1
|
Sufian MA, Hamzi W, Sharifi T, Zaman S, Alsadder L, Lee E, Hakim A, Hamzi B. AI-Driven Thoracic X-ray Diagnostics: Transformative Transfer Learning for Clinical Validation in Pulmonary Radiography. J Pers Med 2024; 14:856. [PMID: 39202047 PMCID: PMC11355475 DOI: 10.3390/jpm14080856] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2024] [Revised: 07/23/2024] [Accepted: 08/01/2024] [Indexed: 09/03/2024] Open
Abstract
Our research evaluates advanced artificial (AI) methodologies to enhance diagnostic accuracy in pulmonary radiography. Utilizing DenseNet121 and ResNet50, we analyzed 108,948 chest X-ray images from 32,717 patients and DenseNet121 achieved an area under the curve (AUC) of 94% in identifying the conditions of pneumothorax and oedema. The model's performance surpassed that of expert radiologists, though further improvements are necessary for diagnosing complex conditions such as emphysema, effusion, and hernia. Clinical validation integrating Latent Dirichlet Allocation (LDA) and Named Entity Recognition (NER) demonstrated the potential of natural language processing (NLP) in clinical workflows. The NER system achieved a precision of 92% and a recall of 88%. Sentiment analysis using DistilBERT provided a nuanced understanding of clinical notes, which is essential for refining diagnostic decisions. XGBoost and SHapley Additive exPlanations (SHAP) enhanced feature extraction and model interpretability. Local Interpretable Model-agnostic Explanations (LIME) and occlusion sensitivity analysis further enriched transparency, enabling healthcare providers to trust AI predictions. These AI techniques reduced processing times by 60% and annotation errors by 75%, setting a new benchmark for efficiency in thoracic diagnostics. The research explored the transformative potential of AI in medical imaging, advancing traditional diagnostics and accelerating medical evaluations in clinical settings.
Collapse
Affiliation(s)
- Md Abu Sufian
- IVR Low-Carbon Research Institute, Chang’an University, Xi’an 710018, China;
- School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK
| | - Wahiba Hamzi
- Laboratoire de Biotechnologie Santé et Environnement, Department of Biology, University of Blida, Blida 09000, Algeria
| | - Tazkera Sharifi
- Data Science Architect-Lead Technologist, Booz Allen Hamilton, Texas City, TX 78226, USA
| | - Sadia Zaman
- Department of Physiology, Queen Mary University, London E1 4NS, UK
| | - Lujain Alsadder
- Department of Physiology, Queen Mary University, London E1 4NS, UK
| | - Esther Lee
- Department of Physiology, Queen Mary University, London E1 4NS, UK
| | - Amir Hakim
- Department of Physiology, Queen Mary University, London E1 4NS, UK
| | - Boumediene Hamzi
- Department of Computing and Mathematical Sciences, California Institute of Technology, Caltech, CA 91125, USA
- The Alan Turing Institute, London NW1 2DB, UK
- Department of Mathematics, Imperial College London, London SW7 2AZ, UK
- Department of Mathematics, Gulf University for Science and Technology (GUST), Mubarak Al-Abdullah 32093, Kuwait
| |
Collapse
|
2
|
Bulińska B, Mazur-Milecka M, Sławińska M, Rumiński J, Nowicki RJ. Artificial Intelligence in the Diagnosis of Onychomycosis-Literature Review. J Fungi (Basel) 2024; 10:534. [PMID: 39194860 DOI: 10.3390/jof10080534] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2024] [Revised: 07/22/2024] [Accepted: 07/24/2024] [Indexed: 08/29/2024] Open
Abstract
Onychomycosis is a common fungal nail infection that is difficult to diagnose due to its similarity to other nail conditions. Accurate identification is essential for effective treatment. The current gold standard methods include microscopic examination with potassium hydroxide, fungal cultures, and Periodic acid-Schiff biopsy staining. These conventional techniques, however, suffer from high turnover times, variable sensitivity, reliance on human interpretation, and costs. This study examines the potential of integrating AI (artificial intelligence) with visualization tools like dermoscopy and microscopy to improve the accuracy and efficiency of onychomycosis diagnosis. AI algorithms can further improve the interpretation of these images. The review includes 14 studies from PubMed and IEEE databases published between 2010 and 2024, involving clinical and dermoscopic pictures, histopathology slides, and KOH microscopic images. Data extracted include study type, sample size, image assessment model, AI algorithms, test performance, and comparison with clinical diagnostics. Most studies show that AI models achieve an accuracy comparable to or better than clinicians, suggesting a promising role for AI in diagnosing onychomycosis. Nevertheless, the niche nature of the topic indicates a need for further research.
Collapse
Affiliation(s)
- Barbara Bulińska
- Department of Dermatology, Venereology, and Allergology, Faculty of Medicine, Medical University of Gdańsk, 80-214 Gdańsk, Poland
| | - Magdalena Mazur-Milecka
- Department of Biomedical Engineering, Faculty of Electronics, Telecommunications and Computer Science, Gdańsk University of Technology, 80-233 Gdańsk, Poland
| | - Martyna Sławińska
- Department of Dermatology, Venereology, and Allergology, Faculty of Medicine, Medical University of Gdańsk, 80-214 Gdańsk, Poland
| | - Jacek Rumiński
- Department of Biomedical Engineering, Faculty of Electronics, Telecommunications and Computer Science, Gdańsk University of Technology, 80-233 Gdańsk, Poland
| | - Roman J Nowicki
- Department of Dermatology, Venereology, and Allergology, Faculty of Medicine, Medical University of Gdańsk, 80-214 Gdańsk, Poland
| |
Collapse
|
3
|
Chen CF, Hsu CH, Jiang YC, Lin WR, Hong WC, Chen IY, Lin MH, Chu KA, Lee CH, Lee DL, Chen PF. A deep learning-based algorithm for pulmonary tuberculosis detection in chest radiography. Sci Rep 2024; 14:14917. [PMID: 38942819 PMCID: PMC11213931 DOI: 10.1038/s41598-024-65703-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2023] [Accepted: 06/24/2024] [Indexed: 06/30/2024] Open
Abstract
In tuberculosis (TB), chest radiography (CXR) patterns are highly variable, mimicking pneumonia and many other diseases. This study aims to evaluate the efficacy of Google teachable machine, a deep neural network-based image classification tool, to develop algorithm for predicting TB probability of CXRs. The training dataset included 348 TB CXRs and 3806 normal CXRs for training TB detection. We also collected 1150 abnormal CXRs and 627 normal CXRs for training abnormality detection. For external validation, we collected 250 CXRs from our hospital. We also compared the accuracy of the algorithm to five pulmonologists and radiological reports. In external validation, the AI algorithm showed areas under the curve (AUC) of 0.951 and 0.975 in validation dataset 1 and 2. The accuracy of the pulmonologists on validation dataset 2 showed AUC range of 0.936-0.995. When abnormal CXRs other than TB were added, AUC decreased in both human readers (0.843-0.888) and AI algorithm (0.828). When combine human readers with AI algorithm, the AUC further increased to 0.862-0.885. The TB CXR AI algorithm developed by using Google teachable machine in this study is effective, with the accuracy close to experienced clinical physicians, and may be helpful for detecting tuberculosis by CXR.
Collapse
Affiliation(s)
- Chiu-Fan Chen
- Division of Chest Medicine, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan, R.O.C
- Shu-Zen Junior College of Medicine and Management, Kaohsiung, Taiwan, R.O.C
- Department of Nursing, Mei-Ho University, Pingtung, Taiwan, R.O.C
| | - Chun-Hsiang Hsu
- Division of Chest Medicine, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan, R.O.C
| | - You-Cheng Jiang
- Division of Chest Medicine, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan, R.O.C
| | - Wen-Ren Lin
- Division of Chest Medicine, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan, R.O.C
| | - Wei-Cheng Hong
- Division of Chest Medicine, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan, R.O.C
| | - I-Yuan Chen
- Division of Chest Medicine, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan, R.O.C
| | - Min-Hsi Lin
- Division of Chest Medicine, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan, R.O.C
| | - Kuo-An Chu
- Division of Chest Medicine, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan, R.O.C
| | - Chao-Hsien Lee
- Department of Nursing, Mei-Ho University, Pingtung, Taiwan, R.O.C
| | - David Lin Lee
- Division of Chest Medicine, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan, R.O.C
| | - Po-Fan Chen
- Department of Obstetrics and Gynecology, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan, R.O.C..
- Quality Center, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan, R.O.C..
| |
Collapse
|
4
|
Molfino NA, Turcatel G, Riskin D. Machine Learning Approaches to Predict Asthma Exacerbations: A Narrative Review. Adv Ther 2024; 41:534-552. [PMID: 38110652 PMCID: PMC10838858 DOI: 10.1007/s12325-023-02743-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Accepted: 11/15/2023] [Indexed: 12/20/2023]
Abstract
The implementation of artificial intelligence (AI) and machine learning (ML) techniques in healthcare has garnered significant attention in recent years, especially as a result of their potential to revolutionize personalized medicine. Despite advances in the treatment and management of asthma, a significant proportion of patients continue to suffer acute exacerbations, irrespective of disease severity and therapeutic regimen. The situation is further complicated by the constellation of factors that influence disease activity in a patient with asthma, such as medical history, biomarker phenotype, pulmonary function, level of healthcare access, treatment compliance, comorbidities, personal habits, and environmental conditions. A growing body of work has demonstrated the potential for AI and ML to accurately predict asthma exacerbations while also capturing the entirety of the patient experience. However, application in the clinical setting remains mostly unexplored, and important questions on the strengths and limitations of this technology remain. This review presents an overview of the rapidly evolving landscape of AI and ML integration into asthma management by providing a snapshot of the existing scientific evidence and proposing potential avenues for future applications.
Collapse
Affiliation(s)
- Nestor A Molfino
- Global Development, Amgen Inc., One Amgen Center Dr, Thousand Oaks, CA, 91320, USA.
| | | | | |
Collapse
|
5
|
Hwang SH, Shin HJ, Kim EK, Lee EH, Lee M. Clinical outcomes and actual consequence of lung nodules incidentally detected on chest radiographs by artificial intelligence. Sci Rep 2023; 13:19732. [PMID: 37957283 PMCID: PMC10643548 DOI: 10.1038/s41598-023-47194-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Accepted: 11/10/2023] [Indexed: 11/15/2023] Open
Abstract
This study evaluated how often clinically significant lung nodules were detected unexpectedly on chest radiographs (CXR) by artificial intelligence (AI)-based detection software, and whether co-existing findings can aid in differential diagnosis of lung nodules. Patients (> 18 years old) with AI-detected lung nodules at their first visit from March 2021 to February 2022, except for those in the pulmonology or thoracic surgery departments, were retrospectively included. Three radiologists categorized nodules into malignancy, active inflammation, post-inflammatory sequelae, or "other" groups. Characteristics of the nodule and abnormality scores of co-existing lung lesions were compared. Approximately 1% of patients (152/14,563) had unexpected lung nodules. Among 73 patients with follow-up exams, 69.9% had true positive nodules. Increased abnormality scores for nodules were significantly associated with malignancy (odds ratio [OR] 1.076, P = 0.001). Increased abnormality scores for consolidation (OR 1.033, P = 0.040) and pleural effusion (OR 1.025, P = 0.041) were significantly correlated with active inflammation-type nodules. Abnormality scores for fibrosis (OR 1.036, P = 0.013) and nodules (OR 0.940, P = 0.001) were significantly associated with post-inflammatory sequelae categorization. AI-based lesion-detection software of CXRs in daily practice can help identify clinically significant incidental lung nodules, and referring accompanying lung lesions may help classify the nodule.
Collapse
Affiliation(s)
- Shin Hye Hwang
- Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yongin Severance Hospital, Yonsei University College of Medicine, 363, Dongbaekjukjeon-daero, Giheung-gu, Yongin-si, Gyeonggi-do, 16995, Republic of Korea
| | - Hyun Joo Shin
- Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yongin Severance Hospital, Yonsei University College of Medicine, 363, Dongbaekjukjeon-daero, Giheung-gu, Yongin-si, Gyeonggi-do, 16995, Republic of Korea
- Center for Digital Health, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin-si, Gyeonggi‑do, Republic of Korea
| | - Eun-Kyung Kim
- Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yongin Severance Hospital, Yonsei University College of Medicine, 363, Dongbaekjukjeon-daero, Giheung-gu, Yongin-si, Gyeonggi-do, 16995, Republic of Korea
| | - Eun Hye Lee
- Center for Digital Health, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin-si, Gyeonggi‑do, Republic of Korea
- Division of Pulmonology, Allergy and Critical Care Medicine, Department of Internal Medicine, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin-si, Gyeonggi-do, Republic of Korea
| | - Minwook Lee
- Department of Radiology, Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yongin Severance Hospital, Yonsei University College of Medicine, 363, Dongbaekjukjeon-daero, Giheung-gu, Yongin-si, Gyeonggi-do, 16995, Republic of Korea.
| |
Collapse
|