Response to Letter to the Editor - Machine-learning model for postoperative atrial fibrillation

Sep 29, 2026

Response to an editorial letter addressing a machine-learning study predicting postoperative atrial fibrillation (POAF) after coronary artery bypass grafting (CABG). The authors clarify the exploratory, hypothesis-generating intent rather than creating a definitive clinical tool, discuss limitations from sample size and events-per-variable ratio, and explain the 50/50 sampling strategy and algorithm choices including PDA and an explainable DT method. The response emphasizes calibration, external validation, TRIPOD-AI reporting, and acknowledges feasibility for future biomarker-focused research.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages2

Reading Time5 min

AccessFree to download

Response to Letter to the Editor: Machine-learning model for postoperative atrial fibrillation

Study intent and objectives

Limitations and validation needs

Sampling strategy and algorithm explainability

Reporting guidance and study conclusions

Turkish Journal of Thoracic and Cardiovascular Surgery 2025;33(4):592-593 Letter to the Edıtor / Editöre Mektup Response to Letter to the Editor: Machine-learning model for postoperative atrial fibrillation Editöre mektuba yanıt: Postoperatif atriyal fibrilasyon için makine-öğrenimi modeli Birkan Akbulut1􀀬, Mustafa Çakır2􀀬, Mustafa Görkem Sarıkaya1􀀬, Okan Oral3􀀬, Mesut Yılmaz3􀀬, Güzin Aykal4􀀬 Institution where the research was done: Antalya Training and Research Hospital, Antalya, Türkiye Author Affiliations: 1Department of Cardiovascular Surgery, Antalya Training and Research Hospital, Antalya, Türkiye 2İskenderun Technical University, İskenderun Vocational School of Higher Education, İskenderun, Hatay, Türkiye 3Faculty of Engineering, Akdeniz University, Antalya, Türkiye 4Department of Biochemistry, Antalya Training and Research Hospital, Antalya, Türkiye We sincerely thank for thoughtful and constructive comments regarding our recent study on the use of machine learning to predict postoperative atrial fibrillation (POAF) after coronary arter bypass grafting (CABG) . [1] We greatly appreciate detailed methodological evaluation and the opportunity to clarify several important points . [2] As stated in our original article, this work represents our institution’s initial experience with clinical prediction modeling using machine learning. Our primary objective was not to establish a definitive clinical tool, but rather to explore the predictive potential of routinely available biomarkers, assess their relative importance, and propose preliminary threshold values that could guide future investigations . We fully acknowledge that our sample size was limited and that the events-per-variable ratio was below the ideal threshold for stable model estimation . This limitation was explicitly discussed in our paper. We view our findings as hypothesis-generating and foundational for larger, multi-center studies . These forthcoming studies should aim to achieve more robust calibration and external validation, as recommended in our article. Regarding the balanced 50/50 sampling strategy, we recognize that this approach may affect calibration and could lead to optimistic accuracy estimates . Our intent was to explore model performance under controlled class balance, not to simulate real-world prevalence. Concerning the choice of algorithms, includingthe Probabilistic Data Association (PDA) classifier, our goal was to test a range of classification approaches during this exploratory phase. We fully agree that explainability and transparency using methods such as SHAP or feature importance visualization are critical for clinical translation . However, in addition to the black-box methods, we also used an explainable method (DT) in our study. Among these, the DT, which is transparent and explainable, was the most successful, as shown in Figure 3. We recognize importance of TRIPOD-AI reporting guidance. Thus, in the conclusion section of our study, this issue was highlighted, and we recommended that researchers refine machine learning models in future studies . In the last paragraph of our article, we acknowledged the limitations highlighted in the critique and stated: “Our study findings suggest that preoperative levels of magnesium, albumin, and total iron-binding capacity may help to predict POAF risk. Corresponding author: Birkan Akbulut. E-mail: [birkan.akbulut@gmail.com](birkan.akbulut@gmail.com) [Doi: 10.5606/tgkdc.dergisi.2025.95348](Doi: 10.5606/tgkdc.dergisi.2025.95348) [Received:](Received: October 10)[ October 10](Received: October 10) , 2025 Accepted: October 11, 2025 Published online: October 20, 2025 Cite this article as: Akbulut B, Çakır M, Sarıkaya MG, Oral O, Yılmaz M, Aykal G. Response to Letter to the Editor: Machine-learning model for postoperative atrial fibrillation. Turk Gogus Kalp Dama 2025;33(4):592-593 . doi: 10.5606/ tgkdc.dergisi.2025.95348 . ©2025 All right reserved

FAQs

What was the primary objective of the authors’ machine-learning work for POAF after CABG?

To explore the predictive potential of routinely available biomarkers, assess their relative importance, and propose preliminary threshold values for future studies rather than establish a definitive clinical tool.

How did the authors address limitations in model estimation?

They acknowledged limited sample size and an events-per-variable ratio below ideal thresholds, describing the findings as hypothesis-generating for larger multi-center work requiring stronger calibration and external validation.

What approaches were used to handle interpretability in the model?

Alongside black-box methods, the authors used an explainable decision tree (DT), which they reported as the most successful option, and they noted that explainability and transparency methods such as SHAP or feature-importance visualization are important for clinical translation.

Sep 29, 2026

Upload by Olivia Brown