nods functioning in the context of affirmation differ from those signaling feedback in their form and the co-occurrence with manual items. To test the hypothesis, we apply OpenPose, a computer vision toolkit, to extract head nod measurements from video recordings and examine head nods in terms of their duration, amplitude and velocity. We describe the basic phonetic properties of head nods in DGS and their interaction with manual items in naturalistic corpus data. Our results show that phonetic properties of affirmative nods differ from those of feedback nods. Feedback nods appear to be on average slower in production and smaller in amplitude than affirmation nods, and they are commonly produced without a co-occurring manual element. We attribute the variations in phonetic properties to the distinct roles these cues fulfill in turn-taking system. This research underlines the importance of non-manual cues in shaping the turn-taking system of sign languages, establishing the links between such research fields as sign language linguistics, conversational analysis, quantitative linguistics and computer vision.
Topics: Humans; Sign Language; Phonetics; Germany; Male; Head; Female; Language; Head Movements
PubMed: 38814896
DOI: 10.1371/journal.pone.0304040