LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 409

Search options

  1. Article ; Online: Suicidality Screening Guidelines Highlight the Need for Intervention Studies.

    Perlis, Roy H

    JAMA network open

    2023  Volume 6, Issue 6, Page(s) e2318773

    MeSH term(s) Humans ; Suicide ; Suicidal Ideation ; Depression
    Language English
    Publishing date 2023-06-01
    Publishing country United States
    Document type Editorial
    ISSN 2574-3805
    ISSN (online) 2574-3805
    DOI 10.1001/jamanetworkopen.2023.18773
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  2. Article ; Online: Classifying Firearm Injury Using EHR Data-Finding the Phenotype by Reading the Notes.

    Perlis, Roy H

    JAMA network open

    2023  Volume 6, Issue 4, Page(s) e235781

    MeSH term(s) Humans ; Firearms ; Wounds, Gunshot/epidemiology ; Electronic Health Records ; Phenotype
    Language English
    Publishing date 2023-04-03
    Publishing country United States
    Document type Journal Article ; Comment
    ISSN 2574-3805
    ISSN (online) 2574-3805
    DOI 10.1001/jamanetworkopen.2023.5781
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  3. Article: Research Letter: Application of GPT-4 to select next-step antidepressant treatment in major depression.

    Perlis, Roy H

    medRxiv : the preprint server for health sciences

    2023  

    Abstract: Introduction: Large language models perform well on a range of academic tasks including medical examinations. The performance of this class of models in psychopharmacology has not been explored.: Method: Chat GPT-plus, implementing the GPT-4 large ... ...

    Abstract Introduction: Large language models perform well on a range of academic tasks including medical examinations. The performance of this class of models in psychopharmacology has not been explored.
    Method: Chat GPT-plus, implementing the GPT-4 large language model, was presented with each of 10 previously-studied antidepressant prescribing vignettes in randomized order, with results regenerated 5 times to evaluate stability of responses. Results were compared to expert consensus.
    Results: At least one of the optimal medication choices was included among the best choices in 38/50 (76%) vignettes: 5/5 for 7 vignettes, 3/5 for 1, and 0/5 for 2. At least one of the poor choice or contraindicated medications was included among the choices considered optimal or good in 24/50 (48%) of vignettes. The model provided as rationale for treatment selection multiple heuristics including avoiding prior unsuccessful medications, avoiding adverse effects based on comorbidities, and generalizing within medication class.
    Conclusion: The model appeared to identify and apply a number of heuristics commonly applied in psychopharmacologic clinical practice. However, the inclusion of less optimal recommendations indicates that large language models may pose a substantial risk if routinely applied to guide psychopharmacologic treatment without further monitoring.
    Language English
    Publishing date 2023-04-18
    Publishing country United States
    Document type Preprint
    DOI 10.1101/2023.04.14.23288595
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  4. Article ; Online: Mending the Holes in the Suicide Safety Net.

    Perlis, Roy H

    JAMA network open

    2022  Volume 5, Issue 7, Page(s) e2225794

    MeSH term(s) Humans ; Suicide/prevention & control
    Language English
    Publishing date 2022-07-01
    Publishing country United States
    Document type Journal Article ; Comment
    ISSN 2574-3805
    ISSN (online) 2574-3805
    DOI 10.1001/jamanetworkopen.2022.25794
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  5. Article ; Online: Accuracy of Attestation Among Micrographic Dermatologic Surgery Diplomates.

    Perlis, Clifford S / Perlis, Roy H

    JAMA network open

    2022  Volume 5, Issue 9, Page(s) e2229795

    MeSH term(s) Data Collection ; Dermatologic Surgical Procedures ; Humans ; Mohs Surgery
    Language English
    Publishing date 2022-09-01
    Publishing country United States
    Document type Journal Article
    ISSN 2574-3805
    ISSN (online) 2574-3805
    DOI 10.1001/jamanetworkopen.2022.29795
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  6. Article ; Online: Evaluating the Application of Large Language Models in Clinical Research Contexts.

    Perlis, Roy H / Fihn, Stephan D

    JAMA network open

    2023  Volume 6, Issue 10, Page(s) e2335924

    Language English
    Publishing date 2023-10-02
    Publishing country United States
    Document type Journal Article
    ISSN 2574-3805
    ISSN (online) 2574-3805
    DOI 10.1001/jamanetworkopen.2023.35924
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  7. Article ; Online: Exercising Heart and Head in Managing Coronavirus Disease 2019 in Wuhan.

    Perlis, Roy H

    JAMA network open

    2020  Volume 3, Issue 3, Page(s) e204006

    MeSH term(s) Betacoronavirus ; COVID-19 ; Coronavirus ; Coronavirus Infections ; Health Personnel ; Humans ; Mental Health ; Pandemics ; Pneumonia, Viral ; SARS-CoV-2
    Keywords covid19
    Language English
    Publishing date 2020-03-02
    Publishing country United States
    Document type Journal Article ; Comment
    ISSN 2574-3805
    ISSN (online) 2574-3805
    DOI 10.1001/jamanetworkopen.2020.4006
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  8. Article ; Online: Essential Work: Psychiatric Clinical Investigation in the Midst of a Pandemic.

    Perlis, Roy H

    The American journal of psychiatry

    2020  Volume 177, Issue 12, Page(s) 1117–1118

    MeSH term(s) Biomedical Research/methods ; Biomedical Research/organization & administration ; COVID-19 ; Clinical Trials as Topic/methods ; Clinical Trials as Topic/organization & administration ; Electronic Health Records ; Humans ; Information Dissemination ; Mobile Applications ; Patient Selection ; Psychiatry ; Self Report ; Telecommunications
    Language English
    Publishing date 2020-07-23
    Publishing country United States
    Document type Journal Article
    ZDB-ID 280045-7
    ISSN 1535-7228 ; 0002-953X
    ISSN (online) 1535-7228
    ISSN 0002-953X
    DOI 10.1176/appi.ajp.2020.20050722
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  9. Article ; Online: Is It Time to Try Sequenced Treatment Alternatives to Relieve Depression (STAR*D) Again?

    Perlis, Roy H / Fava, Maurizio

    JAMA psychiatry

    2022  Volume 79, Issue 4, Page(s) 281–282

    MeSH term(s) Antidepressive Agents/therapeutic use ; Depression/therapy ; Depressive Disorder, Major/drug therapy ; Humans ; Treatment Outcome
    Chemical Substances Antidepressive Agents
    Language English
    Publishing date 2022-02-08
    Publishing country United States
    Document type Journal Article
    ZDB-ID 2701203-7
    ISSN 2168-6238 ; 2168-622X
    ISSN (online) 2168-6238
    ISSN 2168-622X
    DOI 10.1001/jamapsychiatry.2021.4281
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  10. Article ; Online: Clinical decision support for bipolar depression using large language models.

    Perlis, Roy H / Goldberg, Joseph F / Ostacher, Michael J / Schneck, Christopher D

    Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology

    2024  

    Abstract: Management of depressive episodes in bipolar disorder remains challenging for clinicians despite the availability of treatment guidelines. In other contexts, large language models have yielded promising results for supporting clinical decisionmaking. We ... ...

    Abstract Management of depressive episodes in bipolar disorder remains challenging for clinicians despite the availability of treatment guidelines. In other contexts, large language models have yielded promising results for supporting clinical decisionmaking. We developed 50 sets of clinical vignettes reflecting bipolar depression and presented them to experts in bipolar disorder, who were asked to identify 5 optimal next-step pharmacotherapies and 5 poor or contraindicated choices. The same vignettes were then presented to a large language model (GPT4-turbo; gpt-4-1106-preview), with or without augmentation by prompting with recent bipolar treatment guidelines, and asked to identify the optimal next-step pharmacotherapy. Overlap between model output and gold standard was estimated. The augmented model prioritized the expert-designated optimal choice for 508/1000 vignettes (50.8%, 95% CI 47.7-53.9%; Cohen's kappa = 0.31, 95% CI 0.28-0.35). For 120 vignettes (12.0%), at least one model choice was among the poor or contraindicated treatments. Results were not meaningfully different when gender or race of the vignette was permuted to examine risk for bias. By comparison, an un-augmented model identified the optimal treatment for 234 (23.0%, 95% CI 20.8-26.0%; McNemar's p < 0.001 versus augmented model) of the vignettes. A sample of community clinicians scoring the same vignettes identified the optimal choice for 23.1% (95% CI 15.7-30.5%) of vignettes, on average; McNemar's p < 0.001 versus augmented model. Large language models prompted with evidence-based guidelines represent a promising, scalable strategy for clinical decision support. In addition to prospective studies of efficacy, strategies to avoid clinician overreliance on such models, and address the possibility of bias, will be needed.
    Language English
    Publishing date 2024-03-13
    Publishing country England
    Document type Journal Article
    ZDB-ID 639471-1
    ISSN 1740-634X ; 0893-133X
    ISSN (online) 1740-634X
    ISSN 0893-133X
    DOI 10.1038/s41386-024-01841-2
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

To top