Imaging

Researchers from New York-based Mount Sinai Health System have combined artificial intelligence, imaging and clinical data to rapidly detect COVID-19 in patients. In a study published this week in Nature Medicine, researchers used AI algorithms in conjunction with chest CT scans and patient history to quickly diagnose patients who were positive for COVID-19 and improve the detection of patients who presented with normal CT scans. "We were able to show that the AI model was as accurate as an experienced radiologist in diagnosing the disease, and even better in some cases where there was no clear sign of lung disease on CT," said Dr. Zahi Fayad, director of the BioMedical Engineering and Imaging Institute at the Icahn School of Medicine at Mount Sinai, in a statement. WHY IT MATTERS Because the symptoms of COVID-19 are non-specific, it can be difficult to diagnose. Meanwhile, the SARS-CoV-2 virus-specific reverse transcriptase polymerase chain reaction (RT-PCR) test commonly used to identify COVID-positive patients can take up to two days to complete – and clinicians face the possibility of false negatives. RT-PCR test kits are also in short supply throughout many parts of the country. This, researchers say, reiterates the need for other ways to quickly and accurately diagnose patients with COVID-19. Researchers relied on CT scans of more than 900 patients that had been admitted to 18 medical centers in 13 Chinese provinces. They included 419 confirmed COVID-19-positive cases and 486 COVID-19-negative scans. The team also had access to patients' clinical information, including blood test results, age, sex and symptoms.  Using patient data, Mount Sinai researchers developed an AI algorithm to produce separate probabilities of COVID-19 positivity based on CT images, clinical information and the two combined.  "In a test set of 279 patients, the AI system achieved an area under the curve of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist," researchers wrote. In addition, the algorithm correctly identified 17 of 25 patients whose RT-PCR results had tested positive for COVID-19 but who presented with normal CT scans; for comparison, radiologists had classified all the patients as COVID-negative.  Although clinicians in the United States do not frequently use CT scans to diagnose COVID-19, researchers say imaging can play a vital role in conserving hospital resources and treating patients quickly.  "The high sensitivity of our AI model can provide a 'second opinion' to physicians in cases where CT is either negative (in the early course of infection) or shows nonspecific findings, which can be common," said Fayad. "It's something that should be considered on a wider scale, especially in the United States, where currently we have more spare capacity for CT scanning than in labs for genetic tests," Fayad continued. THE LARGER TREND Researchers have increasingly relied on AI to diagnose and treat patients with the novel coronavirus. In March, cognitive computing platform vendor behold.ai announced it had developed an AI-based algorithm to flag chest X-rays from COVID-19. Calling its platform "instant triage," behold.ai predicted it could help speed COVID-19 diagnosis.  "As we evaluate further positive cases from across the world, our results will be further validated," said behold.ai Chief Medical Officer Dr. Tom Naunton Morgan.  "This will increase the utility of our instant triage and potentially help reduce the burden on healthcare systems as more and more cases of pneumonia present and require rapid diagnosis," Morgan said. Other technology vendors have adapted existing tuberculosis-detecting AI technology to help indicate COVID-affected lung tissue in chest X-rays. ON THE RECORD Mount Sinai researchers say their next steps will be to further develop the model to forecast patient outcomes and to share their results with other healthcare facilities. "This study is important because it shows that an artificial intelligence algorithm can be trained to help with early identification of COVID-19, and this can be used in the clinical setting to triage or prioritize the evaluation of sick patients early in their admission to the emergency room," said Dr. Matthew Levin, director of the Mount Sinai Health System's clinical data science team.  "This is an early proof [of] concept that we can apply to our own patient data to further develop algorithms that are more specific to our region and diverse populations," said Levin. "This toolkit can easily be deployed worldwide to other hospitals, either online or integrated into their own systems," said Fayad.   Kat Jercich is senior editor of Healthcare IT News. Twitter: @kjercich Healthcare IT News is a HIMSS Media publication.

POCUS technology from Butterfly Network expands screening capabilities, offering "an immediate and clear picture of what’s happening in a patient’s lungs."

The technique, called federated learning, is designed to enable collaboration among far-flung research organizations on machine learning models, while still protecting patient privacy.

Thirona and Delft Imaging have unveiled CAD4COVID, a tool to help triage COVID-19 cases and indicate the affected lung tissue.

“Instant triage” capability from behold.ai could speed diagnosis of COVID-19 and help ensure resources are allocated properly.

ADHA is working with RANZCR to launch the My Health Record CPD modules for clinical radiologists and imaging practices. 

The pilot showcases an approach to AI integration that keeps impact on the radiologist's workflow to a minimum.

Four experts in diagnostic imaging IT offer CIOs, CMOs and other leaders some best practices for making a complex technology work best for their own healthcare organizations.

A new study, conducted by Korean academic hospitals and Lunit, a medical AI company specializing in developing AI solutions for radiology and oncology, demonstrated the benefits of AI-aided breast cancer detection from mammography images. The study was published online on 6 February 2020, in Lancet Digital Health and features large-scale data of over 170,000 mammogram examinations from five institutions across South Korea, USA, and the UK, consisting of Asian and Caucasian female breast images. TOP FINDINGS One of the major findings showed that AI, in comparison to the radiologists, displayed better sensitivity in detecting cancer with mass (90% vs 78%) and distortion or asymmetry (90% vs 50%). The AI was better in the detection of T1 cancers, which is categorized as early-stage invasive cancer. AI detected 91% of T1 cancers and 87% of node-negative cancers, whereas the radiologist reader group detected 74% for both. Another finding was a significant improvement in the performance of radiologists, before and after using AI. According to the study, the AI alone showed 88.8% sensitivity in breast cancer detection, whereas radiologists alone showed 75.3%. When radiologists were aided by AI, the accuracy increased by 9.5% to 84.8%. An important factor in diagnosing mammograms is breast density and dense breast tissues, mostly from the Asian population, make it harder to interpret as dense tissue is more likely to mask cancers in mammograms. According to the study’s findings, the diagnostic performance of AI was less affected by breast density, whereas radiologists' performance was prone to density, showing higher sensitivity for fatty breasts at 79.2% compared to dense breasts at 73.8%. When aided by AI, the radiologists’ sensitivity when interpreting dense breasts increased by 11%. THE LARGER TREND Findings from a study published in Nature indicated that Google’s AI model spotted breast cancer in de-identified screening mammograms with greater accuracy, with fewer false positives and false negatives than experts, HealthCareITNews reported. Lunit recently raised a $26M Series C funding from Korean and Chinese investors, which the company said was its biggest funding round, according to a DealStreetAsia report in January.  ON THE RECORD “It is an unprecedented quantity of data with accurate ground truth--especially the 36,000 cancer cases, which is seven times larger than the usual number of datasets from resembling studies conducted previously,” said Hyo-Eun Kim, the first author of the study and Chief Product Officer at Lunit.  Prof. Eun-Kyung Kim, the corresponding author of the study and a breast radiologist at Yonsei University Severance Hospital, said: “One of the biggest problems in detecting malignant lesions from mammography images is that to reduce false negatives—missed cases—radiologists tend to increase recalls, casting a wider safety net, which brings an increased number of unnecessary biopsies.” “It requires extensive experience to correctly interpret breast images, and our study showed that AI can help find more breast cancer with lesser recalls, also detecting cancers in its early stage of development.” 

Last week, Victoria-based Melbourne Pathology became the latest pathology provider to upload reports to My Health Record (MHR). This allows both patients and clinicians to have convenient and secure access to their pathology reports. Other Victorian labs sharing reports with consumers and clinicians in the MHR include Alfred Health, Monash Health and VCS Pathology. The full list of participating providers is available here.  THE LARGER TREND Last June, the Northern Territory (NT) Department of Health became the first pathology provider to link the online tests results it is sharing via MHR with Lab Tests Online, HealthcareITNews reported. In the same month, South Australia (SA) Pathology also connected to the MHR. Based on the latest statistics from the Australian Digital Health Agency (ADHA) as of December 2019, there are 22.68 million MHRs, of which 12.99 million records have information in them. ON THE RECORD “Investigation results are one of the most common tools doctors use to evaluate your health. In the 2018-2019 financial year alone, Medicare funded over 147 million pathology tests,” said Professor Meredith Makeham, a GP and Chief Medical Adviser, ADHA in a statement.  “It’s easy to quickly lose track of your results, particularly if you don’t have a regular GP or when you are seeing a range of healthcare professionals to manage multiple conditions and tests. MHR allows you to keep your important test results safe in one place, which you and your healthcare providers can access at any time to make more informed decisions about your treatment or care.” Victorian-based general practitioner, Dr Nathan Pinskier, said: “When I need a patient to have a pathology test, I simply send an electronic request and the patient attends the lab with a paper copy. Since the lab already has the electronic request, there’s no human data entry, which greatly reduces the risk of patients receiving the wrong test. Once there’s a report, I receive a copy through my secure messaging software and my patient receives a copy in their MHR, where it can’t be lost and where future healthcare providers can review it to inform their own clinical decision-making.”