1
|
Perlis RH. Research Letter: Application of GPT-4 to select next-step antidepressant treatment in major depression. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.04.14.23288595. [PMID: 37131648 PMCID: PMC10153309 DOI: 10.1101/2023.04.14.23288595] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/04/2023]
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 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.
Collapse
Affiliation(s)
- Roy H. Perlis
- Massachusetts General Hospital, Boston, MA
- Harvard Medical School, Boston, MA
| |
Collapse
|
2
|
Sheu YH, Magdamo C, Miller M, Smoller JW, Blacker D. Initial antidepressant choice by non-psychiatrists: Learning from large-scale electronic health records. Gen Hosp Psychiatry 2023; 81:22-31. [PMID: 36724694 DOI: 10.1016/j.genhosppsych.2022.12.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/29/2022] [Revised: 12/07/2022] [Accepted: 12/09/2022] [Indexed: 12/14/2022]
Abstract
OBJECTIVES Pharmacological treatment of depression mostly occurs in non-psychiatric settings, but the determinants of initial choice of antidepressant treatment in these settings are unclear. We investigate how non-psychiatrists choose among four antidepressant classes at first prescription (selective serotonin reuptake inhibitors [SSRI], bupropion, mirtazapine, or serotonin-norepinephrine reuptake inhibitors [SNRI]). METHOD Using electronic health records (EHRs), we included adult patients at the time of first antidepressant prescription with a co-occurring diagnosis code for a depressive disorder. We selected 64 variables based on a literature search and expert consultation, constructed the variables from either structured codes or through applying natural language processing (NLP), and modeled antidepressant choice using multinomial logistic regression, using SSRI as the reference class. RESULTS With 47,528 patients, we observed significant associations for 36 of 64 variables. Many of these associations suggested antidepressants' known pharmacological properties/actions guided choice. For example, there was a decreased likelihood of bupropion prescription among patients with epilepsy (adjusted OR 0.49, 95%CI: 0.41-0.57, p < 0.001), and an increased likelihood of mirtazapine prescription among patients with insomnia (adjusted OR 1.59, 95%CI: 1.40-1.80, p < 0.001). CONCLUSIONS Broadly speaking, non-psychiatrists' selection of antidepressant class appears to be at least in part guided by clinically relevant pharmacological considerations.
Collapse
Affiliation(s)
- Yi-Han Sheu
- Center for Precision Psychiatry, Massachusetts General Hospital, 185 Cambridge Street, 2(nd) floor, Boston, MA 02114, USA; Psychiatric and Neurodevelopmental Genetics Unit, Center for Genomic Medicine, Massachusetts General Hospital, 185 Cambridge Street, 6(th) floor, Boston, MA 02114, USA; Department of Psychiatry, Massachusetts General Hospital / Harvard Medical School, 55 Fruit St, Boston, MA 02114, USA; Stanley Center for Psychiatric Research, Broad Institute of MIT and Harvard, 75 Ames Street, Cambridge, MA 02142, USA; Department of Epidemiology, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, Boston, MA 02115, USA.
| | - Colin Magdamo
- Department of Neurology, Massachusetts General Hospital / Harvard Medical School, 55 Fruit St, Boston, MA 02114, USA
| | - Matthew Miller
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, Boston, MA 02115, USA; Harvard Injury Control Research Centre, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, Boston, MA 02115, USA; Bouvé College of Health Sciences, Northeastern University, 360 Huntington Ave, Boston, MA 02115, USA
| | - Jordan W Smoller
- Center for Precision Psychiatry, Massachusetts General Hospital, 185 Cambridge Street, 2(nd) floor, Boston, MA 02114, USA; Psychiatric and Neurodevelopmental Genetics Unit, Center for Genomic Medicine, Massachusetts General Hospital, 185 Cambridge Street, 6(th) floor, Boston, MA 02114, USA; Department of Psychiatry, Massachusetts General Hospital / Harvard Medical School, 55 Fruit St, Boston, MA 02114, USA; Stanley Center for Psychiatric Research, Broad Institute of MIT and Harvard, 75 Ames Street, Cambridge, MA 02142, USA; Department of Epidemiology, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, Boston, MA 02115, USA
| | - Deborah Blacker
- Department of Psychiatry, Massachusetts General Hospital / Harvard Medical School, 55 Fruit St, Boston, MA 02114, USA; Department of Epidemiology, Harvard T.H. Chan School of Public Health, 677 Huntington Ave, Boston, MA 02115, USA
| |
Collapse
|