ACAdrián Csiszárik

Adrián Csiszárik

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Adrián Csiszárik has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Health Former: Dual-Level Time-Aware Transformers for Irregular Electronic Health Record Events

    by Péter Kőrösi Szabó, Gábor Kovács, Botond Forrai, Judit Laki, Tamás Kováts, Miklós Szócska, Adrián Csiszárik

    Background and Objectives: Longitudinal electronic health records (EHRs) form irregular event sequences that mix multiple clinical coding systems and care settings. Learning transferable patient representations requires modeling both within-encounter code composition and long-range temporal dependencies. We aim to develop a pretraining framework that preserves event structure and explicitly uses elapsed time, while remaining straightforward to fine-tune for new supervised endpoints without task-specific feature engineering. Methods: We propose HealthFormer, a dual-level Transformer for event-centric EHR modeling. An Intra-Event Encoder aggregates heterogeneous domain tokens within each typed clinical event into an event embedding via code-specific embedding modules and attention pooling. Event embeddings are combined with a Date Encoder and a continuous-time attention bias based on attention with linear biases (ALiBI) inside an Inter-Event Encoder. We pretrain on Hungarian national administrative health records from a large-scale nationwide longitudinal cohort (spanning millions of individuals over a decade) using multi-task self-supervision with (i) per-domain masked token prediction (masked language modeling, MLM), (ii) event-type prediction under full-event masking (Event-level MLM), (iii) next-event type prediction, and (iv) time-to-next-event (Δt) regression.Results: Pretraining induces hierarchy-consistent organization in learned diagnosis (ICD-10) embedding geometry conducive to analysis and interpretation. On incident cancer prediction, end-to-end fine-tuning achieves test AUCs of 0.81/0.75/0.73 for colorectal cancer (CRC) and 0.94/0.87/0.84 for prostate cancer across 30/60/90-day horizons on balanced cohorts, outperforming logistic-regression baselines, including time-decayed bag-of-codes.Conclusions: HealthFormer provides an event-centric, time-aware representation that transfers via standard fine-tuning without endpoint-specific designs. Using ICD-10 diagnoses and ATC codes can facilitate adoption beyond Hungary. Learned diagnosis embeddings align with the hierarchy, enabling clinical inspection. Broader benchmarking across endpoints remains needed.

  • Open Access

    HealthFormer: Dual-level time-aware Transformers for irregular electronic health record events

    by Péter Kőrösi-Szabó, Gábor Kovács, Botond Forrai, Judit Laki, Tamás Kováts, Miklós Szócska, Adrián Csiszárik

    Longitudinal electronic health records (EHRs) form irregular event sequences that mix multiple clinical coding systems and care settings. Learning transferable patient representations requires modeling both within-encounter code composition and long-range temporal dependencies. We aim to develop a pretraining framework that preserves event structure and explicitly uses elapsed time, while remaining straightforward to fine-tune for new supervised endpoints without task-specific feature engineering. We propose HealthFormer, a dual-level Transformer for event-centric EHR modeling. An Intra-Event Encoder aggregates heterogeneous domain tokens within each typed clinical event into an event embedding via code-specific embedding modules and attention pooling. Event embeddings are combined with a Date Encoder and a continuous-time attention bias based on attention with linear biases (ALiBI) inside an Inter-Event Encoder . We pretrain on Hungarian national administrative health records from a large-scale nationwide longitudinal cohort (spanning millions of individuals over a decade) using multi-task self-supervision with (i) per-domain masked token prediction (masked language modeling, MLM), (ii) event-type prediction under full-event masking (Event-level MLM), (iii) next-event type prediction, and (iv) time-to-next-event (Δ t ) regression. Pretraining induces hierarchy-consistent organization in learned diagnosis (ICD-10) embedding geometry conducive to analysis and interpretation. On incident cancer prediction, end-to-end fine-tuning achieves test AUCs of 0.81/0.75/0.73 for colorectal cancer (CRC) and 0.94/0.87/0.84 for prostate cancer across 30/60/90-day horizons on balanced cohorts, outperforming logistic-regression baselines, including time-decayed bag-of-codes. HealthFormer provides an event-centric, time-aware representation that transfers via standard fine-tuning without endpoint-specific designs. Using ICD-10 diagnoses and ATC codes can facilitate adoption beyond Hungary. Learned diagnosis embeddings align with the hierarchy, enabling clinical inspection. Broader benchmarking across endpoints remains needed.

  • Open Access

    Mode combinability: Exploring convex combinations of permutation aligned models

    by Adrián Csiszárik, Melinda F. Kiss, Péter Kőrösi-Szabó, Márton Muntag, Gergely Papp, Dániel Varga


  • The density of planar sets avoiding unit distances

    by Gergely Ambrus, Adrián Csiszárik, Máté Matolcsi, Dániel Varga, Pál Zsámboki


  • Open Access

    The density of planar sets avoiding unit distances

    by Gergely Ambrus, Adrián Csiszárik, Máté Matolcsi, Dániel Varga, Pál Zsámboki

    By improving upon previous estimates on a problem posed by L. Moser, we prove a conjecture of Erd\H{o}s that the density of any measurable planar set avoiding unit distances cannot exceed $1/4$. Our argument implies the upper bound of $0.2470$.