The Diagnostic and Triage Accuracy of the GPT-3 Artificial Intelligence Model.

Importance: Artificial intelligence (AI) applications in health care have been effective in many areas of medicine, but they are often trained for a single task using labeled data, making deployment and generalizability challenging. Whether a general-purpose AI language model can perform diagnosis and triage is unknown. Objective: Compare the general-purpose Generative Pre-trained Transformer 3 (GPT-3) AI model's diagnostic and triage performance to attending physicians and lay adults who use the Internet. Design: We compared the accuracy of GPT-3's diagnostic and triage ability for 48 validated case vignettes of both common (e.g., viral illness) and severe (e.g., heart attack) conditions to lay people and practicing physicians. Finally, we examined how well calibrated GPT-3's confidence was for diagnosis and triage. Setting and Participants: The GPT-3 model, a nationally representative sample of lay people, and practicing physicians. Exposure: Validated case vignettes (<60 words; <6th grade reading level). Main Outcomes and Measures: Correct diagnosis, correct triage. Results: Among all cases, GPT-3 replied with the correct diagnosis in its top 3 for 88% (95% CI, 75% to 94%) of cases, compared to 54% (95% CI, 53% to 55%) for lay individuals (p<0.001) and 96% (95% CI, 94% to 97%) for physicians (p=0.0354). GPT-3 triaged (71% correct; 95% CI, 57% to 82%) similarly to lay individuals (74%; 95% CI, 73% to 75%; p=0.73); both were significantly worse than physicians (91%; 95% CI, 89% to 93%; p<0.001). As measured by the Brier score, GPT-3 confidence in its top prediction was reasonably well-calibrated for diagnosis (Brier score = 0.18) and triage (Brier score = 0.22). Conclusions and Relevance: A general-purpose AI language model without any content-specific training could perform diagnosis at levels close to, but below physicians and better than lay individuals. The model was performed less well on triage, where its performance was closer to that of lay individuals.

Early prediction of prostate cancer risk in younger men using polygenic risk scores and electronic health records.

BACKGROUND: Prostate cancer (PCa) screening is not routinely conducted in men aged 55 and younger, although this age group accounts for more than 10% of cases. Polygenic risk scores (PRSs) and patient data applied toward early prediction of PCa may lead to earlier interventions and increased survival. We have developed machine learning (ML) models to predict PCa risk in men 55 and under using PRSs combined with patient data. METHODS: We conducted a retrospective study on 91,106 male patients aged 35-55 using the UK Biobank database. Five gradient boosting models were developed and validated utilizing routine screening data, PRSs, additional clinical data, or combinations of the three. RESULTS: Combinations of PRSs and patient data outperformed models that utilized PRS or patient data only, and the highest performing models achieved an area under the receiver operating characteristic curve of 0.788. Our models demonstrated a substantially lower false positive rate (35.4%) in comparison to standard screening using prostate-specific antigen (60%-67%). CONCLUSION: This study provides the first preliminary evidence for the use of PRSs with patient data in a ML algorithm for PCa risk prediction in men aged 55 and under for whom screening is not standard practice.

General Practice in the Time of COVID-19: A Mixed-Methods Service Evaluation of a Primary Care COVID-19 Service.

Primary care coronavirus disease 2019 (COVID-19) clinics were rapidly introduced across the UK to review potentially infectious patients. Evaluation of these services is needed to guide future implementation. This mixed-methods study evaluates patient demographics, clinical presentation, co-morbidities, service usage, and outcomes for the Islington COVID-19 service (London, UK) and from April to May 2020 and thematically analyses survey responses from 29 service clinicians and 41 GP referrers on their service experience. Of the 237 patients booked into the service, a significant number of referrals (n = 91; 38.6%) were made after the presumed infectious period of 14 days. Almost half of all adult referrals (49%) were dealt with remotely (via telephone/video consultation +/- remote oxygen saturation monitoring). The service was perceived to provide a safe way to see patients; it developed local expertise, learning, and empowerment; and it was a positive teamworking experience. These findings suggest that the management of many patients with COVID-19 symptoms is possible in routine general practice with minimal risk through the implementation of remote consultation methods and in patients who present after the post-infectious period. Additionally, the use of remote saturation monitoring and local GP COVID-19 "experts" can support practices to manage COVID-19 patients. Future primary care COVID-19 services should act as empowerment tools to assist GPs to safely manage their own patients and provide support for GPs in this process.