-
Current Opinion in Psychology Jun 2024Facial inference, a cornerstone of person perception, has traditionally been studied through human judgments about personality traits and abilities based on people's... (Review)
Review
Facial inference, a cornerstone of person perception, has traditionally been studied through human judgments about personality traits and abilities based on people's faces. Recent advances in artificial intelligence (AI) have introduced new dimensions to this field, employing machine learning algorithms to reveal people's character, capabilities, and social outcomes based just on their faces. This review examines recent research on human and AI-based facial inference across psychology, business, computer science, legal, and policy studies to highlight the need for scientific consensus on whether or not people's faces can reveal their inner traits, and urges researchers to address the critical concerns around epistemic validity, practical relevance, and societal welfare before recommending AI-based facial inference for consequential uses.
PubMed: 38908348
DOI: 10.1016/j.copsyc.2024.101815 -
The American Journal of Emergency... Jun 2024Emergency department (ED) overcrowding presents a global challenge that inhibits prompt care for critically ill patients. Traditional 5-level triage system that heavily...
OBJECTIVES
Emergency department (ED) overcrowding presents a global challenge that inhibits prompt care for critically ill patients. Traditional 5-level triage system that heavily rely on the judgment of the triage staff could fail to detect subtle symptoms in critical patients, thus leading to delayed treatment. Unlike previous rivalry-focused approaches, our study aimed to establish a collaborative machine learning (ML) model that renders risk scores for severe illness, which may assist the triage staff to provide a better patient stratification for timely critical cares.
METHODS
This retrospective study was conducted at a tertiary teaching hospital. Data were collected from January 2015 to October 2022. Demographic and clinical information were collected at triage. The study focused on severe illness as the outcome. We developed artificial neural network (ANN) models, with or without utilizing the Taiwan Triage and Acuity Scale (TTAS) score as one of the predictors. The model using the TTAS score is termed a machine-human collaborative model (ANN-MH), while the model without it is referred to as a machine-only model (ANN-MO). The predictive power of these models was assessed using the area under the receiver-operating-characteristic (AUROC) and the precision-recall curves (AUPRC); their sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score were compared.
RESULTS
The study analyzed 668,602 ED visits from 2015 to 2022. Among them, 278,724 visits from 2015 to 2018 were used for model training and validation, while 320,201 visits from 2019 to 2022 were for testing model performance. Approximately 2.6% of visits were by severely ill patients, whose TTAS scores ranged from 1 to 5. The ANN-MH model achieved a testing AUROC of 0.918 and AUPRC of 0.369, while for the ANN-MO model the AUROC and AUPRC were 0.909 and 0.339, respectively. Based on these metrics, the ANN-MH model outperformed the ANN-MO model, and both surpassed human triage classification. Subgroup analyses further highlighted the models' capability to identify higher-risk patients within the same triage level.
CONCLUSIONS
The traditional 5-level triage system often falls short, leading to under-triage of critical patients. Our models include a score-based differentiation within a triage level to offer advanced risk stratification, thereby promoting patient safety.
PubMed: 38908339
DOI: 10.1016/j.ajem.2024.06.015 -
Cognition Jun 2024Rules help guide our behavior-particularly in complex social contexts. But rules sometimes give us the "wrong" answer. How do we know when it is okay to break the rules?...
Rules help guide our behavior-particularly in complex social contexts. But rules sometimes give us the "wrong" answer. How do we know when it is okay to break the rules? In this paper, we argue that we sometimes use contractualist (agreement-based) mechanisms to determine when a rule can be broken. Our model draws on a theory of social interactions - "virtual bargaining" - that assumes that actors engage in a simulated bargaining process when navigating the social world. We present experimental data which suggests that rule-breaking decisions are sometimes driven by virtual bargaining and show that these data cannot be explained by more traditional rule-based or outcome-based approaches.
PubMed: 38908304
DOI: 10.1016/j.cognition.2024.105790 -
Annals of Nuclear Medicine Jun 2024This study aims to assess the utility of newly developed objective methods for the evaluation of intracranial abnormal amyloid deposition using PET/CT histogram without...
OBJECTIVE
This study aims to assess the utility of newly developed objective methods for the evaluation of intracranial abnormal amyloid deposition using PET/CT histogram without use of cortical ROI analyses.
METHODS
Twenty-five healthy volunteers (HV) and 38 patients with diagnosed or suspected dementia who had undergone F-FPYBF-2 PET/CT were retrospectively included in this study. Out of them, C-PiB PET/CT had been also performed in 13 subjects. In addition to the conventional methods, namely visual judgment and quantitative analyses using composed standardized uptake value ratio (comSUVR), the PET images were also evaluated by the following new parameters: the skewness and the mode-to-mean ratio (MMR) obtained from the histogram of the brain parenchyma; Top20%-map highlights the areas with high tracer accumulation occupying 20% volume of the total brain parenchymal on the individual's CT images. We evaluated the utility of the new methods using histogram compared with the visual assessment and comSUVR. The results of these new methods between F-FPYBF-2 and C-PiB were also compared in 13 subjects.
RESULTS
In visual analysis, 32, 9, and 22 subjects showed negative, border, and positive results, and composed SUVR in each group were 1.11 ± 0.06, 1.20 ± 0.13, and 1.48 ± 0.18 (p < 0.0001), respectively. Visually positive subjects showed significantly low skewness and high MMR (p < 0.0001), and the Top20%-Map showed the presence or absence of abnormal deposits clearly. In comparison between the two tracers, visual evaluation was all consistent, and the ComSUVR, the skewness, the MMR showed significant good correlation. The Top20%-Maps showed similar pattern.
CONCLUSIONS
Our new methods using the histogram of the brain parenchymal accumulation are simple and suitable for clinical practice of amyloid PET, and Top20%-Map on the individual's brain CT can be of great help for the visual assessment.
PubMed: 38907835
DOI: 10.1007/s12149-024-01956-y -
American Family Physician Jun 2024
Topics: Humans; Health Equity; Documentation; Racism; United States
PubMed: 38905560
DOI: No ID Found -
Frontiers in Aging Neuroscience 2024Recent evidence suggests that anosognosia or unawareness of cognitive impairment in Alzheimer's Disease (AD) may be explained by a disconnection between brain regions...
BACKGROUND
Recent evidence suggests that anosognosia or unawareness of cognitive impairment in Alzheimer's Disease (AD) may be explained by a disconnection between brain regions involved in accessing and monitoring information regarding self and others. It has been demonstrated that AD patients with anosognosia have reduced connectivity within the default mode network (DMN) and that anosognosia in people with prodromal AD is positively associated with bilateral anterior cingulate cortex (ACC), suggesting a possible role of this region in mechanisms of awareness in the early phase of disease. We hypothesized that anosognosia in AD is associated with an imbalance between the activity of large-scale resting-state functional magnetic resonance imaging (fMRI) networks, in particular the DMN, the salience network (SN), and the frontoparietal network (FPN).
METHODS
Sixty patients with MCI and AD dementia underwent fMRI and neuropsychological assessment including the Anosognosia Questionnaire Dementia (AQ-D), a measure of anosognosia based on a discrepancy score between patient's and carer's judgments. After having applied Independent Component Analysis (ICA) to resting fMRI data we performed: (i) correlations between the AQ-D score and functional connectivity in the DMN, SN, and FPN, and (ii) comparisons between aware and unaware patients of the DMN, SN, and FPN functional connectivity.
RESULTS
We found that anosognosia was associated with (i) weak functional connectivity within the DMN, in posterior and middle cingulate cortex particularly, (ii) strong functional connectivity within the SN in ACC, and between the SN and basal ganglia, and (iii) a heterogenous effect concerning the functional connectivity of the FPN, with a weak connectivity between the FPN and PCC, and a strong connectivity between the FPN and ACC. The observed effects were controlled for differences in severity of cognitive impairment and age.
CONCLUSION
Anosognosia in the AD continuum is associated with a dysregulation of the functional connectivity of three large-scale networks, namely the DMN, SN, and FPN.
PubMed: 38903902
DOI: 10.3389/fnagi.2024.1415994 -
Cureus May 2024Toxic epidermal necrolysis (TEN) is a severe and potentially fatal adverse drug reaction. This case report presents a 19-year-old male with pulmonary tuberculosis...
Toxic epidermal necrolysis (TEN) is a severe and potentially fatal adverse drug reaction. This case report presents a 19-year-old male with pulmonary tuberculosis undergoing anti-tubercular therapy who developed TEN. The patient had multiple comorbidities including type 1 diabetes mellitus and multisystem atrophy. ChatGPT was utilized alongside conventional methods to assess causality. While conventional scoring systems estimated mortality at 58.3% (SCORTEN) and 12.3% (ABCD-10), ChatGPT yielded divergent scores. Causality assessment using WHO-Uppsala Monitoring Centre (UMC) and Naranjo's scale indicated rifampicin and isoniazid as probable causative agents. However, ChatGPT provided ambiguous results. The study underscores the potential of AI in pharmacovigilance but emphasizes caution due to discrepancies observed. Collaborative utilization of artificial intelligence (AI) with clinical judgment is advocated to enhance diagnostic accuracy and treatment decisions in adverse drug reactions. This case highlights the importance of integrating AI into drug safety systems while acknowledging its limitations to ensure optimal patient care.
PubMed: 38903274
DOI: 10.7759/cureus.60638 -
The British Journal of General Practice... Jun 2024A majority of sex-workers (SWers) do not have a GP aware of their professional activity, which prevents appropriate support to this group. One of the reasons is fear of...
BACKGROUND
A majority of sex-workers (SWers) do not have a GP aware of their professional activity, which prevents appropriate support to this group. One of the reasons is fear of the doctors' judgment.
AIM
The objective of this research is to identify how sex-work is perceived by primary care practitioners, and how they follow-up this public.
METHOD
This qualitative study using semi-structured interviews with 12 GPs practicing in Brussels was conducted from October 2021 to March 2023.
RESULTS
Results show a lack of understanding of what SW is, of the legal context and of the people who practice it. Doctors know about related health issues, but not about their proportion or origin. The main factor identified as leading to SW is economic insecurity. Sample analysis shows theoretical positions close to a pro-sex stance (néo-réglementarisme).
CONCLUSION
This study demonstrates that primary care doctors' knowledge of SW is limited, and that these limitations can lead to stigmatisation and suboptimal treatment. The following recommendations are to: draw up a list of doctors who can welcome SWers without being judgmental and make this list available to associations active in the field of SW; co-construct a training course, in partnership with SWers, aimed at GPs (it would include sections on the historical and legal context, the approach to harm reduction and substance abuse, PreP, PEP, and a communication guide); and teach courses on marginalised populations with specific health needs during the initial training of medical students.
Topics: Humans; Qualitative Research; Female; General Practitioners; Sex Workers; Male; Interviews as Topic; Adult; Attitude of Health Personnel; Health Knowledge, Attitudes, Practice; Middle Aged
PubMed: 38902051
DOI: 10.3399/bjgp24X737925 -
Zhonghua Wei Chang Wai Ke Za Zhi =... Jun 2024Colorectal cancer is the most common malignant tumor of digestive tract, and the incidence of colorectal cancer in China is especially characterized by middle and low...
Colorectal cancer is the most common malignant tumor of digestive tract, and the incidence of colorectal cancer in China is especially characterized by middle and low rectal cancer. In recent years, with the progress of computer science, artificial intelligence technology has developed rapidly, and has achieved a lot of application results in the medical field. At present, artificial intelligence technology has covered various stages of colorectal cancer, including screening, individualized assessment, auxiliary diagnosis and treatment decision-making, refined surgery and prognosis judgment, providing help for the accurate and individualized treatment of rectal cancer. However, the lack of standardized, systematic, and scalable AI models remains a major pain point for the field. Therefore, it is necessary to carry out large-scale prospective clinical studies on artificial intelligence model to further confirm its application value in the clinical diagnosis and treatment of rectal cancer.
Topics: Humans; Artificial Intelligence; Rectal Neoplasms; Precision Medicine; Prognosis
PubMed: 38901989
DOI: 10.3760/cma.j.cn441530-20240412-00133 -
Nurse Education in Practice Jun 2024This study aims to evaluate the nursing students' informatics competency reported in the literature. (Review)
Review
AIM
This study aims to evaluate the nursing students' informatics competency reported in the literature.
BACKGROUND
Nursing informatics competency holds immense significance in the modern healthcare landscape, making it a vital requirement for nursing students before they graduate and embark on their professional careers. Nurses should integrate evidence-based nursing informatics (NI) into routine procedures to manage acute and chronic illnesses due to the increased complexity of the nursing profession and the healthcare systems.
DESIGN
A systematic review.
METHODS
PubMed, Scopus, Web of Science, and EMBASE were searched till December 2023 for any relevant studies evaluating the nursing informatics competency among students.
RESULTS
In this systematic review of 13 articles, the nursing informatics seems to be familiar among nursing students. Most of the included participants were generally competent, with an average total nursing informatics competency score of 3.4. In addition, they reported good scores for the clinical informatics role (Mean = 2.63), attitude (M= 3.7), basic computer knowledge and skills (M= 3.9), applied computer skills (M= 2.5), and wireless device skills (M= 3.2). However, these results were limited due to the use of structurally different assessment tools and their different cutoff values.
CONCLUSION
Nursing informatics competency has a great impact on the quality of services provided by healthcare systems. It is affected by several factors, such as the student's previous computer experience and the curricular and extracurricular exposure to informatics knowledge and skills. The available literature lacks a precise judgment on the competency of nursing students. But it seems to vary from fair to good among them. So, it is recommended to include nursing informatics as an obligatory course rather than an elective in the nursing baccalaureate. This helps prepare future nurses with the required knowledge and skills for better clinical decision-making.
PubMed: 38901275
DOI: 10.1016/j.nepr.2024.104007