PrEventing PostoPERative Pulmonary Complications by Establishing a MachINe-learning assisTed Approach (PEPPERMINT)

Postoperative pulmonary complications (POPC) are common after general anaesthesia and are a major cause of increased morbidity and mortality in surgical patients. However, prevention and treatment methods for POPC that are considered effective, tie up human and technical resources. The aim of the planned research project is therefore to enable reliable identification of high-risk patients on the basis of a tailored machine learning algorithm using perioperative clinical routine data and sonographic imaging data collected in the recovery room. The randomized clinical trial will include 512 patients undergoing elective surgery in general anaesthesia. The primary outcome will be the development of POPC. The goal of the study is to detect postoperative pulmonary complications before they become clinically manifest.

Study Overview

• Status: Recruiting
• Conditions: Postoperative Pulmonary Complications

Detailed Description

The incidence of postoperative pulmonary complications (POPC) is reported to be 9-40%, depending on the surgical procedure. Various preoperative risk factors are known, but usually cannot be modified. A major problem of older publications was that for a long time there existed no clear definition of the outcome parameter "pulmonary complication". It was not until 2018 that a standardised definition was developed by the Standardised Endpoints for Perioperative Medicine (StEP) collaboration. Due to the high clinical relevance - POPC are the main cause of postoperative morbidity and mortality - clinical scoring systems for the preoperative prediction of POPC have been developed, but their predictive quality still needs to be improved. The currently best evaluated score for predicting postoperative pulmonary complications (ARISCAT: Assess Respiratory Risk in Surgical Patients in Catalonia) has sufficient sensitivity but lacks specificity. Therefore, machine learning methods for determining risk from preoperative routine data are also being tested.

Sonography is becoming increasingly important as a non-invasive examination method that can be performed at the bedside. Various sonographic scores and models have already been developed to predict pulmonary complications. Image processing methods and machine learning, in particular deep learning are also increasingly being used in ultrasound diagnostics. A combination of routine clinical data and imaging data to develop a machine learning algorithm has not yet been tested. However, augmented algorithms using pre- and intraoperative clinical information in addition to ultrasound imaging promise better predictive accuracy than the respective individual methods. In addition, prospective clinical evaluation of machine learning algorithm-based prediction models is lacking to date, although they show good values for "area under the receiver operating characteristic" (AUROC), accuracy and precision in the respective test and validation datasets, which are considered common measures of the predictive quality of such models.

Measures for the prevention of POPC are known, but are probably not consistently applied in clinical routine due to the increased demand, especially for human resources. Therefore, the aim of the study is to identify patients at risk of POPC on the basis of a machine learning algorithm.

All patients are undergoing the same study protocol to develop the machine learning model. Perioperative clinical routine data are going to be assessed as per standard. Postoperatively, a standardized lung sonography is going to be performed in the recovery room. Patients will then be visited on the ward on postoperative day 1, 3 and 7 for clinical examination to detect POPC according to the criteria elaborated by the StEP- collaboration.

According to the case number calculation, 512 adult patients undergoing elective, surgical procedures under general anaesthesia are going to be included. Perioperative routine data will be assessed and stored in a hospital-internal database, as well as data from postoperative clinical examination. Image data from lung sonography will be archived in the PACS for further processing. Based on the collected data, a machine learning algorithm based on neural networks will be trained to predict POPC. The model is created with the anonymized data using the statistics-oriented programming language R and the framework TensorFlow, a deep learning software library based on the programming language Python. The prediction quality of the created prediction model is assessed using the area under the receiver operator characteristics (AUROC) as well as the area under the precision recall curve (AUPRC) and compared with the values of the ARISCAT score, a common score to estimate the risk of POPC.

Precise risk assessment by means of an augmented machine-learning algorithm that uses clinical routine as well as imaging data has great potential to improve patient outcomes and could also help to reduce health care costs.

• Study Type: Observational
• Enrollment (Estimated): 512

Contacts and Locations

• Study Contact: Name: Britta Trautwein, MD; Phone Number: 00731 500 60227; Email: britta.trautwein@uniklinik-ulm.de
• Study Contact Backup: Name: Simone Kagerbauer, PD; Phone Number: 00731 500 60254; Email: simone.kagerbauer@uni-ulm.de

Study Locations

• Germany
  • Ulm, Germany, 89081
    • Recruiting
    • University Hospital Ulm
    • Contact: Britta Trautwein; Phone Number: 004973150060227; Email: britta.trautwein@uniklinik-ulm.de
    • Contact: Simone Kagerbauer; Phone Number: 004973150060254; Email: simone.kagerbauer@uniklinik-ulm.de

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No

• Sampling Method: Probability Sample

Study Population

adult patients in a university hospital

Description

Inclusion Criteria:

• adult patients
• elective, surgical procedure
• general anaesthesia

Exclusion Criteria:

• patients younger than 18 years of age
• outpatient surgery
• postoperative admission to intensive care unit

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Development of the machine learning model; Perioperative clinical routine data are going to be assessed as per standard. Postoperatively, a standardized lung sonography is going to be performed in the recovery room. Patients will then be visited on the ward on postoperative day 1, 3 and 7 for clinical examination to detect postoperative pulmonary complications according to the criteria elaborated by the StEP- collaboration.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Number of patients with postoperative pulmonary complications (POPC)	POPC according to criteria by the StEP-collaboration. This includes a clinical examination and interview of the patients on postoperative day 1,3 and 7.	postoperative day 7 or day of discharge

Collaborators and Investigators

• Sponsor: Britta Trautwein

Publications and helpful links

General Publications

• Fernandez-Bustamante A, Frendl G, Sprung J, Kor DJ, Subramaniam B, Martinez Ruiz R, Lee JW, Henderson WG, Moss A, Mehdiratta N, Colwell MM, Bartels K, Kolodzie K, Giquel J, Vidal Melo MF. Postoperative Pulmonary Complications, Early Mortality, and Hospital Stay Following Noncardiothoracic Surgery: A Multicenter Study by the Perioperative Research Network Investigators. JAMA Surg. 2017 Feb 1;152(2):157-166. doi: 10.1001/jamasurg.2016.4065.
• Szabo M, Bozo A, Darvas K, Soos S, Ozse M, Ivanyi ZD. The role of ultrasonographic lung aeration score in the prediction of postoperative pulmonary complications: an observational study. BMC Anesthesiol. 2021 Jan 14;21(1):19. doi: 10.1186/s12871-021-01236-6.
• Miskovic A, Lumb AB. Postoperative pulmonary complications. Br J Anaesth. 2017 Mar 1;118(3):317-334. doi: 10.1093/bja/aex002.
• Abbott TEF, Fowler AJ, Pelosi P, Gama de Abreu M, Moller AM, Canet J, Creagh-Brown B, Mythen M, Gin T, Lalu MM, Futier E, Grocott MP, Schultz MJ, Pearse RM; StEP-COMPAC Group. A systematic review and consensus definitions for standardised end-points in perioperative medicine: pulmonary complications. Br J Anaesth. 2018 May;120(5):1066-1079. doi: 10.1016/j.bja.2018.02.007. Epub 2018 Mar 27.
• Ferreyra GP, Baussano I, Squadrone V, Richiardi L, Marchiaro G, Del Sorbo L, Mascia L, Merletti F, Ranieri VM. Continuous positive airway pressure for treatment of respiratory complications after abdominal surgery: a systematic review and meta-analysis. Ann Surg. 2008 Apr;247(4):617-26. doi: 10.1097/SLA.0b013e3181675829.
• Ball L, Pelosi P. Predictive scores for postoperative pulmonary complications: time to move towards clinical practice. Minerva Anestesiol. 2016 Mar;82(3):265-7. Epub 2015 Sep 4. No abstract available.
• Nithiuthai J, Siriussawakul A, Junkai R, Horugsa N, Jarungjitaree S, Triyasunant N. Do ARISCAT scores help to predict the incidence of postoperative pulmonary complications in elderly patients after upper abdominal surgery? An observational study at a single university hospital. Perioper Med (Lond). 2021 Dec 8;10(1):43. doi: 10.1186/s13741-021-00214-3.
• Xue B, Li D, Lu C, King CR, Wildes T, Avidan MS, Kannampallil T, Abraham J. Use of Machine Learning to Develop and Evaluate Models Using Preoperative and Intraoperative Data to Identify Risks of Postoperative Complications. JAMA Netw Open. 2021 Mar 1;4(3):e212240. doi: 10.1001/jamanetworkopen.2021.2240.
• van Sloun RJG, Demi L. Localizing B-Lines in Lung Ultrasonography by Weakly Supervised Deep Learning, In-Vivo Results. IEEE J Biomed Health Inform. 2020 Apr;24(4):957-964. doi: 10.1109/JBHI.2019.2936151. Epub 2019 Aug 19.
• Brusasco C, Santori G, Tavazzi G, Via G, Robba C, Gargani L, Mojoli F, Mongodi S, Bruzzo E, Tro R, Boccacci P, Isirdi A, Forfori F, Corradi F; UCARE (Ultrasound in Critical care and Anesthesia Research Group). Second-order grey-scale texture analysis of pleural ultrasound images to differentiate acute respiratory distress syndrome and cardiogenic pulmonary edema. J Clin Monit Comput. 2022 Feb;36(1):131-140. doi: 10.1007/s10877-020-00629-1. Epub 2020 Dec 12.
• Trautwein B, Beer M, Blobner M, Jungwirth B, Kagerbauer SM, Gotz M. Preventing postoperative pulmonary complications by establishing a machine-learning assisted approach (PEPPERMINT): Study protocol for the creation of a risk prediction model. PLoS One. 2025 Aug 19;20(8):e0329076. doi: 10.1371/journal.pone.0329076. eCollection 2025.

Study record dates

Study Major Dates

• Study Start (Actual): April 25, 2023
• Primary Completion (Estimated): September 1, 2026
• Study Completion (Estimated): December 1, 2026

Study Registration Dates

• First Submitted: March 16, 2023
• First Submitted That Met QC Criteria: March 16, 2023
• First Posted (Actual): March 29, 2023

Study Record Updates

• Last Update Posted (Actual): May 8, 2026
• Last Update Submitted That Met QC Criteria: May 4, 2026
• Last Verified: May 1, 2026

More Information

Terms related to this study

• Keywords: machine learning; lung ultrasound
• Other Study ID Numbers: UHUlm

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Due to German regulatory regulations, the investigators are not allowed to publish individual patient data. They can provide the data to researchers upon reasonable request after appraisal by the data protection officer.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No