ASH 2018: Machine Learning–Based Model to Risk Stratify Patients With Myelodysplastic Syndromes
Researchers used machine learning to develop a new system to analyze genomic and clinical data to provide a personalized overall outcome that is patient-specific in myelodysplastic syndromes. In tests, the system outperformed the current standard prognostic tool, suggesting the new model may offer patients and doctors a better and more personalized tool to understand a patient’s risk and inform treatment. These findings were presented by Nazha et al at the 2018 American Society of Hematology (ASH) Annual Meeting & Exposition (Abstract 793).
Patients diagnosed with myelodysplastic syndromes show a wide range of symptoms and may live for only a few months or for decades. About one-third of patients develop acute myeloid leukemia (AML). Predicting a patient’s risk of dying or developing AML is crucial, both to help patients understand their disease and to help doctors determine a course of treatment. High-risk patients are generally treated with a stem cell transplant, which can cure the disease but carries significant risks, whereas other, less risky treatments are recommended for patients with a better prognosis. The best course of treatment for patients at intermediate risk can be unclear because individual clinical trials define risk thresholds in different ways.
“All treatment guidelines are driven by risk, which means that if we get the risk wrong, we get the treatment wrong,” said lead study author Aziz Nazha, MD, of the Cleveland Clinic, in a statement. “Improving and personalizing our prognostic models can help to delineate patients who are at higher vs lower risk—which is particularly challenging for those who fall into the intermediate range—and match them with the appropriate treatment.”
Currently, doctors use the Revised International Prognostic Scoring System (IPSS-R) to assess risk for patients with myelodysplastic syndromes. However, the IPSS-R underestimates or overestimates risk in up to one-third of patients, according to Dr. Nazha.
Machine Learning Algorithm
To improve prognostic tools, Dr. Nazha’s team developed a sophisticated machine learning algorithm that uses genomic and clinical data to determine a patient’s prognosis. They trained the system using patient data from Cleveland Clinic and Munich Leukemia Laboratory (1,471 patients total) and validated it in a separate collection of patient data from the Moffitt Cancer Center (831 patients).
In head-to-head comparisons using patient medical records, the new model correctly estimated overall survival 74% of the time, compared with 67% of the time for IPSS-R. The model correctly predicted a patient’s likelihood of developing AML relative to another patient 81% of the time, compared with 73% of the time for IPSS-R.
Like any decision-support tool, the model is intended to inform human clinicians, not to replace or compete with them, Dr. Nazha said. To further improve the model, the researchers are gathering feedback from clinicians and working to incorporate more outcomes, such as quality of life, into the model. They are also developing ways for the model to update the assessment of risk in response to changing conditions, such as when new test results are available or treatments are completed.
“This project started out of a frustration voiced by many of my patients who want to know what their own risk is and how their prognosis might differ from that of other patients,” said Dr. Nazha. “We wanted to build a personalized prediction tool that can give insights about a specific outcome for a specific patient.”
Dr. Nazha’s next step is to build a website where clinicians can input a patient’s clinical and genetic characteristics and get back the patient’s probability of surviving at different time points such as 6 months, 12 months, and 18 months.
“Understanding a patient’s prognosis allows us to more appropriately develop a treatment plan and counsel patients,” Dr. Nazha said. “We are optimistic an improved prediction will lead to more personalized care.”
Disclosure: See the study authors’ full disclosures at ash.confex.com.
The content in this post has not been reviewed by the American Society of Clinical Oncology, Inc. (ASCO®) and does not necessarily reflect the ideas and opinions of ASCO®.
