Találati lista | Tudóstér

001-es BibID:	BIBFORM129679
035-os BibID:	(scopus)105007989236 (wos)001507622500001
Első szerző:	Berzi András
Cím:	NLP-based removal of personally identifiable information from Hungarian electronic health records / András Berzi, Ervin Berényi, Zita Képes, Barnabás Antal, Ábrahám Gergely Varga, Miklós Emri
Dátum:	2025
ISSN:	2624-8212
Megjegyzések:	Introduction: Electronic health records (EHR) in text format serve as crucial resources for datadriven medical research. To safeguard patient confidentiality, under the General Data Protection Regulation (GDPR), strict measures are required to ensure personal data is anonymized or pseudonymized to protect individual privacy. Natural language processing has consistently proven effective in automating the de-identification of sensitive information.We present spaCy models to recognize personally identifiable information (PII) from a wide range of free-text medical records written in Hungarian, a low-resource language. To develop this model, we compiled a corpus of clinical documents by annotating sensitive information within electronic health records sourced from the University of Debrecen. To simplify the annotation process, we preannotated the documents using a rule-based method. The corpora comprises over 15,000 documents and includes more than 90,000 instances of PII. We trained several models using this corpus and also developed a separate validation corpus to assess their performance.The performance evaluation of the de-identification models on the developed corpora resulted in F1-scores ranging from 0.9697 to 0.9926. On the validation corpora, the F1-scores ranged from 0.9772 to 0.9867, demonstrating that the models can effectively handle previously unseen examples. Our risk analysis revealed that 99.67% of the sensitive information was successfully removed from the validation dataset.The results indicate that similarly to other state-of-the-art systems our model is highly effective at identifying PII in clinical texts, guaranteeing that sensitive information in clinical documents can be protected without sacrificing the quality or usability of the data for research purposes. Despite these positive outcomes, several areas remain to be improved, such as the conduction of additional testing on diverse datasets, particularly those from different healthcare institutions. With ongoing refinements, these models have the potential to greatly enhance the efficiency of data de-identification processes, ensuring compliance with privacy regulations while promoting the secure sharing of medical data for scientific progress.
Tárgyszavak:	Orvostudományok Egészségtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk de-identification Electronic Health Records (EHR) General Data Protection Regulation (GDPR) Hungarian Low-resource language Named Entity Recognition (NER) natural language processing (NLP)
Megjelenés:	Frontiers in Artificial Intelligence. - 8 (2025), p. 1-10. -
További szerzők:	Berényi Ervin (1964-) (radiológus) Képes Zita (1991-) (orvos) Antal Barnabás Varga Ábrahám Gergely (1982-) (jogász) Emri Miklós (1962-) (fizikus)
Pályázati támogatás:	TKP2021-NKTA-34 Egyéb
Internet cím:	Intézményi repozitóriumban (DEA) tárolt változat DOI
Borító:
Saját polcon:

001-es BibID:	BIBFORM131029
Első szerző:	Egeresi Lilla (radiográfus)
Cím:	Relationship Between Effective Dose, Alternative Metrics, and SSDE : experiences with Two CT Dose-Monitoring Systems / Egeresi Lilla Szatmáriné, Urbán László, Dankó Zsolt, Balázs Ervin, Berényi Ervin, Marosi Mária, Kiss János, Bágyi Péter, Képes Zita, Emri Miklós, Balkay László
Dátum:	2025
ISSN:	2075-4418
Megjegyzések:	Background: We assessed the frequency and causes of discrepancies in CT dose indices such as dose-length product (DLP), size-specific dose estimate (SSDE), and effective dose (ED), as calculated by CT dose-monitoring systems. Our secondary aim was to demonstrate the estimation of size-specific ED (SED) from the patients' dose records. Methods: The retrospective study included dosimetric data of 79,383 consecutive CT exams performed on two CT scanners. The following dose values were recorded from both the locally developed dose-monitoring system (DMS) and a commercial dose-monitoring program (DWTM): DLP, SSDE, and ED. Only the DMS provided bodyweight-corrected effective dose (SEDDMS) and the SED based on previous published data. Results: Without body-region-specific analysis, there were no tendentious differences between the DLP, ED, or SSDE values obtained from DWTM and DMS. However, the body region-based correlation revealed substantial differences between EDDMS and EDDW, primarily related to inadequate identification of the body. SSDE showed strong correlation to each anatomical category and CT device, except for the head region, where inadequate consideration of CT inclination was the reason for the biased SSDEDW value. Furthermore, by analyzing the SEDDMS, SSDE, and SED correlations, we concluded that SEDDMS is a promising figure for estimating the SED value. Conclusions: SED provides suitable supplementary size-specific dose data to SDDE and may be a preferable choice for estimating cumulative doses in routine radiological practice.
Tárgyszavak:	Orvostudományok Elméleti orvostudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk computed tomography (CT) dose-monitoring system (DMS) effective dose (ED) size-specific dose estimate (SSDE) size-specific effective dose (SED)
Megjelenés:	Diagnostics. - 15 : 13 (2025), p. 1-15. -
További szerzők:	Urbán László (1960-) Dankó Zsolt (1991-) (fizikus) Balázs Ervin Berényi Ervin (1964-) (radiológus) Marosi Mária (1990-) (radiográfus) Kiss János (1992-) (fizikus) Bágyi Péter (1964-) (radiológus) Képes Zita (1991-) (orvos) Emri Miklós (1962-) (fizikus) Balkay László (1963-) (biofizikus)
Pályázati támogatás:	TKP2021-NKTA-34 Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM082873
035-os BibID:	(WOS)000505064300029 (Scopus)85077463101
Első szerző:	Papp Tamás (orvos)
Cím:	Disorders of neural crest derivates in oncoradiological practice / Papp Tamas, Ferenczi Zsuzsanna, Petro Matyas, Meszar Zoltan, Kepes Zita, Berenyi Ervin
Dátum:	2019
ISSN:	2218-676X 2219-6803
Megjegyzések:	Hundreds of articles discuss the imaging characteristics and molecular background of prominent gastrointestinal (GI) motility disorders and tumors of the peripheral nervous system, but according to our knowledge an article focusing on the classification and developmental background of these heterogeneous diseases is not to be found. Our aim is to give insight on the common features of several diseases and tumors, starting with their common source of origin, the neural crest (NC). The NC is a transient cell population of the embryo, which differentiates into several organs/structures of our body (sympathetic trunk, adrenal medulla). Although the incidence of the individual tumors of NC cells is not high by themselves, the summation of these incidences may be relevant in the daily routine. In the introduction we mention the most prominent developmental routes and molecular pathways of NC cells, which is crucial to understand the pathogenesis and the wide range of involved cell types from the colon to the adrenal gland. We summarized the most important, useful pathological findings and imaging techniques from the X-ray to the positron emission tomography-computed tomography (CT) in order to help the identification of these diseases. This article may help to better understand NC lineage and its unique, diverse role during ontogeny, which may influence the radiologists to change several convictions, or understand better the background and/or connections of a wide range of tumors and syndromes.
Tárgyszavak:	Orvostudományok Klinikai orvostudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk Developmental disorders embryology neural crest (NC) oncology radiology
Megjelenés:	Translational Cancer Research. - 8 : 8 (2019), p. 2916-2923. -
További szerzők:	Winkler-Ferenczi Zsuzsanna Petró Mátyás (1985-) (radiológus) Mészár Zoltán Mihály (1977-) (agrármérnök, biotechnológus) Képes Zita (1991-) (orvos) Berényi Ervin (1964-) (radiológus)
Pályázati támogatás:	KTIA_NAP_13-1-2013-0001 Egyéb 2017-1.2.1-NKP-2017-00002 Egyéb NKFI-108467 OTKA
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: