Comparison of the Discrimination Performance of AI Scoring and the Brixia Score in Predicting COVID-19 Severity on Chest X-Ray Imaging: Diagnostic Accuracy Study.

BACKGROUND: The artificial intelligence (AI) analysis of chest x-rays can increase the precision of binary COVID-19 diagnosis. However, it is unknown if AI-based chest x-rays can predict who will develop severe COVID-19, especially in low- and middle-income countries. OBJECTIVE: The study aims to compare the performance of human radiologist Brixia scores versus 2 AI scoring systems in predicting the severity of COVID-19 pneumonia. METHODS: We performed a cross-sectional study of 300 patients suspected with and with confirmed COVID-19 infection in Jakarta, Indonesia. A total of 2 AI scores were generated using CAD4COVID x-ray software. RESULTS: The AI probability score had slightly lower discrimination (area under the curve [AUC] 0.787, 95% CI 0.722-0.852). The AI score for the affected lung area (AUC 0.857, 95% CI 0.809-0.905) was almost as good as the human Brixia score (AUC 0.863, 95% CI 0.818-0.908). CONCLUSIONS: The AI score for the affected lung area and the human radiologist Brixia score had similar and good discrimination performance in predicting COVID-19 severity. Our study demonstrated that using AI-based diagnostic tools is possible, even in low-resource settings. However, before it is widely adopted in daily practice, more studies with a larger scale and that are prospective in nature are needed to confirm our findings.

Accuracy of Bedside Lung Ultrasound in Emergency (BLUE) Protocol to Diagnose the Cause of Acute Respiratory Distress Syndrome (ARDS): A Meta-Analysis.

BACKGROUND: There is a stigma that ultrasound cannot be used to see abnormalities in the air-filled organs makes ultrasound rarely used to identify lung abnormalities. This study purpose comparing diagnostic accuracy of BLUE protocol with gold standard for each diagnosis causing acute respiratory failure. METHODS: Systematic search was done in 6 databases (Pubmed/MEDLINE, Embase, Cochrane Central, Scopus, Ebscohost/CINAHL dan Proquest) and multiple grey-literature sources for cross-sectional studies. We manually extracted the data from eligible studies and calculated pooled sensitivity, pooled specificity, likelihood ratio (LR) and diagnostic odds ratio (DOR). We follow PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) guideline throughout these processes. RESULTS: Four studies has been picked from total 509 studies involved. The results yield parameters indicating BLUE protocol as a reliable modality to diagnose pneumonia with pooled sensitivity 84% (95% CI, 76-89%),  pooled specificity 98%  (95% CI, 93-99%), LR+ 42 (95% CI, 12-147), LR- 0.12 (95% CI, 0.07-0.2) and DOR 252 (95% CI, 81-788), respectively. It also considerably applicable to diagnose pulmonary oedema with pooled sensitivity 89% (95% CI, 81-93%), pooled specificity 94% (95% CI, 89-96%), LR+ 14 (95% CI, 8-25), LR- 0.165 (95% CI, 0.11-0.24), and DOR 116 (95% CI, 42-320), respectively. CONCLUSION: BLUE protocol has good diagnostic accuracy to diagnose pneumonia and pulmonary oedema. We recommend implementing BLUE protocol as a tool in evaluating cause of ARF.

Variation of usual interstitial pneumonia using HRCT in Scleroderma Patients.

Progressive Systemic Sclerosis or Scleroderma is a systemic inflammation marked by endothelial damaged, fibrosis, and inflammation in skin, joints, and visceral organs. Pulmonary hypertension and interstitial pulmonary disease (Ssc-ILD) are the most reported pulmonary complications in scleroderma patients. The pathogenesis of SSc- ILD is not well understood and the spectrum of SSc-ILD ranges from minimal lung involvement, which is often non-progressive, to severe illnesses. Usual Interstitial Pneumonia's (UIP) is one pattern of Ssc-ILD, marked in one-third of the patients with characteristic of honeycomb appearance and bronchiectasis. It is very important to determine the UIP based on radiology imaging especially with the presence of a poor prognosis in patients with UIP. This case report will discuss the importance of finding UIP-type ILD patterns based on HRCT in patients with scleroderma and different outcome.

Misleading Diagnosis of Radiological Imaging of COVID-19 Pneumonia During Pandemic Era: Risk on the Existence of CMV Infection.

Coronavirus disease 2019 (COVID-19) is an acute respiratory disease which rapidly disseminated due to Severe Acute Respiratory Syndrome CoronaVirus-2 (SARS-CoV-2) virus. Clinical presentations of COVID-19 are fever, non-productive cough, and dyspnea. Although the diagnosis establishment is done by detecting the viral ribonucleic acid (RNA) through reverse transcription-polymerase chain reaction (RT-PCR) method, CT scan has an important role in detection and treatment of COVID-19 especially in high prevalence regions. Chest CT scan has high sensitivity yet low specificity because there are a lot of other pathological spectrums that also present features of COVID-19 such as ground glass opacities (GGO) and consolidation, one of them is CMV infection. The objective of this case report is to raise vigilance towards other diseases that have radiological image similarities with COVID-19, especially in the immunocompromised patients who are susceptible to viral infections like CMV infection so that the delay in the disease treatment can be prevented.

The Importance of Chest CT Scan in COVID-19.

The coronavirus disease 2019 (COVID-19) is a highly transmissible acute respiratory disease that is caused by the Severe Acute Respiratory Syndrome CoronaVirus-2 (SARS-CoV-2), a beta coronavirus first discovered in Wuhan, China, in late 2019. COVID-19 has been spreading swiftly globally, and as of March 2020, has been officially declared a pandemic by the World Health Organization (WHO). One of the challenges in managing COVID-19 is the identification of a swift, accessible, and reliable diagnostic modality that could serve as an alternative to a reverse-transcriptase polymerase chain reaction (RT-PCR). As of the writing of this paper, RT-PCR is still the recommended tool in diagnosing COVID-19, but the notion of a more prompt and accurate diagnostic tool is a possibility worth looking into. The objective of this case study is to investigate the importance and utility of chest computed tomography (CT) in the diagnosis of COVID-19, as increasing pieces of evidence suggest that chest CT could prove useful in the clinical pathway in diagnosing COVID-19.

Practical Guidelines Management of Graves Ophthalmopathy.

Graves' ophthalmopathy is the most common extra-thyroid manifestation in patients with Graves' disease, based on inflammatory and autoimmune conditions in orbital tissue. This practical guideline was formed by a multidiciplinary team, and is intended to provide guidance for diagnosis and management of Graves' ophthalmopathy in daily clinical practice to improve quality of care and treatment outcome.

Rad51 Expression in Nasopharyngeal Carcinoma and Its Association with Tumor Reduction: A Preliminary Study in Indonesia.

BACKGROUND: Overexpression of Rad51 protein in many tumor cells has been proven to increase radioresistance and can be related to the resistance of chemosensitivity of tumor cells. This preliminary study was conducted to determine the relationship between the Rad51 expression level in nasopharyngeal carcinoma and the response of the treatment based on the measurement of the tumor reduction. METHODS: Thirteen cases of the NPCs were analyzed. The expression levels of the Rad51 were examined from the pretreatment biopsies. Furthermore, tumor reductions were determined based on the change in sum longest diameter of the nasopharyngeal CT-scan before and after therapy. RESULTS: The expression level of the Rad51 was associated with the reduction of tumor mass. The P value was 0.049 and the correlation coefficient was 0.479. CONCLUSION: The tumor cells Rad51 expression levels may affect the tumor reduction of NPC after the therapy.