Large Language Models for Optimizing Patient Recruitment Decisions in Voice Data Generation Projects.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Anibal James, Nama Geetha Krishna Chaitanya, Ganesh Shrramana, Nafii Yosef, Cruz Samantha Salvi, Daoud Veronica, Zanin Madeleine, Le Tram, Khorrami Parsa, Wood Bradford J, Clifton David, Toghranegar Jamie, Bensoussan Yael, Bensoussan Yael E, Elemento Olivier, Bélisle-Pipon Jean-Christophe, Dorr David, Ghosh Satrajit, Johnson Alistair, Payne Phillip, Powell Maria E, Rameau Anaïs, Ravitsky Vardit, Sigaras Alexandros, Awan Shaheen, Bahr Ruth, Bolser Donald, Jenkins Kathy J, Rudzicz Frank, Siu Jennifer, Watts Stephanie, Abdel-Aty Yassmeen, Syed Toufeeq Ahmed, Anibal James, Bedrick Steven, Bevers Isaac, Boyer Micah, Brito Rahul, Casalino Selina A, Costello John, Diaz-Ocampo Enrique, Elmahdy Mahmoud, Fletcher Kenneth, Gelbard Alexander, Hanna Karim, Hersh Bill, Jayachandran Lochana, Jenney Kaley, Krussel Andrea, Loewith Chloe, Neal Tempestt, Premi-Bortolotto Claire, Rohde Sarah, Cruz Samantha Salvi, Silberholz Elizabeth, Sutherland Duncan, Talluri Venkata Swarna Mukhi, Toghranegar Jamie, Vinson Kimberly, Wilson Claire, Zanin Madeleine, Zesiewicz Theresa, Zhao Robin
Аннотация
METHODS: The publicly available GOSSIS-1-eICU dataset was filtered to create patient populations that were relevant to voice data generation projects. Lab results and vital signs from the electronic health record were also used to train a neural network for prediction of disease type. Prediction uncertainty estimates were included in the dataset as approximate indicators of health complexity. To select the best recruitment choice for addressing imbalances, an open-source large language model (LLM) was then instructed to assess dataset statistics and the characteristics of possible participants. Simulations were run in which the system constructed datasets of 250 patients.
RESULTS: In over 90% of cases, the proposed system reduced categorical imbalances and widened continuous distributions when compared to randomly sampled counterfactual datasets (q-value < 0.05). Variables included race, age, BMI, sex, disease type, oxygenation status, co-morbidities, post-operative status, Glasgow Coma Scale verbal response score, the Acute Physiology Score III, prediction uncertainty, vital signs, and lab results.
CONCLUSION: LLMs may provide useful, explainable recommendations when presented with dataset distribution statistics and candidate profiles. In the future, this simulated scenario may be extended to align with conditions in emergency departments or other high-volume settings.
LEVEL OF EVIDENCE: 3.