Implementation of an Artificial Intelligence-Based Double Read System in Capturing Pulmonary Nodule Discrepancy in CT Studies.

Studies show that up to 80% of all radiology errors are due to errors in perception. Early detection is critical for good outcomes in patients with primary lung cancer and lung metastasis. However, pulmonary nodules can be easily missed due to their small size. We prospectively applied a machine vision algorithm to CT studies containing lung parenchyma to detect pulmonary nodules, as well as a natural language processing algorithm to the text of the report to identify documentation of pulmonary nodules. Apparent discrepancies in perception - instances where a pulmonary nodule was not reported - were flagged for a secondary review by a radiologist. Four thousand and nine hundred studies were prospectively processed, of which 450 cases with potential discrepancies were detected. Preliminary manual analysis was performed to analyze the base error rate and to optimize thresholds for the machine vision and natural language processing algorithms, and 104 cases were flagged for final review. Of these 104 cases, 50 cases contained undocumented pulmonary nodules. Among these cases, 7 cases were classified as likely to be significant, where report addendums were done and the clinicians notified. We have successfully implemented an automated double read system to detect pulmonary nodule discrepancies, with minimal disruption to the radiology workflow and while keeping personal health information on-premises. This successful implementation demonstrates the viability of using an automated and secure radiology double-read system to improve patient safety in radiology workflows, either at a health system or an independent radiology practice.

Managing a Renal Transplant Programme During the COVID-19 Pandemic: Practical Experience from a Singapore Transplant Centre.

INTRODUCTION: Coronavirus Disease 2019 (COVID-19) has significantly affected the way healthcare is delivered in Singapore. Healthcare services such as renal transplantation had to rapidly adjust and meet the needs to (1) protect patients and staff, (2) ramp up, conserve or redeploy resources while (3) ensuring that critical services remained operational. This paper aims to describe the experience of the renal transplant programme at the Singapore General Hospital (SGH) in responding to the risks and constraints posed by the pandemic. METHODS AND MATERIALS: This is a review and summary of the SGH renal transplant programme's policy and protocols that were either modified or developed in response to the COVID-19 Pandemic. RESULTS: A multi-pronged approach was adopted to respond to the challenges of COVID-19. These included ensuring business continuity by splitting the transplant team into different locations, adopting video and tele-consults to minimise potential patient exposure to COVID-19, streamlining work processes using electronic forms, ensuring safe paths for patients who needed to come to hospital, ring-fencing and testing new inpatients at risk for COVID-19, enhancing precautionary measures for transplant surgery, ensuring a stable supply chain of immunosuppression, and sustaining patient and staff education programmes via video conferencing. CONCLUSIONS: Though the COVID-19 pandemic has reduced access to kidney transplantation, opportunities arose to adopt telemedicine into mainstream transplant practice as well as use electronic platforms to streamline work processes. Screening protocols were established to ensure that transplantation could be performed safely, while webinars reached out to empower patients to take precautions against COVID-19.

Diagnostic Ultrasound Services During the Coronavirus Disease (COVID-19) Pandemic.

OBJECTIVE. Nosocomial transmission of coronavirus disease (COVID-19) to frontline health care workers is well known, and health care workers may inadvertently become vectors for onward transmission. Ultrasound (US) service providers are at significant risk because scanning usually requires prolonged close patient contact. The bulky US equipment may also facilitate fomite transmission of disease. With increasing use of point-of-care and portable diagnostic US services, the risk is substantial. CONCLUSION. Our experience and protocols may help service providers with their own effective response against COVID-19.

Rapid Progression to Acute Respiratory Distress Syndrome: Review of Current Understanding of Critical Illness from Coronavirus Disease 2019 (COVID-19) Infection

The coronavirus disease 2019 (COVID-19) outbreak that started in Wuhan, Hubei province, China in December 2019 has now extended across the globe with >100,000 cases and 3,000 deaths reported in 93 countries as of 7 March 2020. We report a case of COVID-19 infection in a 64-year-old man who developed rapidly worsening respiratory failure and acute respiratory distress syndrome (ARDS) that required intubation. As the clinical spectrum of COVID-19 ranges widely from mild illness to ARDS with a high risk of mortality, there is a need for more research to identify early markers of disease severity. Current evidence suggests that patients with advanced age, pre-existing comorbidities or dyspnoea should be closely monitored, especially at 1-2 weeks after symptom onset. It remains to be seen if laboratory findings such as lymphopenia or elevated lactate dehydrogenase may serve as early surrogates for critical illness or markers of disease recovery. Management of ARDS in COVID-19 remains supportive while we await results of drug trials. More studies are needed to understand the incidence and outcomes of ARDS and critical illness from COVID-19, which will be important for critical care management and resource planning.

Torsion of a Myomatous, Non-gravid Uterus: CT Findings.

Uterine torsion is a rare condition which is part of a spectrum of gynecological emergencies. If diagnosis is delayed or the condition is left untreated, severe consequences such as infertility and life-threatening complications can arise. As presenting features are often non-specific and can be similar to commonly encountered gastrointestinal and urinary conditions, computed tomography is usually the first imaging modality utilized in an emergency setting. It is therefore important that the radiologist is familiar with recognizing computed tomography features of uterine torsion. We share our findings in a patient with uterine torsion in a non-gravid uterus, diagnosed on contrast-enhanced computed tomography with multiplanar reconstruction.