TY - GEN
T1 - Towards Development of Natural Language Processing Model to Support Infertility Treatment Planning in Poland
AU - Zamojski, Dawid
AU - Pudelko, Adam
AU - Gajewska-Kucharek, Alicja
AU - Marczyk, Michal
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - Infertility treatment begins with an interview, during which all medical information related to the patient’s history and diagnostic test results are collected. Next, a physician may determine the most appropriate direction for further treatment. We hypothesize that a task-specific deep learning (DL) model could support clinical decisions. However, there is a lack of Polish medical language corpus and language-specific medical DL models. Thus, we tested three general-use Natural Language Processing (NLP) models trained on Polish word collections: (i) bert-base-polish-cased-v1; (ii) herbert-base-cased; (iii) polish-roberta-base-v2. We evaluated the efficacy of the models using 80 Electronic Health Records (EHRs) with information obtained during the medical interview to predict the future stages of infertility treatment. The best Polish medical text classification model was the bert-base-polish-cased-v1 trained on pre-processed data. The lack of a Polish medical corpus decreased the results’ interpretability. Nevertheless, we believe that thanks to the developed model, it will be possible to estimate the pregnancy and decisions on the choice of treatment method more precisely.
AB - Infertility treatment begins with an interview, during which all medical information related to the patient’s history and diagnostic test results are collected. Next, a physician may determine the most appropriate direction for further treatment. We hypothesize that a task-specific deep learning (DL) model could support clinical decisions. However, there is a lack of Polish medical language corpus and language-specific medical DL models. Thus, we tested three general-use Natural Language Processing (NLP) models trained on Polish word collections: (i) bert-base-polish-cased-v1; (ii) herbert-base-cased; (iii) polish-roberta-base-v2. We evaluated the efficacy of the models using 80 Electronic Health Records (EHRs) with information obtained during the medical interview to predict the future stages of infertility treatment. The best Polish medical text classification model was the bert-base-polish-cased-v1 trained on pre-processed data. The lack of a Polish medical corpus decreased the results’ interpretability. Nevertheless, we believe that thanks to the developed model, it will be possible to estimate the pregnancy and decisions on the choice of treatment method more precisely.
KW - Deep learning
KW - Infertility treatment
KW - Natural language processing models
KW - Polish electronic health records
KW - Text pre-processing
UR - https://www.scopus.com/pages/publications/105023591767
U2 - 10.1007/978-3-032-08455-2_21
DO - 10.1007/978-3-032-08455-2_21
M3 - Conference contribution
AN - SCOPUS:105023591767
SN - 9783032084545
T3 - Lecture Notes in Computer Science
SP - 278
EP - 291
BT - Bioinformatics and Biomedical Engineering - 12th International Conference, IWBBIO 2025, Proceedings
A2 - Rojas, Ignacio
A2 - Ortuño, Francisco
A2 - Rojas Ruiz, Fernando
A2 - Herrera, Luis Javier
A2 - Valenzuela, Olga
A2 - Escobar, Juan José
PB - Springer Science and Business Media Deutschland GmbH
T2 - 12th International Work-Conference on Bioinformatics and Biomedical Engineering, IWBBIO 2025
Y2 - 16 July 2025 through 18 July 2025
ER -