Deep Learning Analysis of Polish Electronic Health Records for
Diagnosis Prediction in Patients with Cardiovascular Diseases

J 2022

Deep Learning Analysis of Polish Electronic Health Records for Diagnosis Prediction in Patients with Cardiovascular Diseases

ANETTA, Krištof, Aleš HORÁK, Tomasz JADCZYK, Wojciech WOJAKOWSKI, Krystian WITA et. al.

Základní údaje

Originální název

Deep Learning Analysis of Polish Electronic Health Records for Diagnosis Prediction in Patients with Cardiovascular Diseases

Autoři

ANETTA, Krištof (703 Slovensko, domácí), Aleš HORÁK (203 Česká republika, domácí), Tomasz JADCZYK (616 Polsko), Wojciech WOJAKOWSKI (616 Polsko) a Krystian WITA (616 Polsko)

Vydání

Journal of Personalized Medicine, Basel, MDPI, 2022, 2075-4426

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10200 1.2 Computer and information sciences

Stát vydavatele

Švýcarsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 3.508 v roce 2021

Kód RIV

RIV/00216224:14330/22:00125875

Organizační jednotka

Fakulta informatiky

DOI

http://dx.doi.org/10.3390/jpm12060869

UT WoS

000818311800001

Klíčová slova anglicky

electronic health records; deep learning; text analysis; diagnosis prediction; Polish language

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 6. 4. 2023 10:01, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

Electronic health records naturally contain most of the medical information in the form of doctor’s notes as unstructured or semi-structured texts. Current deep learning text analysis approaches allow researchers to reveal the inner semantics of text information and even identify hidden consequences that can offer extra decision support to doctors. In the presented article, we offer a new automated analysis of Polish summary texts of patient hospitalizations. The presented models were found to be able to predict the final diagnosis with almost 70% accuracy based just on the patient’s medical history (only 132 words on average), with possible accuracy increases when adding further sentences from hospitalization results; even one sentence was found to improve the results by 4%, and the best accuracy of 78% was achieved with five extra sentences. In addition to detailed descriptions of the data and methodology, we present an evaluation of the analysis using more than 50,000 Polish cardiology patient texts and dive into a detailed error analysis of the approach. The results indicate that the deep analysis of just the medical history summary can suggest the direction of diagnosis with a high probability that can be further increased just by supplementing the records with further examination results.

Návaznosti

EF19_073/0016943, projekt VaV

Název: Interní grantová agentura Masarykovy univerzity

LM2018101, projekt VaV

Název: Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy (Akronym: LINDAT/CLARIAH-CZ)

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, LINDAT/CLARIAH-CZ - Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy

MUNI/IGA/1326/2021, interní kód MU

Název: New Horizons of Electronic Health Record Analysis using Deep Learning (Akronym: Health Record Analysis using Deep Learning)

Investor: Masarykova univerzita, New Horizons of Electronic Health Record Analysis using Deep Learning

Citovat

ANETTA, Krištof, Aleš HORÁK, Tomasz JADCZYK, Wojciech WOJAKOWSKI a Krystian WITA. Deep Learning Analysis of Polish Electronic Health Records for Diagnosis Prediction in Patients with Cardiovascular Diseases. Journal of Personalized Medicine. Basel: MDPI, 2022, roč. 12, č. 6, s. 1-17. ISSN 2075-4426. Dostupné z: https://dx.doi.org/10.3390/jpm12060869.

@article{1855618,
   author = {Anetta, Krištof and Horák, Aleš and Jadczyk, Tomasz and Wojakowski, Wojciech and Wita, Krystian},
   article_location = {Basel},
   article_number = {6},
   doi = {http://dx.doi.org/10.3390/jpm12060869},
   keywords = {electronic health records; deep learning; text analysis; diagnosis prediction; Polish language},
   language = {eng},
   issn = {2075-4426},
   journal = {Journal of Personalized Medicine},
   title = {Deep Learning Analysis of Polish Electronic Health Records for Diagnosis Prediction in Patients with Cardiovascular Diseases},
   url = {https://www.mdpi.com/2075-4426/12/6/869},
   volume = {12},
   year = {2022}
}

TY  - JOUR
ID  - 1855618
AU  - Anetta, Krištof - Horák, Aleš - Jadczyk, Tomasz - Wojakowski, Wojciech - Wita, Krystian
PY  - 2022
TI  - Deep Learning Analysis of Polish Electronic Health Records for Diagnosis Prediction in Patients with Cardiovascular Diseases
JF  - Journal of Personalized Medicine
VL  - 12
IS  - 6
SP  - 1-17
EP  - 1-17
PB  - MDPI
SN  - 20754426
KW  - electronic health records
KW  - deep learning
KW  - text analysis
KW  - diagnosis prediction
KW  - Polish language
UR  - https://www.mdpi.com/2075-4426/12/6/869
N2  - Electronic health records naturally contain most of the medical information in the form of doctor’s notes as unstructured or semi-structured texts. Current deep learning text analysis approaches allow researchers to reveal the inner semantics of text information and even identify hidden consequences that can offer extra decision support to doctors. In the presented article, we offer a new automated analysis of Polish summary texts of patient hospitalizations. The presented models were found to be able to predict the final diagnosis with almost 70% accuracy based just on the patient’s medical history (only 132 words on average), with possible accuracy increases when adding further sentences from hospitalization results; even one sentence was found to improve the results by 4%, and the best accuracy of 78% was achieved with five extra sentences. In addition to detailed descriptions of the data and methodology, we present an evaluation of the analysis using more than 50,000 Polish cardiology patient texts and dive into a detailed error analysis of the approach. The results indicate that the deep analysis of just the medical history summary can suggest the direction of diagnosis with a high probability that can be further increased just by supplementing the records with further examination results.
ER  -

ANETTA, Krištof, Aleš HORÁK, Tomasz JADCZYK, Wojciech WOJAKOWSKI a Krystian WITA. Deep Learning Analysis of Polish Electronic Health Records for Diagnosis Prediction in Patients with Cardiovascular Diseases. \textit{Journal of Personalized Medicine}. Basel: MDPI, 2022, roč.~12, č.~6, s.~1-17. ISSN~2075-4426. Dostupné z: https://dx.doi.org/10.3390/jpm12060869.

Podrobný výpis o publikaci