New AI Model Based on 3D CT Scans Improves Accuracy of Machine Learning in COVID-19 Diagnosis
|
By HospiMedica International staff writers Posted on 17 Dec 2021 |

Researchers have developed an artificial intelligence (AI) model that can diagnose COVID-19 as well as a panel of professional radiologists, while preserving the privacy of patient data.
An international team of researchers, led by the University of Cambridge (Cambridge, England) and the Huazhong University of Science and Technology (Hubei, China), used a technique called federated learning to build their model. Using federated learning, an AI model in one hospital or country can be independently trained and verified using a dataset from another hospital or country, without data sharing. The researchers based their model on more than 9,000 CT scans from approximately 3,300 patients in 23 hospitals in the UK and China. Their results provide a framework where AI techniques can be made more trustworthy and accurate, especially in areas such as medical diagnosis where privacy is vital.
AI has provided a promising solution for streamlining COVID-19 diagnoses and future public health crises. However, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a challenge for training a model that can be used worldwide. In the early days of the COVID-19 pandemic, many AI researchers worked to develop models that could diagnose the disease. However, many of these models were built using low-quality data, ‘Frankenstein’ datasets, and a lack of input from clinicians. Many of the same researchers from the current study highlighted that these earlier models were not fit for clinical use in the spring of 2021.
The international team of researchers used two well-curated external validation datasets of appropriate size to test their model and ensure that it would work well on datasets from different hospitals or countries. The researchers based their framework on three-dimensional CT scans instead of two-dimensional images. CT scans offer a much higher level of detail, resulting in a better model. They used 9,573 CT scans from 3,336 patients collected from 23 hospitals located in China and the UK.
The researchers also had to mitigate for bias caused by the different datasets, and used federated learning to train a better generalized AI model, while preserving the privacy of each data centre in a collaborative setting. For a fair comparison, the researchers validated all the models on the same data, without overlapping with the training data. The team had a panel of radiologists make diagnostic predictions based on the same set of CT scans, and compared the accuracy of the AI models and human professionals. The researchers say their model is useful not just for COVID-19, but for any other diseases that can be diagnosed using a CT scan.
“AI has a lot of limitations when it comes to COVID-19 diagnosis, and we need to carefully screen and curate the data so that we end up with a model that works and is trustworthy,” said co-first author Hanchen Wang from Cambridge’s Department of Engineering.
“Before COVID-19, people didn’t realize just how much data you needed to collect in order to build medical AI applications,” said co-author Dr. Michael Roberts from AstraZeneca and Cambridge’s Department of Applied Mathematics and Theoretical Physics. “Different hospitals, different countries all have their own ways of doing things, so you need the datasets to be as large as possible in order to make something that will be useful to the widest range of clinicians.”
Related Links:
University of Cambridge
Huazhong University of Science and Technology
Latest COVID-19 News
- Low-Cost System Detects SARS-CoV-2 Virus in Hospital Air Using High-Tech Bubbles
- World's First Inhalable COVID-19 Vaccine Approved in China
- COVID-19 Vaccine Patch Fights SARS-CoV-2 Variants Better than Needles
- Blood Viscosity Testing Can Predict Risk of Death in Hospitalized COVID-19 Patients
- ‘Covid Computer’ Uses AI to Detect COVID-19 from Chest CT Scans
- MRI Lung-Imaging Technique Shows Cause of Long-COVID Symptoms
- Chest CT Scans of COVID-19 Patients Could Help Distinguish Between SARS-CoV-2 Variants
- Specialized MRI Detects Lung Abnormalities in Non-Hospitalized Long COVID Patients
- AI Algorithm Identifies Hospitalized Patients at Highest Risk of Dying From COVID-19
- Sweat Sensor Detects Key Biomarkers That Provide Early Warning of COVID-19 and Flu
- Study Assesses Impact of COVID-19 on Ventilation/Perfusion Scintigraphy
- CT Imaging Study Finds Vaccination Reduces Risk of COVID-19 Associated Pulmonary Embolism
- Third Day in Hospital a ‘Tipping Point’ in Severity of COVID-19 Pneumonia
- Longer Interval Between COVID-19 Vaccines Generates Up to Nine Times as Many Antibodies
- AI Model for Monitoring COVID-19 Predicts Mortality Within First 30 Days of Admission
- AI Predicts COVID Prognosis at Near-Expert Level Based Off CT Scans
Channels
Artificial Intelligence
view channel
Explainable AI Examines Sepsis Mortality Risk and Emergency Care Delays
Preventing sepsis-related deaths in emergency departments (EDs) remains challenging because patient deterioration can result from multiple rapidly evolving and interconnected factors. These include triage... Read more
Causal AI Tool Withholds Ovarian Cancer Treatment Recommendations When Evidence Insufficient
Ovarian cancer treatment often requires individualized decisions, particularly when available patient data do not clearly favor one therapeutic approach. However, artificial intelligence (AI) systems may... Read moreCritical Care
view channel
Wearable Patch Enables Continuous Troponin Monitoring for Postoperative Cardiac Injury
Myocardial injury after noncardiac surgery (MINS) is heart muscle damage that occurs following procedures not involving the heart. Detecting MINS is challenging because most cases are asymptomatic and... Read more
Wearable Heart Mapping May Help Identify Cardiovascular Hospitalization Risk
Cardiac scar tissue can develop when heart muscle cells die and fail to regenerate, often due to vascular blockages or age-related changes, even in individuals without a history of heart attack.... Read moreSurgical Techniques
view channel
Modular Robotic Surgery System Cleared for General Surgery Procedures
Upper and lower abdominal procedures, including cholecystectomy, hernia repair, small-bowel resection, and gastric bypass, account for approximately 3.5 million operations annually in the U.... Read more
FDA Authorizes Robotic System for En Bloc Bladder Resection
Bladder cancer frequently recurs, making accurate staging essential for treatment planning. Conventional transurethral resection can fragment tumors, complicating margin assessment and detrusor muscle... Read more
Fluorescence Imaging Reveals Nerves Under Normal Operating-Room Lighting
Preventing unintended nerve injury remains a major concern during surgery, particularly in complex anatomical regions where nerves can be difficult to distinguish from surrounding tissue.... Read more
Programmable Microwave Ablation System Gains CE Mark for Minimally Invasive Tissue Ablation
Hospitals continue to seek minimally invasive approaches that simplify procedural planning and provide controlled energy delivery for tissue ablation. Thermal ablation systems are used across multiple... Read morePatient Care
view channelVirtual Reality Program May Reduce Anxiety Before Pediatric Surgery
Presurgery anxiety affects an estimated 50% to 75% of children undergoing surgery and can complicate anesthesia induction, increase postoperative pain, and prolong recovery. Sedation is often used to manage... Read more
Video-Based Support Helps Older Adults Clarify Kidney Disease Treatment Preferences
Advanced chronic kidney disease (CKD) involves progressive loss of kidney function that can lead to kidney failure and difficult treatment decisions. For older adults, these decisions may include choosing... Read moreMedical Imaging
view channel
AI Uses Routine MRI to Predict Deep Brain Stimulation Response in Dystonia
Dystonia is a debilitating neurological movement disorder characterized by involuntary muscle contractions that cause abnormal movements and postures. Deep brain stimulation (DBS) is one of the few treatments... Read more
AI Combines Brain Imaging Features to Identify Cognitive Impairment in CKD
Chronic kidney disease (CKD) can affect multiple organs, including the brain, with cognitive impairment emerging as a common complication. Changes in executive function, attention, and memory can reduce... Read moreAI Software Gains FDA Clearance for Brain Aneurysm Detection and Follow-Up
Unruptured intracranial aneurysms are often asymptomatic and can be difficult to detect on head computed tomography angiography, especially in busy acute-care workflows. Missed or delayed identification... Read more
Lung Ultrasound Predicts Progression of Interstitial Lung Abnormalities in Rheumatoid Arthritis
Interstitial lung abnormalities are a pulmonary concern in patients with rheumatoid arthritis, requiring monitoring to detect disease progression. However, tracking these changes often involves repeated... Read moreHealth IT
view channel
Telemonitoring Program Improves Quality of Life After Heart Failure Discharge
Heart failure is a chronic condition associated with high mortality, frequent hospitalizations, and reduced quality of life. Patients face particularly high risks of readmission and death after discharge,... Read more
Clinical Decision Support Tool Automates CKD Risk Assessment in Primary Care
Chronic kidney disease (CKD) requires timely diagnosis, risk assessment, and coordinated treatment in primary care. Delayed recognition can affect decisions about testing, blood pressure control, cardiovascular... Read morePoint of Care
view channel
Handheld Imaging Device May Help Identify Preterm Birth Risk Earlier
Preterm birth, defined as delivery before 37 weeks of pregnancy, can lead to serious neonatal complications, including neurological, developmental, and respiratory problems. However, identifying pregnancies... Read more
New Breath Condensate Testing Approach Enhances Reliability for COPD Monitoring
Chronic obstructive pulmonary disease (COPD) is a progressive lung condition that can increasingly impair breathing over time. Diagnosis and monitoring may be burdensome because patients often require... Read more
Continuous Glucose Monitoring Identifies Cardiometabolic Risk in Adults Without Diabetes
Dysglycemia—abnormal blood glucose regulation—can fluctuate throughout the day and often escape conventional screening. Clinicians typically rely on fasting plasma glucose and hemoglobin A1c, which offer... Read moreBusiness
view channel
Stryker Completes Acquisition to Broaden Shoulder Surgery Offerings
Stryker (Portage, MI, USA) has completed its acquisition of ZuriMED (Zurich, Switzerland), a privately held developer of the FiberLocker System, expanding its Sports Medicine portfolio with a commercialized... Read more








