Cardiopulmonary exercise testing before lung resection surgery:
still indicated? Evaluating predictive utility using machine
learning

J 2026

Cardiopulmonary exercise testing before lung resection surgery: still indicated? Evaluating predictive utility using machine learning

FILAKOVSZKY, Akos; Kristián BRAT; Thomas TSCHOELLITSCH; Štěpán BARTOŠ; Andrej MAZÚR et al.

Základní údaje

Originální název

Cardiopulmonary exercise testing before lung resection surgery: still indicated? Evaluating predictive utility using machine learning

Autoři

FILAKOVSZKY, Akos; Kristián BRAT; Thomas TSCHOELLITSCH; Štěpán BARTOŠ; Andrej MAZÚR; Jens MEIER; Lyle OLSON a Ivan ČUNDRLE

Vydání

THORAX, LONDON, BMJ PUBLISHING GROUP, 2026, 0040-6376

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 7.700 v roce 2024

Označené pro přenos do RIV

Organizační jednotka

Lékařská fakulta

Klíčová slova anglicky

Exercise; Lung Cancer

Štítky

14110122, 14110811

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 16. 2. 2026 09:32, Mgr. Tereza Miškechová

Anotace

V originále

Rationale Despite significant advances in patient care and outcomes, criteria for cardiopulmonary exercise testing (CPET) in risk stratification guidelines for lung resection have not been updated in over a decade. We hypothesised that CPET no longer holds additional predictive value for postoperative complications.Methods In this secondary analysis, we included lung resection candidates from two prospective, multicentre studies eligible for CPET and assessed with preoperative pulmonary function tests (PFTs) and arterial blood gas analysis. Postoperative pulmonary (PPCs) and cardiovascular complications (PCCs) were documented during hospitalisation. We trained five types of machine learning models applying nested cross-validation to predict complications and compared predictive performance based on four metrics, including area under the receiver operating characteristic curve (AUC-ROC).Results A total of 497 patients were included. PPCs developed in 71 (14%) patients. Adding CPET parameters to PFTs and baseline clinical data did not improve the ability of models to predict PPCs in unselected patients (AUC-ROC=0.72-0.78; p=0.47), nor in those meeting American College of Chest Physicians (ACCPs) (n=236; AUC-ROC=0.64-0.78; p=0.70) or European Respiratory Society/European Society of Thoracic Surgery (ERS/ESTS) criteria (n=168; AUC-ROC=0.59-0.76; p=0.92). PCCs developed in 90 (18%) patients. CPET parameters likewise did not improve model performance for the prediction of PCCs in unselected patients (AUC-ROC=0.65-0.73; p=0.96), nor in the ACCP (AUC-ROC=0.61-0.73; p=0.82) or ERS/ESTS subgroups (AUC-ROC=0.62-0.69; p=0.87).Conclusions In contemporary surgical practice, CPET did not improve the predictive performance of machine learning models for PPCs or PCCs in patients with an indication based on established guidelines or in those without. The role of CPET in preoperative risk stratification for lung resection should be re-evaluated.Trial registration number NCT03498352, NCT04826575.

Návaznosti

MUNI/A/1447/2024, interní kód MU

Název: Využití parametrů dýchání v klidu, během zátěže a během spánku pro predikci perioperačnícho outcome a optimalizaci.

Investor: Masarykova univerzita, Využití parametrů dýchání v klidu, během zátěže a během spánku pro predikci perioperačnícho outcome a optimalizaci.

Citovat

FILAKOVSZKY, Akos; Kristián BRAT; Thomas TSCHOELLITSCH; Štěpán BARTOŠ; Andrej MAZÚR; Jens MEIER; Lyle OLSON a Ivan ČUNDRLE. Cardiopulmonary exercise testing before lung resection surgery: still indicated? Evaluating predictive utility using machine learning. THORAX. LONDON: BMJ PUBLISHING GROUP, 2026, 9 s. ISSN 0040-6376. Dostupné z: https://doi.org/10.1136/thorax-2024-221485.

@article{2531004,
   author = {Filakovszky, Akos and Brat, Kristián and Tschoellitsch, Thomas and Bartoš, Štěpán and Mazúr, Andrej and Meier, Jens and Olson, Lyle and Čundrle, Ivan},
   article_location = {LONDON},
   doi = {https://doi.org/10.1136/thorax-2024-221485},
   keywords = {Exercise; Lung Cancer},
   language = {eng},
   issn = {0040-6376},
   journal = {THORAX},
   title = {Cardiopulmonary exercise testing before lung resection surgery: still indicated? Evaluating predictive utility using machine learning},
   url = {https://thorax.bmj.com/content/early/2025/10/02/thorax-2024-221485},
   year = {2026}
}

TY  - JOUR
ID  - 2531004
AU  - Filakovszky, Akos - Brat, Kristián - Tschoellitsch, Thomas - Bartoš, Štěpán - Mazúr, Andrej - Meier, Jens - Olson, Lyle - Čundrle, Ivan
PY  - 2026
TI  - Cardiopulmonary exercise testing before lung resection surgery: still indicated? Evaluating predictive utility using machine learning
JF  - THORAX
PB  - BMJ PUBLISHING GROUP
SN  - 00406376
KW  - Exercise
KW  - Lung Cancer
UR  - https://thorax.bmj.com/content/early/2025/10/02/thorax-2024-221485
N2  - Rationale Despite significant advances in patient care and outcomes, criteria for cardiopulmonary exercise testing (CPET) in risk stratification guidelines for lung resection have not been updated in over a decade. We hypothesised that CPET no longer holds additional predictive value for postoperative complications.Methods In this secondary analysis, we included lung resection candidates from two prospective, multicentre studies eligible for CPET and assessed with preoperative pulmonary function tests (PFTs) and arterial blood gas analysis. Postoperative pulmonary (PPCs) and cardiovascular complications (PCCs) were documented during hospitalisation. We trained five types of machine learning models applying nested cross-validation to predict complications and compared predictive performance based on four metrics, including area under the receiver operating characteristic curve (AUC-ROC).Results A total of 497 patients were included. PPCs developed in 71 (14%) patients. Adding CPET parameters to PFTs and baseline clinical data did not improve the ability of models to predict PPCs in unselected patients (AUC-ROC=0.72-0.78; p=0.47), nor in those meeting American College of Chest Physicians (ACCPs) (n=236; AUC-ROC=0.64-0.78; p=0.70) or European Respiratory Society/European Society of Thoracic Surgery (ERS/ESTS) criteria (n=168; AUC-ROC=0.59-0.76; p=0.92). PCCs developed in 90 (18%) patients. CPET parameters likewise did not improve model performance for the prediction of PCCs in unselected patients (AUC-ROC=0.65-0.73; p=0.96), nor in the ACCP (AUC-ROC=0.61-0.73; p=0.82) or ERS/ESTS subgroups (AUC-ROC=0.62-0.69; p=0.87).Conclusions In contemporary surgical practice, CPET did not improve the predictive performance of machine learning models for PPCs or PCCs in patients with an indication based on established guidelines or in those without. The role of CPET in preoperative risk stratification for lung resection should be re-evaluated.Trial registration number NCT03498352, NCT04826575.
ER  -

FILAKOVSZKY, Akos; Kristián BRAT; Thomas TSCHOELLITSCH; Štěpán BARTOŠ; Andrej MAZÚR; Jens MEIER; Lyle OLSON a Ivan ČUNDRLE. Cardiopulmonary exercise testing before lung resection surgery: still indicated? Evaluating predictive utility using machine learning. \textit{THORAX}. LONDON: BMJ PUBLISHING GROUP, 2026, 9 s. ISSN~0040-6376. Dostupné z: https://doi.org/10.1136/thorax-2024-221485.

Přehled o publikaci