Evaluation of Pneumoconiosis High Risk Early Warning Models

The Development and Clinical Application of Pneumoconiosis High Risk Early Warning Models Based on Convolutional Neural Network in Chest Radiography

Precaution of pneumoconiosis is more important than treatment. However, the current process can't early warn the high-risk dust exposed workers until they are diagnosed with pneumoconiosis. With the feature of efficiency, impersonality and quantification, artificial intelligence is just appropriate for solving this problems. Therefore, we are aiming at adapting deep learning to develop models of pneumoconiosis intelligent detection, grade diagnosis and high risk early warning. The annotated images will be used for convolutional neural networks (CNNs) algorithm training, aiming at pneumoconiosis screening and grade diagnosis. Moreover, risk score calculated by density heat map will be used for early warning of dust-exposed workers. Then follow up of cohort will be implied to verify the validity of the risk score. By this way, the high-risk dust-exposed workers will get early intervention and better prognosis, which can obviously reduce medical burden.

Study Overview

• Status: Recruiting
• Conditions: Pneumoconiosis

Detailed Description

Pneumoconiosis, the predominant occupational disease in China and all over the world. Chest radiography is the most accessible and affordable radiological test available for the physical examination of dust-exposed workers and mass screening for pneumoconiosis. But the diagnosis process has some disadvantages, such as strong subjectivity, inefficiency, and disability of judgement of borderline lesion, etc. Besides, precaution of pneumoconiosis is more important than treatment. However, the current process can't early warn the high-risk dust exposed workers until they are diagnosed with pneumoconiosis. With the feature of efficiency, impersonality and quantification, artificial intelligence is just appropriate for solving the aforesaid problems. Up to now, there has been rare research about adapting deep learning for pneumoconiosis grade diagnosis and high risk early warning. In our previous studies, we set up a chest radiograph database, which contains more than 100,000 digital pneumoconiosis radiography images. The result of detection-system evaluation demonstrated that the accuracy in the identification of pneumoconiosis could reach 90%, with an AUC(Area Under The Curve) of 0.965 and a sensitivity of 99%. More works need to be continued. Therefore, we are aiming at adapting deep learning to develop models of pneumoconiosis intelligent detection, grade diagnosis and high risk early warning. The annotated images will be used for convolutional neural networks (CNNs) algorithm training, aiming at pneumoconiosis screening and grade diagnosis. Moreover, risk score calculated by density heat map will be used for early warning of dust-exposed workers. Then follow up of cohort will be implied to verify the validity of the risk score. By this way, the high-risk dust-exposed workers will get early intervention and better prognosis, which can obviously reduce medical burden.

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

Contacts and Locations

• Study Contact: Name: Xiao Li, M.D.; Phone Number: +8613051709411; Email: lixiao.sy@bjmu.edu.cn

Study Locations

• China
  • Beijing
    • Beijing, Beijing, China, 100191
      • Recruiting
      • Peking University Third Hospital
      • Contact: Xiao Li, M.D.; Phone Number: +8613051709411; Email: lixiao.sy@bjmu.edu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 60 years (ADULT)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Probability Sample

Study Population

dust-exposed workers of 16 provinces of China

Description

Inclusion Criteria:

1. workers exposed to dust;
2. have digital chest radiography

Exclusion Criteria:

1. basal pulmonary disease;
2. dimission from dust-exposed work

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort
low-risk group; Risk Index∈[0,0.5)
high-risk group; Risk Index∈[0.5,1)

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
participants diagnosed as "pneumoconiosis"	Number of Participants diagnosed as "pneumoconiosis"	before December, 31,2022
death	Number of Participants who dies	before December, 31,2022

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Forced Expiratory Volume In 1s(FEV1) in %	Forced Expiratory Volume In 1s	before December, 31,2022
arterial partial pressure of oxygen, PaO2	arterial partial pressure of oxygen	before December, 31,2022
modified Medical Research Council，mMRC	a questionnaire used to assess symptom	before December, 31,2022

Collaborators and Investigators

• Sponsor: Peking University Third Hospital
• Investigators: Principal Investigator: Xiao Li, M.D., Peking University Third Hospital

Study record dates

Study Major Dates

• Study Start (ACTUAL): August 1, 2018
• Primary Completion (ANTICIPATED): December 1, 2021
• Study Completion (ANTICIPATED): December 1, 2025

Study Registration Dates

• First Submitted: June 23, 2021
• First Submitted That Met QC Criteria: July 2, 2021
• First Posted (ACTUAL): July 7, 2021

Study Record Updates

• Last Update Posted (ACTUAL): July 7, 2021
• Last Update Submitted That Met QC Criteria: July 2, 2021
• Last Verified: June 1, 2021

More Information

Terms related to this study

• Keywords: artificial intelligence; computer-aided diagnosis; pneumoconiosis; Deep Convolutional Neural Networks
• Additional Relevant MeSH Terms: Respiratory Tract Diseases; Lung Diseases; Occupational Diseases; Lung Diseases, Interstitial; Lung Injury; Pneumoconiosis
• Other Study ID Numbers: PekingUTH-002

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

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