Value of CT Radiomics Combined with Clinical Features in the Diagnosis of Allergic Bronchopulmonary Aspergillosis

Distribution of Aspergillus species and risk factors for aspergillosis in mainland China: a systematic review

Background

Aspergillus, a widespread fungus in the natural environment, poses a significant threat to human health by entering the human body via the airways and causing a disease called aspergillosis. This study comprehensively analyzed data on aspergillosis in published articles from mainland China to investigate the prevalence of Aspergillus, and risk factors, mortality rate, and underlying condition associated with aspergillosis.

Methods

Published articles were retrieved from Google Scholar, PubMed, and Science Direct online search engines. In the 101 analyzed studies, 3558 Aspergillus isolates were meticulously collected and classified. GraphPad Prism 8 was used to statistically examine the epidemiology and clinical characteristics of aspergillosis.

Results

Aspergillus fumigatus was prominently reported (n = 2679, 75.14%), followed by A. flavus (n = 437, 12.25%), A. niger (n = 219, 6.14%), and A. terreus (n = 119, 3.33%). Of a total of 9810 patients, 7513 probable cases accounted for the highest number, followed by confirmed cases (n = 1956) and possible cases (n = 341). In patients, cough emerged as the most common complaint (n = 1819, 18.54%), followed by asthma (n = 1029, 10.48%) and fever (1024, 10.44%). Of total studies, invasive pulmonary aspergillosis (IPA) was reported in 47 (45.53%) studies, exhibiting an increased prevalence in Beijing (n = 12, 25.53%), Guangdong (n = 7, 14.89%), and Shanghai (n = 6, 12.76%). Chronic pulmonary aspergillosis (CPA) was reported in 14 (13.86%) studies. Among the total of 14 studies, the occurrence of CPA was 5 (35.71%) in Beijing and 3 (21.42%) in Shanghai. Allergic bronchopulmonary aspergillosis (ABPA), was reported at a lower frequency (n = 8, 7.92%), Guangdong recorded a relatively high number (n = 3, 37.5%), followed by Beijing (n = 2, 25.0%), and Shanghai (n = 1, 12.5%). Percentage of death reported: IPA had the highest rate (n = 447, 68.87%), followed by CPA (n = 181, 27.88%) and ABPA (n = 14, 2.15%). Among the aspergillosis patients, 6220 had underlying conditions, including chronic lung disease (n = 3765, 60.53%), previous tuberculosis (n = 416, 6.68%), and organ transplant or organ failure (n = 648, 10.41%). Aspergillosis was also found in patients using corticosteroid therapy (n = 622, 10.0%).

Conclusion

This review sheds light on the prevalence patterns of Aspergillus species, risk factors of aspergillosis, and gaps in surveillance that could be helpful for the control and treatment of aspergillosis and guide the researchers in future studies.

Registration

This systematic review was prospectively registered on PROSPERO: Registration ID CRD42023476870.

Adoption value of support vector machine algorithm-based computed tomography imaging in the diagnosis of secondary pulmonary fungal infections in patients with malignant hematological disorders

This study aimed to assess the feasibility of diagnosing secondary pulmonary fungal infections (PFIs) in patients with hematological malignancies (HM) using computerized tomography (CT) imaging and a support vector machine (SVM) algorithm. A total of 100 patients with HM complicated by secondary PFI underwent CT scans, and they were included in the training group. Concurrently, 80 patients with the same underlying disease who were treated at our institution were included in the test group. The types of pathogens among different PFI patients and the CT imaging features were compared. Radiomic features were extracted from the CT imaging data of patients, and a diagnostic SVM model was constructed by integrating these features with clinical characteristics. Aspergillus was the most common pathogen responsible for PFIs, followed by Candida, Pneumocystis jirovecii, Mucor, and Cryptococcus, in descending order of occurrence. Patients typically exhibited bilateral diffuse lung lesions. Within the SVM algorithm model, six radiomic features, namely the square root of the inverse covariance of the gray-level co-occurrence matrix (square root IV), the square root of the inverse covariance of the gray-level co-occurrence matrix, and small dependency low gray-level emphasis, significantly influenced the diagnosis of secondary PFIs in patients with HM. The area under the curve values for the training and test sets were 0.902 and 0.891, respectively. Therefore, CT images based on the SVM algorithm demonstrated robust predictive capability in diagnosing secondary PFIs in conjunction with HM.