TY - GEN
T1 - The Scope of In-Context Learning for the Extraction of Medical Temporal Constraints
AU - Seegmiller, Parker
AU - Gatto, Joseph
AU - Basak, Madhusudan
AU - Cook, Diane
AU - Ghasemzadeh, Hassan
AU - Stankovic, John
AU - Preum, Sarah
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Medications often impose temporal constraints on everyday patient activity. Violations of such medical temporal constraints (MTCs) lead to a lack of treatment adherence, in addition to poor health outcomes and increased healthcare expenses. These MTCs are found in drug usage guidelines (DUGs) in both patient education materials and clinical texts. Computationally representing MTCs in DUGs will advance patient-centric healthcare applications by helping to define safe patient activity patterns. We define a novel taxonomy of MTCs found in DUGs and develop a novel context-free grammar (CFG) to computationally represent MTCs from unstructured DUGs. Additionally, we release three new datasets with a combined total of N =836 DUGs labeled with normalized MTCs. We develop an in-context learning (ICL) solution for automatically extracting and normalizing MTCs found in DUGs, achieving an average F1 score of 0.62 across all datasets. Finally, we rigorously investigate ICL model performance against a baseline model, across datasets and MTC types, and through in-depth error analysis.
AB - Medications often impose temporal constraints on everyday patient activity. Violations of such medical temporal constraints (MTCs) lead to a lack of treatment adherence, in addition to poor health outcomes and increased healthcare expenses. These MTCs are found in drug usage guidelines (DUGs) in both patient education materials and clinical texts. Computationally representing MTCs in DUGs will advance patient-centric healthcare applications by helping to define safe patient activity patterns. We define a novel taxonomy of MTCs found in DUGs and develop a novel context-free grammar (CFG) to computationally represent MTCs from unstructured DUGs. Additionally, we release three new datasets with a combined total of N =836 DUGs labeled with normalized MTCs. We develop an in-context learning (ICL) solution for automatically extracting and normalizing MTCs found in DUGs, achieving an average F1 score of 0.62 across all datasets. Finally, we rigorously investigate ICL model performance against a baseline model, across datasets and MTC types, and through in-depth error analysis.
KW - health
KW - health nlp application
KW - information extraction
KW - medication information extraction
KW - natural language processing
KW - temporal information extraction
UR - http://www.scopus.com/inward/record.url?scp=85181570816&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85181570816&partnerID=8YFLogxK
U2 - 10.1109/ICHI57859.2023.00107
DO - 10.1109/ICHI57859.2023.00107
M3 - Conference contribution
AN - SCOPUS:85181570816
T3 - Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023
SP - 601
EP - 609
BT - Proceedings - 2023 IEEE 11th International Conference on Healthcare Informatics, ICHI 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 11th IEEE International Conference on Healthcare Informatics, ICHI 2023
Y2 - 26 June 2023 through 29 June 2023
ER -