Chest Diseases Research Articles

Artificial intelligence and feature based transfer learning framework for diagnosis of chest diseases using radiology images

The subject of artificial intelligence-assisted diagnosis and design in the medical industry is very exciting due to considerable developments in medical imaging. In real-world applications, previous manual feature extraction strategies were inefficient in achieving the required results. The number of medical image databases is quickly increasing to accommodate hospital-based diseases as a result of the numerous uses of medical images in healthcare facilities, pathology, and medical diagnostic fields. The primary objective of this study is to create a computerized Artificial intelligence system that can accurately diagnose different diseases and reduce mistakes in the testing process. The study has two primary aspects. In the initial phase, we utilized the deep transfer learning method to extract the pertinent and crucial features from the image x-ray. Subsequently, the support vector machine employs these crucial extracted features to diagnose diseases from the x-ray14 dataset. The imbalanced dataset problem was also addressed with the utilization of the Synthetic Minority Oversampling Technique (SMOTE). The authors conduct a comparative analysis of the findings from this study in relation to other cutting-edge studies and employ cross-dataset experiments to evaluate its efficacy. The results demonstrate that the proposed approach has a detection accuracy of 95.2% for the disease. The VGG-16 model achieved 78.4% accuracy and an AUC of 90%. The proposed model can be applied to other diseases for further experiments.

Multi-modal deep learning methods for classification of chest diseases using different medical imaging and cough sounds.

Chest disease refers to a wide range of conditions affecting the lungs, such as COVID-19, lung cancer (LC), consolidation lung (COL), and many more. When diagnosing chest disorders medical professionals may be thrown off by the overlapping symptoms (such as fever, cough, sore throat, etc.). Additionally, researchers and medical professionals make use of chest X-rays (CXR), cough sounds, and computed tomography (CT) scans to diagnose chest disorders. The present study aims to classify the nine different conditions of chest disorders, including COVID-19, LC, COL, atelectasis (ATE), tuberculosis (TB), pneumothorax (PNEUTH), edema (EDE), pneumonia (PNEU). Thus, we suggested four novel convolutional neural network (CNN) models that train distinct image-level representations for nine different chest disease classifications by extracting features from images. Furthermore, the proposed CNN employed several new approaches such as a max-pooling layer, batch normalization layers (BANL), dropout, rank-based average pooling (RBAP), and multiple-way data generation (MWDG). The scalogram method is utilized to transform the sounds of coughing into a visual representation. Before beginning to train the model that has been developed, the SMOTE approach is used to calibrate the CXR and CT scans as well as the cough sound images (CSI) of nine different chest disorders. The CXR, CT scan, and CSI used for training and evaluating the proposed model come from 24 publicly available benchmark chest illness datasets. The classification performance of the proposed model is compared with that of seven baseline models, namely Vgg-19, ResNet-101, ResNet-50, DenseNet-121, EfficientNetB0, DenseNet-201, and Inception-V3, in addition to state-of-the-art (SOTA) classifiers. The effectiveness of the proposed model is further demonstrated by the results of the ablation experiments. The proposed model was successful in achieving an accuracy of 99.01%, making it superior to both the baseline models and the SOTA classifiers. As a result, the proposed approach is capable of offering significant support to radiologists and other medical professionals.

Current Research Status of Respiratory Motion for Thorax and Abdominal Treatment: A Systematic Review.

Malignant tumors have become one of the serious public health problems in human safety and health, among which the chest and abdomen diseases account for the largest proportion. Early diagnosis and treatment can effectively improve the survival rate of patients. However, respiratory motion in the chest and abdomen can lead to uncertainty in the shape, volume, and location of the tumor, making treatment of the chest and abdomen difficult. Therefore, compensation for respiratory motion is very important in clinical treatment. The purpose of this review was to discuss the research and development of respiratory movement monitoring and prediction in thoracic and abdominal surgery, as well as introduce the current research status. The integration of modern respiratory motion compensation technology with advanced sensor detection technology, medical-image-guided therapy, and artificial intelligence technology is discussed and analyzed. The future research direction of intraoperative thoracic and abdominal respiratory motion compensation should be non-invasive, non-contact, use a low dose, and involve intelligent development. The complexity of the surgical environment, the constraints on the accuracy of existing image guidance devices, and the latency of data transmission are all present technical challenges.

Research and implementation of multi-disease diagnosis on chest X-ray based on vision transformer.

Disease diagnosis in chest X-ray images has predominantly relied on convolutional neural networks (CNNs). However, Vision Transformer (ViT) offers several advantages over CNNs, as it excels at capturing long-term dependencies, exploring correlations, and extracting features with richer semantic information. We adapted ViT for chest X-ray image analysis by making the following three key improvements: (I) employing a sliding window approach in the image sequence feature extraction module to divide the input image into blocks to identify small and difficult-to-detect lesion areas; (II) introducing an attention region selection module in the encoder layer of the ViT model to enhance the model's ability to focus on relevant regions; and (III) constructing a parallel patient metadata feature extraction network on top of the image feature extraction network to integrate multi-modal input data, enabling the model to synergistically learn and expand image-semantic information. The experimental results showed the effectiveness of our proposed model, which had an average area under the curve value of 0.831 in diagnosing 14 common chest diseases. The metadata feature network module effectively integrated patient metadata, further enhancing the model's accuracy in diagnosis. Our ViT-based model had a sensitivity of 0.863, a specificity of 0.821, and an accuracy of 0.834 in diagnosing these common chest diseases. Our model has good general applicability and shows promise in chest X-ray image analysis, effectively integrating patient metadata and enhancing diagnostic capabilities.

Diagnostic Yield and Outcome Of Bronchoscopy Unit at Ain Shams University Hospital in Current Clinical Practice (Including Recent Modalities and Interventional Pulmonolgy) Marwa S Daif, Ragy Mamdouh Ghaly Lecturer of Chest Diseases, Lecturer of Ches

Diagnostic Yield and Outcome Of Bronchoscopy Unit at Ain Shams University Hospital in Current Clinical Practice (Including Recent Modalities and Interventional Pulmonolgy) Marwa S Daif, Ragy Mamdouh Ghaly Lecturer of Chest Diseases, Lecturer of Ches

AI-Powered Chest Disease Detection and Classification using Deep Learning

AI-Powered Chest Disease Detection and Classification using Deep Learning Method presents an innovative approach to revolutionize chest disease diagnosis through the integration of advanced deep learning techniques. This initiative focuses on the development of an intelligent system that can effectively detect and classify a variety of chest diseases by analysing medical images, such as chest X-rays and CT scans. At its core, the project involves the compilation and preparation of a diverse dataset containing both normal and disease-affected chest images. Leveraging the capabilities of deep learning, particularly convolutional neural networks (CNNs), the project then designs and trains models to learn intricate patterns and features indicative of different chest diseases. The models are optimized for accuracy and robustness. This efficiency translates to quicker diagnoses, enabling prompt medical interventions. The AI system serves as a complementary tool for healthcare professionals, aiding in decision- making by providing valuable insights and augmenting their expertise.

Satisfaction Level of Multi-Drug Resistant Tuberculosis Patient: A Hospital Based Study in Bangladesh

Background: Realizing the patients’ need and improving the quality of services, a satisfaction survey can effectively help management and the patient. The aim of this study was to investigate satisfaction level of multi-drug resistant tuberculosis (MDRTB) patients at tertiary level hospital in Bangladesh. Methods: A cross-sectional study conducted at Chest Disease Hospital (CDH), Rajshahi among 199 MDR-TB patients using random sampling technique. A semi-structured questionnaire was used to collect basic, socio-demographic, behavioral and satisfaction specific data with ensuring no any risk for providing right information. Five point “Likert Scale” was used to measure patients’ satisfaction level. The relevant data were carefully coded and recoded for statistical analysis, and independent samples t-test and multinomial logistic regression analysis were used to see the difference and association of influencing factors on satisfaction. Results: In this study, we observed that the mean age of MDR-TB patient admitted at CDH was 39.8 years with range from 16 to 62 years. About 90% patients were satisfied with behavior of care providers, and 50% and 29% patients were satisfied in hospital environment and supplied food respectively. We also found that old age group, male, less educated, smoker, diabetic, married, high income and less expenditure group, business or service holder and Muslim were more satisfied than their counterparts. The multinomial logistic regression analysis showed that young age group (≤40 years) was five times more dissatisfied than old age group (≥40 years) (OR=5.345; 95% CI: 1.123-25.448; p<0.05). Receiving monthly money from the program positively impacted on satisfaction. Similarly, drug toxicity, length of stay and loneliness was negatively impacted on satisfaction. Conclusion: Considering the mentioned influencing factors can strengthen the national control program effort at CDH in Rajshahi division, Bangladesh. Similar study in other chest disease hospitals located mostly in different divisions in the country can also help comparing the factors for nationwide improvement.

Authors' Response.

Dear Editor, We would like to thank Dr. Madias for his valuable comment on our original article entitled "QT interval prolongation in Takotsubo Syndrome: a frightening feature with no major prognostic impact" published in Monaldi Archives for Chest Disease on December 6, 2023...

Drug Resistance Tests for Mycobacterium Tuberculosis and Compatibility between Tests; From Past to Today

Objective: The gold standard for pulmonary tuberculosis diagnosis is the demonstration of Mycobacterium tuberculosis bacilli. Drug susceptibility test results of the bacilli obtained are crucial in tuberculosis treatment management. The various tests used to determine drug susceptibility must yield the same result. In the present study, we aimed to evaluate the compatibility of drug susceptibility test results obtained by Löwenstein-Jensen (L-J) and BACTEC 460TB methods from the past to the present. Material and Methods: Sputum results from 79 patients suspected of multidrug-resistant pulmonary tuberculosis (MDR-TB) clinically, radiologically, and bacteriologically were evaluated for isoniazid, rifampicin, ethambutol, and streptomycin between June 1997 and June 1998. Culture and drug sensitivity tests on the L-J medium were conducted at the Heybeliada Chest Diseases and Thoracic Surgery Center bacteriology laboratory, while culture and drug sensitivity tests with the BACTEC 460 TB system were performed at another center. The results were assessed for compatibility using the Kappa (κ) test, a tool for comparing two independent parameters. Results: All drug sensitivity tests for isoniazid, rifampicin, ethambutol, and streptomycin were collectively evaluated. It was determined that 263 (83.3%) of 316 drug sensitivity tests yielded concordant results, while 53 (16.7%) produced discordant results. The drug sensitivity tests using L-J and BACTEC 460TB methods indicated compatibility only for streptomycin (κ = 0.715). In contrast, they yielded different results for isoniazid (κ = 0.585), ethambutol (κ = 0.552), and rifampicin (κ = 0.507). Streptomycin exhibited compatibility, while isoniazid, ethambutol, and rifampicin showed incompatibility between the L-J and BACTEC 460TB methods. Conclusion: Drug sensitivity tests are pivotal in tuberculosis treatment management. While literature suggests compatibility between L-J and BACTEC 460TB methods, our study revealed incompatibility. Evaluation of drug sensitivities may lead to confusing results. Current practices involving studies in the same laboratory and genetic testing contribute to faster and more accurate outcomes in managing drug-resistant tuberculosis. Genetic tests and reference laboratories remain crucial for antituberculosis drug sensitivity, emphasizing their continued importance.

EVALUATION OF INTERVENTIONS AND QUALITY OF LIFE FOR ADVANCED STAGE CANCER PATIENTS APPLYING TO THE EMERGENCY DEPARTMENT

Objective: This study aimed to evaluate the palliative care needs of advanced stage
 cancer patients who applied to the emergency department.
 Material and Method: The research is descriptive and was conducted with 159 patients
 who met the selection criteria in the emergency departments of three public hospitals in
 Istanbul. The data for the study was collected using three tools: the Patient Information
 Questionnaire Form, the Palliative Performance Scale (PPS), and the Quality of Life in
 Palliative Cancer Care Patients (EORTC-QLQ C15-PAL) Scale.
 Results: Patients frequently applied to the emergency department for pain (31.7%),
 dyspnea (16.2%), and nausea- vomiting (15.8%). In general, consultation was requested
 from 88.7% of the patients, and the most frequently consulted clinics were 49.8%
 internal medicine, 25.1% anaesthesia, 6.5% surgery and 6% chest diseases. Consultation
 was requested from 88.7% of the patients, and the internal medicine unit was consulted
 most frequently with a rate of 49.8%. The most common outcome was 38.4% clinical
 admission. 67.2% of the patients had a PPS score of 70 or less. The patients' emergency
 service visits resulted in 38.4% clinical admission, 32.1% discharge, 23.3% intensive
 care unit and 6.3% exitus. The patients' follow-up time in the emergency department
 was also determined to be a minimum of half an hour, a maximum of 5 hours, and an
 average of 1.9±1.2 hours.
 Conclusion: The study found that 93% of the patients did not receive palliative care
 support. Considering this basis, it can be recommended to provide the necessary
 guidance for cancer patients who apply to emergency departments to receive palliative
 care support and to structure this step within the health system. Such a structure may
 contribute to the diagnosis of patients who need palliative care support.

Chest radiology report generation based on cross-modal multi-scale feature fusion

Chest radiology imaging plays a crucial role in the early screening, diagnosis, and treatment of chest diseases. The accurate interpretation of radiological images and the automatic generation of radiology reports not only save the doctor's time but also mitigate the risk of errors in diagnosis. The core objective of automatic radiology report generation is to achieve precise mapping of visual features and lesion descriptions at multi-scale and fine-grained levels. Existing methods typically combine global visual features and textual features to generate radiology reports. However, these approaches may ignore the key lesion areas and lack sensitivity to crucial lesion location information. Furthermore, achieving multi-scale characterization and fine-grained alignment of medical visual features and report text features proves challenging, leading to a reduction in the quality of radiology report generation. Addressing these issues, we propose a method for chest radiology report generation based on cross-modal multi-scale feature fusion. First, an auxiliary labeling module is designed to guide the model to focus on the lesion region of the radiological image. Second, a channel attention network is employed to enhance the characterization of location information and disease features. Finally, a cross-modal features fusion module is constructed by combining memory matrices, facilitating fine-grained alignment between multi-scale visual features and reporting text features on corresponding scales. The proposed method is experimentally evaluated on two publicly available radiological image datasets. The results demonstrate superior performance based on BLEU and ROUGE metrics compared to existing methods. Particularly, there are improvements of 4.8% in the ROUGE metric and 9.4% in the METEOR metric on the IU X-Ray dataset. Moreover, there is a 7.4% enhancement in BLEU-1 and a 7.6% improvement in the BLEU-2 on the MIMIC-CXR dataset.

CNN-IKOA: convolutional neural network with improved Kepler optimization algorithm for image segmentation: experimental validation and numerical exploration

Chest diseases, especially COVID-19, have quickly spread throughout the world and caused many deaths. Finding a rapid and accurate diagnostic tool was indispensable to combating these diseases. Therefore, scientists have thought of combining chest X-ray (CXR) images with deep learning techniques to rapidly detect people infected with COVID-19 or any other chest disease. Image segmentation as a preprocessing step has an essential role in improving the performance of these deep learning techniques, as it could separate the most relevant features to better train these techniques. Therefore, several approaches were proposed to tackle the image segmentation problem accurately. Among these methods, the multilevel thresholding-based image segmentation methods won significant interest due to their simplicity, accuracy, and relatively low storage requirements. However, with increasing threshold levels, the traditional methods have failed to achieve accurate segmented features in a reasonable amount of time. Therefore, researchers have recently used metaheuristic algorithms to tackle this problem, but the existing algorithms still suffer from slow convergence speed and stagnation into local minima as the number of threshold levels increases. Therefore, this study presents an alternative image segmentation technique based on an enhanced version of the Kepler optimization algorithm (KOA), namely IKOA, to better segment the CXR images at small, medium, and high threshold levels. Ten CXR images are used to assess the performance of IKOA at ten threshold levels (T-5, T-7, T-8, T-10, T-12, T-15, T-18, T-20, T-25, and T-30). To observe its effectiveness, it is compared to several metaheuristic algorithms in terms of several performance indicators. The experimental outcomes disclose the superiority of IKOA over all the compared algorithms. Furthermore, the IKOA-based segmented CXR images at eight different threshold levels are used to train a newly proposed CNN model called CNN-IKOA to find out the effectiveness of the segmentation step. Five performance indicators, namely overall accuracy, precision, recall, F1-score, and specificity, are used to disclose the CNN-IKOA’s effectiveness. CNN-IKOA, according to the experimental outcomes, could achieve outstanding outcomes for the images segmented at T-12, where it could reach 94.88% for overall accuracy, 96.57% for specificity, 95.40% for precision, and 95.40% for recall.

Federated learning with deep convolutional neural networks for the detection of multiple chest diseases using chest x-rays

Federated learning with deep convolutional neural networks for the detection of multiple chest diseases using chest x-rays

A Machine Learning Approach for the Detection of Thoracic Disease using Chest X-ray reports

Today, several chest diseases are on the rise and these are often diagnosed through the use of chest X-rays, a common and economical clinical test to perform. This work uses a machine learning approach for the detection of thoracic diseases using chest X-ray reports and involves leveraging algorithms and models to analyze medical imaging data for the presence of various conditions affecting the chest area. Our main goal is to create a predictive model based on textual reports released by radiologists, with the use of Natural Language Processing. The proposed approach aims to facilitate the examination of textual reports written by radiologists, to predict the onset of diseases in patients. Specifically, reports generated by radiologists are meticulously processed and reviewed using the GloVe and LSI models. This analysis allows you to identify the presence of diseases and provides insights into the specific thoracic pathology. The results obtained through the implementation of our approach (accuracy above 96% for the best model) underline the good performance and potential of the developed predictive model.

Evaluation of the national AIDS program and HIV/AIDS surveillance system in Jordan.

The National AIDS Program in Jordan has faced numerous challenges, including insufficient funding, limited resources, and complexities brought on by refugee influxes. The absence of a reliable HIV/AIDS surveillance system further complicates tracking and responding to the epidemic. This study aimed to evaluate the performance and functionality of the National AIDS Program and the HIV/AIDS surveillance system. A qualitative study was conducted to evaluate the National AIDS Program and the HIV/AIDS Surveillance System in Jordan. The study involved 14 key informants specialized in HIV/AIDS Surveillance Systems. Interviews were guided by an interview guide based on the Updated Centers for Disease Control and Prevention Guidelines for Evaluating Public Health Surveillance Systems. Data analysis was performed through directed content analysis. The Voluntary Counseling and Testing Center in Jordan confronts multiple challenges, including poor infrastructure, limited accessibility, and inadequate facilities. Additionally, there is a lack of effective coordination between the Voluntary Counseling and Testing center and the Chest Diseases and Migrant Health Directorate, particularly regarding testing for Tuberculosis. HIV screening in Jordan is hindered by various factors, including disease sensitivity. Voluntary Counseling and Testing lacks HIV/AIDS specialists AND staff adequate training and fails to adhere to updated treatment guidelines. Persistent deficiencies in human resources, equipment, and training continue to plague the HIV/AIDS Surveillance System. Key informants expressed dissatisfaction with the data's usefulness, citing concerns over poor data quality. The data were seldom used for prioritizing resources, identifying at-risk individuals, assessing HIV/AIDS risk factors, or evaluating prevention and control measures. The National AIDS Program and HIV/AIDS Surveillance System activities in Jordan are unstructured, poorly coordinated, and inefficient. Many gaps related to National AIDS Program and HIV/AIDS Surveillance System performance and data were identified. Recommendations include developing an electronic surveillance system for data collection, notification, and reporting, and building the capacities of HIV/AIDS healthcare providers in screening, diagnosis, and management.

Comparison of Pneumonia-specific Scores, Sepsis Score and Generic Score in Predicting the Severity of Community-acquired Pneumonia: A Cross-sectional Study

Introduction: Pneumonia is defined as inflammation of the pulmonary parenchyma caused by an infectious agent. Community-acquired Pneumonia (CAP) is a heterogeneous disease with a significant disease burden, morbidity, and mortality. Severe Community-acquired Pneumonia (SCAP) has been proven to be associated with increased Intensive Care Unit (ICU) admission, mechanical ventilation, and mortality. Although several severity assessment tools are available, there is a lack of evidence to support one tool over another in patients with pneumonia. Aim: To compare the ability of pneumonia-specific scores {{Confusion, Urea, Respiratory rate, Blood pressure (CURB)- 65 and Expanded CURB-65)}, Sepsis score {quick Sepsisrelated Organ Failure Assessment (qSOFA)}, and Generic score {National Early Warning Score (NEWS)} in predicting SCAP patients at the time of hospital admission. Materials and Methods: This was a hospital-based crosssectional study conducted in the Department of Pulmonary Medicine, Government Hospital for Chest and Communicable Diseases, Andhra Medical College, Visakhapatnam, India, on 100 patients with clinically and radiologically diagnosed CAP over a period of six months from April 2023 to September 2023 after obtaining Institutional ethics clearance and informed consent. All four severity scores (CURB-65, eCURB-65, qSOFA, NEWS) were documented in each patient at the time of admission. Outcomes such as 30-day mortality and ICU admission were measured. Receiver Operating Characteristic (ROC) curve analysis was performed for mortality prediction and ICU admission for all four scoring systems, and statistical analysis was carried out using Statistical Packages for Social Sciences (SPSS) version 24.0. Results: Out of 100 patients, 62 (62%) were males, and the remaining 38 (38%) were females with a mean age of 56±15 years. The number of patients with co-morbidities was 48 (48%). Regarding addictive habits, smoking and alcohol played a significant role at 38% and 33%, respectively. A 30- day mortality was observed in 18 (18%) patients, and 20 (20%) patients received ICU treatment. The frequency of patients with co-morbidities such as Diabetes Mellitus (DM), Hypertension (HTN), Ischaemic Heart Disease (IHD), and Chronic Obstructive Pulmonary Disease (COPD) was 21%, 33%, 5%, and 3%, respectively. For ICU admission as an outcome measure, the Area Under Receiver Operating Characteristics (AUROC) values were as follows: CURB-65: 0.977 (95% CI: 0.949-1.00, p-value <0.001); Expanded CURB-65: 0.966 (95% CI: 0.931-1.00, p-value <0.001); qSOFA: 0.935 (95% CI: 0.881-0.989, p-value <0.001); NEWS score: 0.967 (95% CI: 0.934-1.00, p-value <0.001). Conclusion: In the present study, all four scoring systems were equally effective in detecting the need for ICU admission and predicting 30-day mortality among CAP patients at the time of admission. However, organ-specific tools (CURB-65 (2-3) moderate) have demonstrated valid and effective means of assessing severity compared to sepsis scores and generic tools.

Characteristics of drug resistance pulmonary tuberculosis among patients attending consultant clinic for chest and respiratory diseases in Kirkuk City

Characteristics of drug resistance pulmonary tuberculosis among patients attending consultant clinic for chest and respiratory diseases in Kirkuk City

Quantitative Assessment Characteristics of Small Pulmonary Vessel Remodelling in Populations at High Risk for COPD and Smokers Using Low-Dose CT.

To explore the morphological alterations in small pulmonary vessels in populations at high risk for chronic obstructive pulmonary disease (COPD) and smokers based on multiple computed tomography (CT) quantitative parameters. A total of 1969 Three Major Chest Diseases Screening Study participants with available demographic data and smoking history who underwent low-dose chest CT from 2018 to 2020 were included. All subjects were divided into normal, high risk for COPD, and COPD groups according to their pulmonary function test (PFT) results. Furthermore, the three groups were further subdivided into never-smokers, current smokers, and former smokers subgroups according to their smoking history. Quantitative parameters, such as the number, area at 6 mm~24 mm subpleura and volume of small pulmonary vessels, were extracted by computer software. Differences in small pulmonary vessel parameters among the groups were compared using two-way ANOVA. The number, area at 6 mm~24 mm subpleura and volume of small pulmonary vessels in the group at high risk for COPD were lower than those in the normal group (P<0.05). The number, area at 6 mm~24 mm subpleura and volume of small pulmonary vessels in the COPD group were higher than those in the normal group (P<0.05). The number, area of small pulmonary vessels at 6 mm~12 mm subpleura in current smokers with high risk for COPD were higher than those in former smokers with high risk for COPD (P<0.05). The number, area, and volume of small pulmonary vessels in populations at high risk for COPD were decreased. Smoking cessation may impede structural changes in small pulmonary vessels in populations at high risk for COPD.

A Privacy-Enhanced Framework for Chest Disease Classification using Federated Learning and Blockchain

A Privacy-Enhanced Framework for Chest Disease Classification using Federated Learning and Blockchain

Prevalence of Exercise-induced Desaturation in Survivors of Severe COVID-19 Pneumonia and the Predictive Value of Lung Ultrasound: A Cross-sectional Study

Introduction: Survivors of severe Coronavirus Disease2019 (COVID-19) pneumonia may experience ExerciseInduced Desaturation (EID), which can remain undiagnosed at discharge, as most exhibit normal resting Arterial Blood Gases (ABGs). This undiagnosed condition may lead to unexpected hospital readmissions, causing additional burden to the health system. However, the prevalence of EID among this population, especially in developing countries, is not well documented. Aim: To estimate the prevalence of EID among survivors of severe COVID-19 pneumonia and to explore the predictive role of Lung Ultrasound Scan (LUS) in detecting EID. Materials and Methods: This hospital-based, observational, cross-sectional study was conducted at the Institute of Chest Diseases in Kozhikode, Kerala, India from October 2021 to September 2022. It involved 153 COVID-19 patients aged 18 years and above who had recovered from severe pneumonia, were otherwise fit for hospital discharge, and had normal resting ABGs. The study examined the prevalence of EID using the 6-Minute Walk Test (6MWT). Additionally, it investigated the predictive ability of a LUS for EID. A LUS was performed on all patients and scoring was conducted according to the established protocol. Results: The mean age of the study subjects was 53.50±14.13 years, with 119 (77.8%) being male. During the 6MWT, 96 patients (62.7%) showed significant desaturation. A total of 83 (95.4%) subjects in the desaturated group required Non-Invasive Ventilation (NIV) compared to 4 (4.6%) in the non-desaturated group (p&lt;0.001). All 24 (100%) subjects in the desaturated group required Invasive Mechanical Ventilation (IMV), while none in the non-desaturated group did. The mean Length Of Stay (LOS) in the hospital was 35.50±13.35 days for the desaturated group, compared to 23.32±16.25 days for the non-desaturated group (p&lt;0.001). The LUS score was significantly higher in the desaturated group (16.61±5.92) than in the non-desaturated group (5.54±4.62). The Receiver Operating Characteristic (ROC) curve for the LUS score indicated a cut-off value of 8.5 for identifying significant EID. Conclusion: Survivors of COVID-19 who recovered from Acute Respiratory Failure (ARF) and have normal resting ABGs may still have significant EID. A protocol-based LUS score can potentially identify individuals at risk for EID.