When it comes to improving disease detection, diagnosis, and clinical care, Artificial Intelligence (AI) could potentially revolutionise the field of radiology. The technology has the potential to assist clinicians by uncovering hidden information within imaging scans invisible to even the well-trained eye.
In a paper, published in JAMA Oncology, Columbia University researchers demonstrate that applying artificial intelligence to standard-of-care imaging can help predict how well immunotherapy will work for patients with melanoma. In particular, they developed a machine-learning algorithm that analyses a patient’s computed tomography (CT) scans and creates a biomarker – known as a radiomic signature – that correlates with patient outcome.
In a prognostic analysis of prospectively collected clinical trial data from 575 patients with a diagnosis of advanced melanoma, a random forest algorithm found that 4 computed tomography imaging features, 2 related to tumour size and 2 reflecting changes in tumour imaging phenotype, best estimated overall survival with immunotherapy. The combination of these features (signature) outperformed Response Evaluation Criteria in Solid Tumors 1.1, the standard method based on tumour diameter.
The researchers aim to expand the project with his colleagues to a variety of different tumour types — such as lung cancer, colon cancer, renal cancer, and prostate cancer — as well as other treatments beyond immunotherapy. The researchers wanted to start with a novel therapy and chose melanoma because of the recent, rapid adoption of immunotherapy for the disease.
Currently, clinicians rely almost entirely on tumour size to estimate the benefit of therapy. Patients receive a baseline CT scan and then subsequent follow-up scans after treatment has begun. If the tumour shrinks, the treatment seems to be working, while growth implies that the patient’s disease is getting worse. But this is not necessarily the case with immunotherapy, and studies have shown that tumour size and growth does not always correlate with overall survival.
Most of the current response criteria were developed several decades ago to assess the response to systemic treatments like chemotherapy. Immunotherapy has new patterns of response and progression, with some patients having a transitory increase in tumour size and then a response. Because of that, we needed to create new tools to predict treatment success.
The researchers validated the algorithm on data from 287 patients with advanced melanoma who participated in the multicentre clinical trials, which administered the immunotherapy drug pembrolizumab. The radiomic signature, which used CT images obtained at baseline and 3-month follow-up, was able to estimate overall survival at 6 months with a high degree of accuracy. In fact, it outperformed the standard method based on tumour diameter, known as Response Evaluation Criteria in Solid Tumours 1.1 (RECIST 1.1), which is commonly used in clinical trials to assess treatment efficacy.
The field of radiology and imaging, in general, has never been more exciting with this artificial intelligence revolution. AI gives an opportunity to optimise the information that we have from all of our imaging modalities to speed diagnosis, to become more accurate and precise, and give patients more effective treatments.
As reported by OpenGov Asia, a data scientist said during an online demonstration of the solution that a toolkit that can reduce algorithmic bias in Artificial Intelligence (AI) tools for the health industry would mean better care for everyone. The unique risks in algorithmic bias come from the way that it allows the systematic and repeatable automation of biases to impact people on a previously impossible scale. Designers may input the assumptions into the technology so they should be tested to ensure they are not automating harm.
A significant increase in the number of AI startups in the healthcare sector is anticipated to positively influence the North American market growth during the forecast period. Additionally, the growing usage of artificial intelligence in the healthcare industry is among the other factors expected to fuel the demand for artificial intelligence in healthcare in North America.