Newest papers

ECG for laboratory values:A comprehensive physiological and technical analysis

Walentin Palanchuk · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28507 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

ECG broader validasi pengukuran laboratorium penting untuk pengambilan keputusan klinis tetapi biasanya memerlukan pengambilan sampel darah invasif. Penelitian terbaru menunjukkan bahwa rekaman ECG mungkin berisi informasi di luar ritme jantung dan memberikan informasi terkait dengan nilai-nilai laboratorium. Tesis ini menyelidiki prediksi NT-proBNP dari rekaman ECG dan metadata pasien menggunakan kerangka kerja pembelajaran mendalam multimodal, sementara mempertimbangkan keandalan fisiologis dari prediksi berbasis ECG. Ini juga membandingkan konfigurasi 1-lead menggunakan lead II dengan konfigurasi 12-lead yang sesuai. eksperimen tambahan pada glukosa, hemoglobin, dan potassium disajikan dalam lampiran. Regresi, klasifikasi biner independen, dan eksperimen klasifikasi tiga kelas dilakukan menggunakan MIMIC-IV, dengan tugas tiga kelas berdasarkan ambang batas klinis yang ditetapkan

Machine translation (Meta M2M100); the English original follows.

Abstract

Laboratory measurements are essential for clinical decision making but typically require invasive blood sampling. Recent research suggests that ECG recordings may contain information beyond cardiac rhythm and provide information related to laboratory values. This thesis investigates NT-proBNP prediction from ECG recordings and patient metadata using a multimodal deep learning framework, while considering the physiological plausibility of ECG-based prediction. It also compares a 1-lead configuration using lead II with the corresponding 12-lead configuration. Additional experiments on glucose, hemoglobin, and potassium are presented in the appendix. Regression, binary classification, and three-class classification experiments were conducted using MIMIC-IV, with the three-class task based on clinically established thresholds. The 12-lead configuration consistently achieved better performance. Regression reached a mean absolute error of 534.98 pg/mL for 1-lead and 514.27 pg/mL for 12-lead. Binary classification achieved AUROCs of 0.849 and 0.876, respectively, while three-class classification achieved macro-averaged AUROCs of 0.738 and 0.752. The results indicate that precise NT-proBNP regression remains challenging, whereas broader concentration ranges can be classified more effectively. The findings are consistent with the physiological hypothesis that ECG characteristics and NT-proBNP concentrations reflect shared cardiovascular processes. ECG-based NT-proBNP prediction may therefore provide complementary information, particularly for classifying broader concentration ranges. However, laboratory measurements remain necessary, and validation on independent datasets is required.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Artificial intelligence, Binary classification, Computer science, Regression analysis, Regression, Machine learning

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange