Developing a Machine Learning Model to Predict Pleural Adhesion Preoperatively Using Pleural Ultrasound

Developing a Machine Learning Model to Predict Pleural Adhesion Preoperatively Using Pleural Ultrasound: a Prospective Observational Study

This study aims to investigate the accuracy of using pleural ultrasound (USP) to identify pleural adhesions in patients who plan to receive video-assisted thoracoscopic surgery. It employs three-dimensional convolutional neural network (3D-CNN) technology to process USP-related images and video data for machine learning, and to establish a diagnostic model for identifying pleural adhesions using 3D-CNN-USP. The study will determine the sensitivity, specificity, positive predictive value, and negative predictive value of 3D-CNN-USP in identifying pleural adhesions. Additionally, it will explore the feasibility and effectiveness of using 3D-CNN-USP for preoperative identification of pleural adhesions in VATS, thereby supporting the implementation of day surgery in thoracic surgery and ultimately serving clinical practice.

Study Overview

• Status: Not yet recruiting
• Conditions: Pleural Diseases; Lung Cancer; Machine Learning

Detailed Description

Lung cancer is currently the leading cause of death from malignant tumors worldwide. Surgery is the primary treatment method for lung cancer, and breakthroughs in thoracic surgical techniques play a crucial role in the diagnosis and treatment of lung cancer. Medical ultrasound technology, due to its non-invasive, flexible, convenient, and economical characteristics, is widely used in clinical practice. With the advancement of ultrasound technology and the need to address clinical challenges, ultrasound imaging technology has seen new developments in the field of thoracoscopic surgery.

In the era of minimally invasive surgery, intraoperative pleural adhesions are one of the main factors affecting the implementation of video-assisted thoracoscopic surgery (VATS). Especially under the concept of enhanced recovery after surgery (ERAS), the day surgery model for VATS has gradually taken shape. However, pleural adhesions significantly increase intraoperative trauma and prolong hospital stays. Additionally, pleural adhesions increase the risk of lung injury during VATS and, in severe cases, may hinder access to the pleural space, necessitating conversion to open thoracotomy. Pleural adhesions increase intraoperative time and morbidity in thoracic surgery due to poor visibility, bleeding, and lung and vascular injuries. The presence, location, and degree of pleural adhesions are useful for determining the initial port placement or choosing between open or VATS approaches. Therefore, accurately predicting the presence and specific location of pleural adhesions preoperatively is crucial for the development of day surgery under thoracic ERAS, ensuring the safety and efficiency of future VATS day surgeries.

Previous studies have shown that chest CT is difficult to predict pleural adhesions, with a sensitivity of only 72% and a sensitivity of only 46% for determining adhesions at specific locations. In contrast, ultrasonography of the pleura (USP) can dynamically display pleural sliding and adhesions with surrounding lung tissue, and has real-time monitoring capabilities based on movement, providing unique advantages for detecting pleural adhesions. Preoperative prediction of pleural adhesions using USP has significant application value. Studies have already demonstrated the advantages of using transthoracic pleural ultrasound to identify pleural adhesions. Nicola et al. conducted 1,192 ultrasounds to predict pleural adhesions, confirming 1,124 positive cases and 68 negative cases, with a sensitivity of 80.6%, specificity of 96.1%, positive predictive value of 73.2%, and negative predictive value of 97.4%. However, there are still some issues with using USP to predict pleural adhesions. Physicians who can identify pleural adhesions need to be trained in lung ultrasound, and ultrasound examination and interpretation are skill-dependent techniques. The burden of training thoracic ultrasound physicians remains a clinical challenge.

Three-dimensional convolutional neural network (3D-CNN) technology is an emerging technology in the field of artificial intelligence and machine learning. Unlike traditional convolutional neural networks (CNN), 3D-CNN can process three-dimensional data that includes a time dimension, making it suitable for analyzing the real-time dynamic image features of ultrasound images. This technology holds promise for developing a machine learning model to interpret USP images, potentially replacing physician interpretation and improving the accuracy of USP in identifying pleural adhesions.

In summary, this study intends to use USP for preoperative identification of pleural adhesions in patients scheduled for VATS surgery. It aims to investigate the accuracy of USP in predicting intraoperative pleural adhesions and to develop a diagnostic model using 3D-CNN technology to process USP-related images and video data for machine learning. The study will explore the sensitivity, specificity, positive predictive value, and negative predictive value of the 3D-CNN-USP model in identifying pleural adhesions. Additionally, it will examine the feasibility and effectiveness of using 3D-CNN-USP for preoperative identification of pleural adhesions to support the implementation of day surgery in thoracic surgery.

• Study Type: Observational
• Enrollment (Estimated): 200

Contacts and Locations

• Study Contact: Name: Xuehan Gao, MD; Phone Number: 18801341299; Email: gaoxh1299@163.com
• Study Contact Backup: Name: Yuanjing Gao, MD; Phone Number: 16619765781; Email: yuanjing1997@gmail.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients who plan to accept VATS surgery in Peking Union Medical college Hospital, and agree to perform preoperative plerual ultrasound examination.

Description

Inclusion Criteria:

1. Patients who plan to accept VATS surgery.

Exclusion Criteria:

1. Patients who can not obtain detailed clinical information;
2. Patients or their family members who can not understand the conditions and objectives of the study or refuse to participate in the study;
3. Patients with conditions affecting observation, such as skin lesions, infections, or scars in the area of the chest wall to be examined.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensitivity	Sensitivity of three-dimensional convolutional neural network (3D-CNN) in identifying pleural adhesions using pleural ultrasound (USP). The sensitivity value ranges from 0 to 100, with higher values indicating greater sensitivity.	From enrollment to the end of surgery.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Specificity	Specificity off 3D-CNN in identifying pleural adhesions using USP. The specificity value ranges from 0 to 100, with higher values indicating greater specificity.	From enrollment to the end of surgery.
Positive predictive value	Positive predictive value (PPV) of 3D-CNN in identifying pleural adhesions using USP. PPV is calculated by dividing the number of true positive results by the total number of positive test results. A higher PPV means that the test is more reliable in correctly identifying those with the condition.	From enrollment to the end of surgery.
Negative predictive value	Negative predictive value (NPV) of 3D-CNN in identifying pleural adhesions using USP. NPV is calculated by dividing the number of true negative results by the total number of negative test results. A higher NPV means that the test is more reliable in correctly identifying those without the condition.	From enrollment to the end of surgery.

Collaborators and Investigators

• Sponsor: Peking Union Medical College Hospital

Publications and helpful links

General Publications

• Mason AC, Miller BH, Krasna MJ, White CS. Accuracy of CT for the detection of pleural adhesions: correlation with video-assisted thoracoscopic surgery. Chest. 1999 Feb;115(2):423-7. doi: 10.1378/chest.115.2.423.
• Cassanelli N, Caroli G, Dolci G, Dell'Amore A, Luciano G, Bini A, Stella F. Accuracy of transthoracic ultrasound for the detection of pleural adhesions. Eur J Cardiothorac Surg. 2012 Nov;42(5):813-8; discussion 818. doi: 10.1093/ejcts/ezs144. Epub 2012 Apr 19.

Study record dates

Study Major Dates

• Study Start (Estimated): June 1, 2024
• Primary Completion (Estimated): December 30, 2025
• Study Completion (Estimated): March 30, 2026

Study Registration Dates

• First Submitted: May 15, 2024
• First Submitted That Met QC Criteria: May 15, 2024
• First Posted (Actual): May 21, 2024

Study Record Updates

• Last Update Posted (Actual): May 21, 2024
• Last Update Submitted That Met QC Criteria: May 15, 2024
• Last Verified: May 1, 2024

More Information

Terms related to this study

• Keywords: machine learning; VATS; pleural adhesion; 3D-CNN
• Additional Relevant MeSH Terms: Pathologic Processes; Respiratory Tract Diseases; Fibrosis; Cicatrix; Tissue Adhesions; Pleural Diseases
• Other Study ID Numbers: USPDPA01

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: The data of this study will be used in future analyses and be published in academic article.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No