Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 11 de 11
Filter
Add more filters











Publication year range
1.
Article in English | MEDLINE | ID: mdl-39246048

ABSTRACT

BACKGROUND: Artificial intelligence (AI) is engineered to emulate tasks that have historically required human interaction and intellect, including learning, pattern recognition, decision-making, and problem-solving. Although AI models like ChatGPT-4 have demonstrated satisfactory performance on medical licensing exams, suggesting a potential for supporting medical diagnostics and decision-making, no study of which we are aware has evaluated the ability of these tools to make treatment recommendations when given clinical vignettes and representative medical imaging of common orthopaedic conditions. As AI continues to advance, a thorough understanding of its strengths and limitations is necessary to inform safe and helpful integration into medical practice. QUESTIONS/PURPOSES: (1) What is the concordance between ChatGPT-4-generated treatment recommendations for common orthopaedic conditions with both the American Academy of Orthopaedic Surgeons (AAOS) clinical practice guidelines (CPGs) and an orthopaedic attending physician's treatment plan? (2) In what specific areas do the ChatGPT-4-generated treatment recommendations diverge from the AAOS CPGs? METHODS: Ten common orthopaedic conditions with associated AAOS CPGs were identified: carpal tunnel syndrome, distal radius fracture, glenohumeral joint osteoarthritis, rotator cuff injury, clavicle fracture, hip fracture, hip osteoarthritis, knee osteoarthritis, ACL injury, and acute Achilles rupture. For each condition, the medical records of 10 deidentified patients managed at our facility were used to construct clinical vignettes that each had an isolated, single diagnosis with adequate clarity. The vignettes also encompassed a range of diagnostic severity to evaluate more thoroughly adherence to the treatment guidelines outlined by the AAOS. These clinical vignettes were presented alongside representative radiographic imaging. The model was prompted to provide a single treatment plan recommendation. Each treatment plan was compared with established AAOS CPGs and to the treatment plan documented by the attending orthopaedic surgeon treating the specific patient. Vignettes where ChatGPT-4 recommendations diverged from CPGs were reviewed to identify patterns of error and summarized. RESULTS: ChatGPT-4 provided treatment recommendations in accordance with the AAOS CPGs in 90% (90 of 100) of clinical vignettes. Concordance between ChatGPT-generated plans and the plan recommended by the treating orthopaedic attending physician was 78% (78 of 100). One hundred percent (30 of 30) of ChatGPT-4 recommendations for fracture vignettes and hip and knee arthritis vignettes matched with CPG recommendations, whereas the model struggled most with recommendations for carpal tunnel syndrome (3 of 10 instances demonstrated discordance). ChatGPT-4 recommendations diverged from AAOS CPGs for three carpal tunnel syndrome vignettes; two ACL injury, rotator cuff injury, and glenohumeral joint osteoarthritis vignettes; as well as one acute Achilles rupture vignette. In these situations, ChatGPT-4 most often struggled to correctly interpret injury severity and progression, incorporate patient factors (such as lifestyle or comorbidities) into decision-making, and recognize a contraindication to surgery. CONCLUSION: ChatGPT-4 can generate accurate treatment plans aligned with CPGs but can also make mistakes when it is required to integrate multiple patient factors into decision-making and understand disease severity and progression. Physicians must critically assess the full clinical picture when using AI tools to support their decision-making. CLINICAL RELEVANCE: ChatGPT-4 may be used as an on-demand diagnostic companion, but patient-centered decision-making should continue to remain in the hands of the physician.

2.
J Orthop Trauma ; 38(8S): S9-S10, 2024 Aug 01.
Article in English | MEDLINE | ID: mdl-39007632

ABSTRACT

VIDEO AVAILABLE AT: https://ota.org/education/ota-online-resources/video-library-procedures-techniques/achievinglimb-length-equality.


Subject(s)
Femoral Fractures , Leg Length Inequality , Humans , Femoral Fractures/surgery , Femoral Fractures/diagnostic imaging , Leg Length Inequality/etiology , Leg Length Inequality/prevention & control
3.
J Am Acad Orthop Surg ; 32(3): 123-129, 2024 Feb 01.
Article in English | MEDLINE | ID: mdl-37976385

ABSTRACT

INTRODUCTION: Clinical documentation is a critical aspect of health care that enables healthcare providers to communicate effectively with each other and maintain accurate patient care records. Artificial intelligence tools, such as chatbots and virtual assistants, have the potential to assist healthcare providers in clinical documentation. ChatGPT is an artificial intelligence conversational model that generates human-like responses to text-based prompts. In this study, we sought to investigate ChatGPT's ability to assist with writing a history of present illness based on standardized patient histories. METHODS: A blinded, randomized controlled study was conducted to compare the use of typing, dictation, and ChatGPT as tools to document history of present illness (HPI) of standardized patient histories. Eleven study participants, consisting of medical students, orthopaedic surgery residents, and attending surgeons, completed three HPIs using a different documentation technique for each one. Participants were randomized into cohorts based on the type of documentation technique. Participants were asked to interview standardized patients and document the patient's history of present illness using their assigned method. RESULTS: ChatGPT was found to be intermediate for speed; dictation was fastest, but produced markedly longer and higher quality patient histories based on Physician Documentation Quality Instrument score compared with dictation and typing. However, ChatGPT included erroneous information in 36% of the documents. Poor agreement existed on the quality of patient histories between reviewers. DISCUSSION: Our study suggests that ChatGPT has the potential to improve clinical documentation by producing more comprehensive and organized HPIs. ChatGPT can generate longer and more detailed documentation compared with typing or dictation documentation methods. However, additional studies are needed to investigate and address concerns regarding privacy, bias, and accuracy of information.


Subject(s)
Artificial Intelligence , Surgeons , Humans , Communication , Documentation , Health Facilities
4.
J Hand Surg Glob Online ; 4(6): 448-451, 2022 Nov.
Article in English | MEDLINE | ID: mdl-36425363

ABSTRACT

Carpal tunnel syndrome is the most common upper extremity peripheral neuropathy syndrome. Treatment ranges from nonsurgical methods, including night-orthosis fabrication and corticosteroid injections to surgical management via a carpal tunnel release (CTR). Carpal tunnel release alleviates nerve compression by releasing the transverse carpal ligament, and performed as either an open CTR (OCTR) or endoscopic CTR (ECTR) procedure. However, there is no consensus on the superiority of the 2 approaches. Practitioners may be limited to 1 technique because of surgeons' comfort, access to an operating room versus a procedure room, and cost. The purpose of this article was to describe the surgical technique for wide awake, local anesthesia, no tourniquet ECTR performed in an office-based setting, which would decrease operating room demand and cost.

5.
Appetite ; 176: 106129, 2022 09 01.
Article in English | MEDLINE | ID: mdl-35718310

ABSTRACT

The scientific literature and advocacy organisations highlight three harm-related arguments as paramount reasons for the reduction and cessation of the consumption of animal-derived products (ADP) - violence toward animals, damage to the environment, and human health. However, research on their comparative effects is scarce and there is no clear definition of which type of argument is the most effective in restricting ADP consumption. Based on cognitive dissonance theory, this study aimed to investigate the effects of these types of arguments on meat-eaters' attitudes and beliefs toward the propositions of reducing and ceasing ADP consumption. The study sample comprised 545 Brazilian adults. We adopted an experimental between-subjects design based on the presentation of vignettes. Each participant responded to one of the vignettes (animal rights, environmental, or health arguments) or a control condition. Results showed that greater levels of ADP-related dissonance provoked greater positive attitudes toward the reduction and cessation of ADP consumption. Compared to baseline, the animal rights and environmental messages significantly increased dissonance and positive attitudes toward ADP restriction, but not the health argument. Participants most frequently adopted the dissonance-management strategies of denial of responsibility, denial of harm, and the articulation of beliefs favourable to change. The discussion highlights that the different effects of social influence contexts and argument types depend on their capacity to reveal ADP consumption as morally problematic behaviour. To our knowledge, this is the first study to experimentally compare the effects of animal rights, environmental and health-related arguments in generating ADP-related dissonance and attitude change.


Subject(s)
Animal Rights , Attitude , Animals , Humans , Cognitive Dissonance , Health Behavior
6.
Br J Soc Psychol ; 61(4): 1245-1262, 2022 Oct.
Article in English | MEDLINE | ID: mdl-35349739

ABSTRACT

People across the world have responded to the pandemic by mobilizing and organizing to support their communities, setting up mutual aid groups to provide practical, financial, and social support. Mutual aid means short-term 'crisis response' for some, while for other groups, it is a chance to radically restructure society, and what it means to be a member of that society. Drawing on social representations theory and previous work on citizenship in social and political psychology, we examined the ways in which mutual aid was understood and performed by members of UK Covid-19 mutual aid groups. We conducted 29 interviews with members of these groups in May/June 2020. A reflexive thematic analysis showed that mutual aid groups were characterized as complex, efficient, and non-hierarchical units, operating on the principles of solidarity, kindness, and trust. Two tensions were evident in the data, specifically between (1) collaboration with existing organizations and structures (e.g., local government and the police), and resistance to it and (2) maximizing group inclusivity and sustaining political critique. Findings are discussed in relation to existing theoretical and empirical work on citizenship and mutual aid groups.


Subject(s)
COVID-19 , Citizenship , Humans , Pandemics/prevention & control , Social Support , United Kingdom
7.
J Community Appl Soc Psychol ; 32(3): 423-437, 2022.
Article in English | MEDLINE | ID: mdl-34898965

ABSTRACT

Mutual aid groups developed and mobilized in communities across the UK and globally at the outset of the pandemic in order to support vulnerable community members with practical assistance and emotional support, with some understanding their work in political terms. This study adopted a "social cure" lens to investigate the effects of group identification and group perceptions on anxiety and coping self-efficacy among members of UK Covid-19 mutual aid groups. Survey data were collected from self-identified members of these groups (N = 844) during the initial period of "lockdown" restrictions in April - May 2020. Correlational analyses showed that identification with the mutual aid group was linked to more positive group perceptions and better self-reported psychological outcomes. Perceived group politicization showed the reverse pattern. Mixed support for the "social cure" model was evident; the effect of group identification on coping self-efficacy (but not anxiety) was serially mediated by perceived support and collective efficacy. Perceived group politicization was a significant moderator, seeming to amplify the indirect effect of group identification on coping self-efficacy via perceived support. Results are discussed in light of previous empirical work on the social cure and Covid-19 mutual aid groups. Please refer to the Supplementary Material section to find this article's Community and Social Impact Statement.

8.
Phys Sportsmed ; 50(3): 239-243, 2022 06.
Article in English | MEDLINE | ID: mdl-33784939

ABSTRACT

OBJECTIVES: In 2018 the NFL instituted playing rule article 8, which aimed to help decrease sport related concussion (SRC) by broadening the helmet-hit rule, making it a foul when a player lowers his head to make contact with his helmet against an opponent. Previous studies have demonstrated that the rate of lower extremity injuries increased following the institution of the targeting rule in NCAA football. The objective of this study was to determine if playing rule article 8 unintentionally led to a significant increase in the rate of lower extremity injuries sustained by NFL players during regular season games. METHODS: This study was a retrospective review of all NFL players who were placed on the publically available injury reports for a lower extremity injury from the 2016-2017 through 2019-2020 regular seasons. With article 8 taking effect starting with the 2018-2019 season, players were assigned to a pre- or post-rule cohort based on date of injury for purposes of injury rate comparison. Injury rates were calculated per 1000 athletic exposures (AE). Incidence rate ratio (RR) with 95% confidence intervals (CI) compared injury rates between the two cohorts. RESULTS: There was a 3% decrease in the lower extremity injury rate in 2018-2019 to 2019-2020 compared with 2016-2017 to 2017-2018, however this was not statistically significant (33.6 versus 34.3/1000 AEs, respectively; RR, 0.97; 95% CI 0.92-1.04). There was a 40% decrease in the SRC rate when comparing the post- to the pre-article-8 cohort (3.3 vs. 5.5/1000 AEs, respectively; RR 0.60; 95% CI 0.50-0.73). CONCLUSIONS: The rate of lower extremity injuries and players placed on the injury reserve over the past two NFL seasons following the enactment of playing rule article 8 has not significantly increased. However, the average games missed due to lower extremity injuries significantly increased under playing rule article 8, which suggests that the severity of lower extremity injuries possibly increased. LEVEL OF EVIDENCE: IV Diagnostic.


Subject(s)
Athletic Injuries , Brain Concussion , Football , Athletic Injuries/epidemiology , Athletic Injuries/prevention & control , Brain Concussion/epidemiology , Football/injuries , Humans , Incidence , Lower Extremity/injuries , Retrospective Studies , Seasons
9.
J Health Psychol ; 27(9): 2147-2160, 2022 08.
Article in English | MEDLINE | ID: mdl-34154436

ABSTRACT

The recognition and representation of BAME community as 'high risk' of Covid-19 in the UK presents both a health and an identity threat to this ethnic group. This study employed thematic analysis to explore response to these threats as related by a sample of 13 middle class members of the South Asian community. This work advances both health and identity psychological theory by recognising the affinity between expressions of health efficacy and identity. Our findings identify South Asian intragroup stigmatisation and commonalities that have implications for the promotion of health behaviour and health communications for minority groups.


Subject(s)
COVID-19 , Asian People , Ethnicity , Humans , Minority Groups/psychology , United Kingdom
10.
Int J Pediatr Otorhinolaryngol ; 148: 110823, 2021 Sep.
Article in English | MEDLINE | ID: mdl-34237522

ABSTRACT

IMPORTANCE: Paediatric inflammatory multisystem syndrome, temporally associated with SARS-CoV-2 (PIMS-TS) is a novel disease first identified in 2020. Recent cohort studies have described the complex presentation and symptomatology. This paper provides detailed description of the dysphagia and dysphonia symptoms, management, and outcome. OBJECTIVE: To describe dysphagia and dysphonia in PIMS-TS. DESIGN: Retrospective cohort study. SETTING: Single tertiary and quaternary children's hospital. PARTICIPANTS: All 50 children treated for paediatric multisystem inflammatory disease between April and June 2020 were included in this study. MAIN OUTCOME(S) AND MEASURE(S): Dysphonia: GRBAS Perceptual Severity Scores, Vocal Handicap Index scores and the Vocal Tract Discomfort Scale. Dysphagia: Functional Oral Intake Scale. RESULTS: Fifty children met the diagnostic criteria for PIMS-TS. 33 (66%) were male. Median age was 10 years (range: 1-17). 36 (72%) were of Black, Asian or minority ethnic background. Nine (18%) required specialist assessment and management of dysphagia and/or dysphonia. Five (55%) were male with a median age of 9 years 7 months (range: 1-15 years). Symptoms typically resolved within three months. Two children presented with persisting dysphonia three months post-presentation. Neurological, inflammatory, and iatrogenic causes of dysphagia and dysphonia were identified. CONCLUSIONS AND RELEVANCE: Dysphonia and dysphagia are present in children with PIMS-TS. Further data is required to understand pathophysiology, estimate incidence, and determine prognostic factors. This preliminary data highlights the need for dysphagia and dysphonia screening and timely referral for specialist, multidisciplinary assessment and treatment to ensure short-term aspiration risk is managed and long-term, functional outcomes are optimised.


Subject(s)
COVID-19 , Deglutition Disorders , Dysphonia , Child , Deglutition Disorders/diagnosis , Deglutition Disorders/epidemiology , Deglutition Disorders/etiology , Dysphonia/diagnosis , Dysphonia/etiology , Humans , Infant , Male , Retrospective Studies , SARS-CoV-2 , Systemic Inflammatory Response Syndrome
11.
J Orthop Surg (Hong Kong) ; 27(1): 2309499019832815, 2019.
Article in English | MEDLINE | ID: mdl-30827175

ABSTRACT

PURPOSE: The purposes of this study were to determine the rate of venous thromboembolism (VTE) after discharge from the hospital in patients treated operatively with a pelvic ring or acetabular fracture and to define the main time frame in which VTE occurs within the 90-day period after hospital discharge. METHODS: California and Florida State Inpatient Databases from 2005 to 2009 were used to identify patients with clinically significant VTEs within 90 days of hospital discharge. ICD-9 diagnosis codes identified patients with a pelvic ring or acetabular fracture and a VTE. Procedure codes distinguished patients having surgical fracture treatment. Deep vein thrombosis (DVT) and pulmonary embolus (PE) were included. RESULTS: Overall, 13,589 patients had a pelvic ring or acetabular fracture and operative treatment. One hundred thirteen patients (0.83%) had a VTE within 90 days after hospital discharge: 69 (0.51%) had a DVT, 28 (0.21%) had a PE, and 16 (0.12%) had both. Twenty-four (28%) of DVTs and 10 (23%) of PEs occurred >35 days after discharge, being evenly distributed out to 90 days. There were five fatal PEs, occurring 2, 3, 7, 31, and 51 days after discharge. Therefore, overall, <0.2% of patients developed a DVT and <0.1% were diagnosed with a PE (only 1 fatal; <0.01%) >35 days after the index hospitalization. CONCLUSIONS: A substantial proportion of VTE events occur over 35 days after discharge; however, the overall risk is low with fatal PE being extremely low (<0.01%). Given the diminished VTE risk after 35 days, the decision to further extend antithrombotic drug therapy may be guided by patient-specific factors, such as prolonged immobility.


Subject(s)
Fractures, Bone/surgery , Pelvic Bones/injuries , Postoperative Complications/epidemiology , Venous Thromboembolism/epidemiology , Adolescent , Adult , Aged , Aged, 80 and over , Female , Humans , Male , Middle Aged , Patient Discharge , Pulmonary Embolism/epidemiology , Risk Factors , Time Factors , Venous Thrombosis/epidemiology , Young Adult
SELECTION OF CITATIONS
SEARCH DETAIL