Researchers Develop AI Algorithm to Predict Immunotherapy Response
|
By HospiMedica International staff writers Posted on 12 Sep 2018 |
A team of French researchers have designed an algorithm and developed it to analyze Computed Tomography (CT) scan images, establishing for the first time that artificial intelligence (AI) can process medical images to extract biological and clinical information. The researchers have created a so-called radiomic signature, which defines the level of lymphocyte infiltration of a tumor and provides a predictive score for the efficacy of immunotherapy in the patient.
In the near future, this could make it possible for physicians to use imaging to identify biological phenomena in a tumor located anywhere in the body without performing a biopsy.
Currently, there are no markers, which can accurately identify patients who will respond to anti-PD-1/PD-L1 immunotherapy in a situation where only 15 to 30% of patients do respond to such treatment. The more immunologically richer the tumor environment (presence of lymphocytes), the higher is the chances of immunotherapy being effective. Hence, the researchers tried to characterize this environment using imaging and correlate this with the patients’ clinical response. In their study, the radiomic signature was captured, developed and validated genomically, histologically and clinically in 500 patients with solid tumors (all sites) from four independent cohorts.
The researchers first used a machine learning-based approach to teach the algorithm how to use relevant information extracted from CT scans of patients participating in an earlier study, which also held tumor genome data. Thus, based solely on images, the algorithm learned to predict what the genome might have revealed about the tumor immune infiltrate, in particular with respect to the presence of cytotoxic T-lymphocytes (CD8) in the tumor, thus establishing a radiomic signature.
The researchers tested and validated this signature in other cohorts, including that of TCGA (The Cancer Genome Atlas), thus demonstrating that imaging could predict a biological phenomenon, providing an estimation of the degree of immune infiltration of a tumor. Further, in order to test the signature’s applicability in a real situation and correlate it to the efficacy of immunotherapy, it was evaluated using CT scans performed before the start of treatment in patients participating in five phase I trials of anti-PD-1/PD-L1 immunotherapy. The researchers found that the patients in whom immunotherapy was effective at three and six months had higher radiomic scores as did those with better overall survival.
In their next clinical study, the researchers will assess the signature both retrospectively and prospectively, using a larger number of patients and stratifying them based on cancer type in order to refine the signature. They will also use more sophisticated automatic learning and AI algorithms to predict patient response to immunotherapy, while integrating data from imaging, molecular biology and tissue analysis. The researchers aim to identify those patients who are most likely to respond to treatment, thereby improving the efficacy/cost ratio of treatment.
In the near future, this could make it possible for physicians to use imaging to identify biological phenomena in a tumor located anywhere in the body without performing a biopsy.
Currently, there are no markers, which can accurately identify patients who will respond to anti-PD-1/PD-L1 immunotherapy in a situation where only 15 to 30% of patients do respond to such treatment. The more immunologically richer the tumor environment (presence of lymphocytes), the higher is the chances of immunotherapy being effective. Hence, the researchers tried to characterize this environment using imaging and correlate this with the patients’ clinical response. In their study, the radiomic signature was captured, developed and validated genomically, histologically and clinically in 500 patients with solid tumors (all sites) from four independent cohorts.
The researchers first used a machine learning-based approach to teach the algorithm how to use relevant information extracted from CT scans of patients participating in an earlier study, which also held tumor genome data. Thus, based solely on images, the algorithm learned to predict what the genome might have revealed about the tumor immune infiltrate, in particular with respect to the presence of cytotoxic T-lymphocytes (CD8) in the tumor, thus establishing a radiomic signature.
The researchers tested and validated this signature in other cohorts, including that of TCGA (The Cancer Genome Atlas), thus demonstrating that imaging could predict a biological phenomenon, providing an estimation of the degree of immune infiltration of a tumor. Further, in order to test the signature’s applicability in a real situation and correlate it to the efficacy of immunotherapy, it was evaluated using CT scans performed before the start of treatment in patients participating in five phase I trials of anti-PD-1/PD-L1 immunotherapy. The researchers found that the patients in whom immunotherapy was effective at three and six months had higher radiomic scores as did those with better overall survival.
In their next clinical study, the researchers will assess the signature both retrospectively and prospectively, using a larger number of patients and stratifying them based on cancer type in order to refine the signature. They will also use more sophisticated automatic learning and AI algorithms to predict patient response to immunotherapy, while integrating data from imaging, molecular biology and tissue analysis. The researchers aim to identify those patients who are most likely to respond to treatment, thereby improving the efficacy/cost ratio of treatment.
Latest AI News
- AI Analysis of Smartwatch ECGs May Help Detect Weakened Heart Function
- AI Tool Speeds Echocardiogram Reporting With Comparable Accuracy
- AI Tool Predicts Hypertensive Crisis Up to 72 Hours Ahead
- AI Tool Improves Hospital Discharge Summaries to Support Follow-Up Care
- AI Chatbot Helps Women Identify Heart Disease Risks and Symptoms
- AI Tool Predicts Suicide Risk in Emergency Departments from Routine Data
- AI Model Improves Breast Cancer Survival Prediction
- AI Tool Prioritizes Peer Referrals to Expand HIV Testing Access
- Explainable AI Dermoscopy Tool Supports Risk Assessment for Skin Cancer
- AI Tool Predicts Cancer Survival and Biological Age from Single Facial Photo
- AI Tool Improves Smartphone Detection of Abnormal Pediatric Lung Sounds
- AI Tool Detects Coronary Heart Disease from Face and Tongue Images
- Optical Imaging System Helps Predict Chemotherapy Response in Cancer
- AI Tool Predicts Long-Term Cardiovascular Risk from Sleep Study ECG
- Predictive Model Supports Growth Hormone Treatment Planning in Idiopathic Short Stature
- AI Model Predicts Prolonged Sitting in Chronic Pelvic Pain
Channels
Artificial Intelligence
view channel
AI Analysis of Smartwatch ECGs May Help Detect Weakened Heart Function
Left ventricular systolic dysfunction (LVSD) occurs when the heart’s main pumping chamber does not contract effectively. The condition can remain asymptomatic for some time but may progress to symptomatic... Read more
AI Tool Speeds Echocardiogram Reporting With Comparable Accuracy
Echocardiography is the most widely used form of cardiac imaging, playing a key role in diagnosing heart disease and guiding treatment decisions. However, reviewing ultrasound images and documenting cardiac... Read moreCritical Care
view channel
AI-Derived Heart Age Linked to Cardiovascular and Dementia-Related Mortality
Cardiovascular disease is increasingly associated with dementia-related mortality and other forms of age-related decline. Identifying people with greater long-term vulnerability before severe outcomes... Read more
Inhaled Therapy Uses Modified Bacteria to Break Down Pseudomonas Biofilms
Biofilms are protective layers of bacteria that can form inside endotracheal tubes during mechanical ventilation, making infections difficult to treat because intravenous antibiotics often struggle to... Read moreSurgical Techniques
view channel
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 more
Minimally Invasive Balloon Procedure May Redirect Blood Flow During Cardiac Arrest
Out-of-hospital cardiac arrest has a low survival rate, and patients who do not respond to prolonged advanced resuscitation have few remaining treatment options. During cardiopulmonary resuscitation, blood... 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 moreHealth IT
view channel
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 more
EHR Alerts Support Dosing, Sedation, and Shock Recognition in Cardiac Care
Electronic health record alerts can add to clinician workload when they are poorly targeted. In critical cardiac care, however, delayed decisions can affect treatment timing, sedation exposure, and escalation... 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







