Artificial intelligence applications in pulmonology and its advantages during the pandemic period.

Artificial intelligence, with its increasing data volume, developing technologies, more information processing power and new algorithms, has a wide usage area in all sectors. In the field of health, these technologies is gaining an increasing place every day. Artificial intelligence methods can act as a simulation of the human mind and intelligence, resulting in the analysis and classification of complex data in a short time. Thus, by separating the small differences in the images examined, it can help diagnosis, detect preliminary signs of the disease and predict how the disease will develop. Computer based programs; diagnostic algorithms, surgical support and robotic systems developed on the basis of patient data are increasingly used in the drug development industry. In this study, artificial intelligence applications in the field of health and its use in pulmonology, the place of wearable technologies in our department and the advantages they provide us during the pandemic period were discussed in the light of the literature.

Post-COVID Interstitial Lung Disease: How do We Deal with This New Entity?

Background: In the postacute phase of coronavirus disease-2019 (COVID-19), survivors may have persistent symptoms, lung function abnormalities, and sequelae lesions on thoracic computed tomography (CT). This new entity has been defined as post-COVID interstitial lung disease (ILD) or residual disease. Aims: To evaluate the characteristics, risk factors and clinical significance of post-COVID ILD. Study Design: Multicenter cross-sectional analysis of data from a randomized clinical study. Methods: In this study, patients with persistent respiratory symptoms 3 months after recovery from COVID-19 were evaluated by two pulmonologists and a radiologist. post-COVID ILD was defined as the presence of respiratory symptoms, hypoxemia, restrictive defect on lung function tests, and interstitial changes on follow-up high-resolution computed tomography (HRCT). Results: At the three-month follow-up, 375 patients with post-COVID-19 syndrome were evaluated, and 262 patients were found to have post-COVID ILD. The most prevalent complaints were dyspnea (n = 238, 90.8%), exercise intolerance (n = 166, 63.4%), fatigue (n = 142, 54.2%), and cough (n = 136, 52%). The mean Medical Research Council dyspnea score was 2.1 ± 0.9, oxygen saturation was 92.2 ± 5.9%, and 6-minute walking distance was 360 ± 140 meters. The mean diffusing capacity of the lung for carbon monoxide was 58 ± 21, and the forced vital capacity was 70% ± 19%. Ground glass opacities and fibrotic bands were the most common findings on thoracic HRCT. Fibrosis-like lesions such as interlobular septal thickening and traction bronchiectasis were observed in 38.3% and 27.9% of the patients, respectively. No honeycomb cysts were observed. Active smoking [odds ratio (OR), 1.96; 95% confidence interval (CI), 1.44-2.67), intensive care unit admission during the acute phase (OR, 1.46; 95% CI, 1.1-1.95), need for high-flow nasal oxygen (OR, 1.55; 95% CI, 1.42-1.9) or non-invasive ventilation (OR, 1.31; 95% CI, 0.8-2.07), and elevated serum lactate dehydrogenase levels (OR, 1.23; 95% CI 1.18-1.28) were associated with the development of post-COVID ILD. At the 6-month follow-up, the respiratory symptoms and pulmonary functions had improved spontaneously without any specific treatment in 35 patients (13.4%). The radiological interstitial lesions had spontaneously regressed in 54 patients (20.6%). Conclusion: The co-existence of respiratory symptoms, radiological parenchymal lesions, and pulmonary functional abnormalities which suggest a restrictive ventilatory defect should be defined as post-COVID-19 ILD. However, the term "fibrosis" should be used carefully. Active smoking, severe COVID-19, and elevated lactate dehydrogenase level are the main risk factors of this condition. These post-COVID functional and radiological changes could disappear over time in 20% of the patients.

Lung cancer detection based on computed tomography image using convolutional neural networks.

BACKGROUND: Lung cancer is the most common type of cancer, accounting for 12.8% of cancer cases worldwide. As initially non-specific symptoms occur, it is difficult to diagnose in the early stages. OBJECTIVE: Image processing techniques developed using machine learning methods have played a crucial role in the development of decision support systems. This study aimed to classify benign and malignant lung lesions with a deep learning approach and convolutional neural networks (CNNs). METHODS: The image dataset includes 4459 Computed tomography (CT) scans (benign, 2242; malignant, 2217). The research type was retrospective; the case-control analysis. A method based on GoogLeNet architecture, which is one of the deep learning approaches, was used to make maximum inference on images and minimize manual control. RESULTS: The dataset used to develop the CNNs model is included in the training (3567) and testing (892) datasets. The model's highest accuracy rate in the training phase was estimated as 0.98. According to accuracy, sensitivity, specificity, positive predictive value, and negative predictive values of testing data, the highest classification performance ratio was positive predictive value with 0.984. CONCLUSION: The deep learning methods are beneficial in the diagnosis and classification of lung cancer through computed tomography images.

Deep learning for diagnosis of malign pleural effusion on computed tomography images.

BACKGROUND: The pleura is a serous membrane that surrounds the lungs. The visceral surface secretes fluid into the serous cavity and the parietal surface ensures a regular absorption of this fluid. If this balance is disturbed, fluid accumulation occurs in the pleural space called "Pleural Effusion". Today, accurate diagnosis of pleural diseases is becoming more critical, as advances in treatment protocols have contributed positively to prognosis. Our aim is to perform computer-aided numerical analysis of Computed Tomography (CT) images from patients showing pleural effusion images on CT and to examine the prediction of malignant/benign distinction using deep learning by comparing with the cytology results. METHODS: The authors classified 408 CT images from 64 patients whose etiology of pleural effusion was investigated using the deep learning method. 378 of the images were used for the training of the system; 15 malignant and 15 benign CT images, which were not included in the training group, were used as the test. RESULTS: Among the 30 test images evaluated in the system; 14 of 15 malignant patients and 13 of 15 benign patients were estimated with correct diagnosis (PPD: 93.3%, NPD: 86.67%, Sensitivity: 87.5%, Specificity: 92.86%). CONCLUSION: Advances in computer-aided diagnostic analysis of CT images and obtaining a pre-diagnosis of pleural fluid may reduce the need for interventional procedures by guiding physicians about which patients may have malignancies. Thus, it is cost and time-saving in patient management, allowing earlier diagnosis and treatment.

Perceived Need for Mental Health Services Among Healthcare Workers During the Coronavirus Disease-19 Pandemic in Turkey: A Multicenter Cross-sectional Study

Background: The coronavirus disease-2019 pandemic has contributed to work-related psychosocial risks in healthcare workers. Aims: To evaluate the perceived need for mental health services and related factors in Turkish healthcare workers practicing in pandemic hospitals. Study Design: Cross-sectional study. Methods: Data were collected from face-to-face interviews with healthcare workers at 19 pandemic hospitals in 13 provinces between September and November 2021. The study survey included the evaluation of the perceived need for and utilization of mental health services in the previous year, as well as sociodemographic, health-related, and work-related characteristics, the General Health Questionnaire-12, the World Health Organization Quality of Life-BREF (WHOQoL-BREF) questionnaire, and the Fear of coronavirus disease-2019 scale (FCV-19S). Results: Of 1,556 participants, 522 (33.5%) reported a perceived need for mental health services, but only 133 (8.5%) reported receiving these services. Multiple logistic regression analysis of the perceived need for mental health services revealed significant relationships with lower age, female sex, being a current smoker, having a chronic disease, having a mental disorder, coronavirus disease-2019 contact within the last three months in settings other than the home or workplace, a positive coronavirus disease-2019 vaccination history, being a physician, being a non-physician healthcare professional, and coronavirus disease-2019 contact within the last three months at work. After adjustment for these characteristics, higher General Health Questionnaire-12 and FCV-19S scores and lower WHOQoL-BREF domain scores were related to the perceived need for mental health services in logistic regression analyses. Conclusion: The findings indicate a substantial need for mental health services amongst Turkish healthcare workers during the pandemic and outline participants' characteristics regarding high-priority groups for the intervention. Future research may focus on developing actions and evaluating their efficiency.

Deep learning for diagnosis of malign pleural effusion on computed tomography images

Abstract Background The pleura is a serous membrane that surrounds the lungs. The visceral surface secretes fluid into the serous cavity and the parietal surface ensures a regular absorption of this fluid. If this balance is disturbed, fluid accumulation occurs in the pleural space called "Pleural Effusion". Today, accurate diagnosis of pleural diseases is becoming more critical, as advances in treatment protocols have contributed positively to prognosis. Our aim is to perform computer-aided numerical analysis of Computed Tomography (CT) images from patients showing pleural effusion images on CT and to examine the prediction of malignant/benign distinction using deep learning by comparing with the cytology results. Methods The authors classified 408 CT images from 64 patients whose etiology of pleural effusion was investigated using the deep learning method. 378 of the images were used for the training of the system; 15 malignant and 15 benign CT images, which were not included in the training group, were used as the test. Results Among the 30 test images evaluated in the system; 14 of 15 malignant patients and 13 of 15 benign patients were estimated with correct diagnosis (PPD: 93.3%, NPD: 86.67%, Sensitivity: 87.5%, Specificity: 92.86%). Conclusion Advances in computer-aided diagnostic analysis of CT images and obtaining a pre-diagnosis of pleural fluid may reduce the need for interventional procedures by guiding physicians about which patients may have malignancies. Thus, it is cost and time-saving in patient management, allowing earlier diagnosis and treatment.