#AANAM – Precision Innovative Network and Splice Machine Will Present Predictive Healthcare Application at AAN Meeting

#AANAM – Precision Innovative Network and Splice Machine Will Present Predictive Healthcare Application at AAN Meeting

A new clinical application prototype that uses machine learning to help physicians predict the best treatment options for patients with multiple sclerosis (MS) will be unveiled at the American Academy of Neurology’s 2019 annual meeting May 4–10, in Philadelphia, Pennsylvania.

The prototype is called PIN Population Data Platform. It has been developed by Splice Machine, a company focused on developing artificial intelligence, and Precision Innovative Network (PIN), a company that uses large amounts of networked data to address the unmet needs of patients and help physicians make decisions to improve care.

Medical decision-making is a tricky task, as there are a multitude of factors that affect, for example, whether a patient will respond well to a treatment; therefore, making the right call is critical. Now, a newly developed clinical application prototype based on machine learning may be of help to predict the best treatment options for patients with multiple sclerosis (MS).

At the American Academy of Neurology’s 2019 annual meeting, to be held May 4–10, in Philadelphia, Splice Machine and Precision Innovative Network (PIN) — companies that focus on developing artificial intelligence and making it easier for physicians to practice medicine, respectively — will unveil a prototype that uses machine learning to help guide medical decision-making.

The prototype is called PIN Population Data Platform, and its an early predictive model focused on MS.

The healthcare prototype was developed by using multi-dimensional data from more than 300 MS patients. By understanding a wide array of patient data simultaneously — factors ranging from age and weight to patients’ mobility, dexterity, and gait — the model may help guide neurologists’ decisions as they predict how particular patients’ diseases will progress, and to ensure all patients are given the treatment(s) they are most likely to respond well to with minimal undesired side effects.

“Being able to capture the granular, robust data about a patient and contextualize it is a significant factor in the success of precision medicine,” Allen Gee, MD, PhD, a neurologist from PIN, said in a press release.

“If we understand the functionality of a patient’s nervous system by looking at data around gait, cognition, and dexterity, we can support the highest quality of medical decision-making and deliver the right therapies in the continuum of care,” Gee added.

The new prototype also is expected to reduce healthcare costs (by reducing unnecessary medical tests and procedures), improve communication between patients and doctors, and ultimately improve patient care and outcomes.

The companies are planning to offer this technology to pharmaceutical companies to help manage clinical trials, and to hospitals to help directly guide medical decision-making.

“Together with PIN, we are working to pioneer a path to improved patient care and outcomes, by allowing doctors to take control over disease and treatment decisions in a data-driven manner,” said Monte Zweben, Splice Machine co-founder and CEO.

“I’m proud to be part of the growing movement to improve patient care by empowering clinicians to leverage real-time data to determine and justify the optimal treatments for each person with confidence,” Zweben concluded.

2 comments

  1. Glenda says:

    This is scary to me. Will the patient be required to enter a lot of data? Can the physician “override” the PIN recommendation? Would he/she override if the PIN is part of the medical record and possibly be used as evidence against the physician? Please let physicians use their own brain and education to determine the best course of action. This is written by both a nurse and a patient with MS.

  2. Roberto Araya says:

    300 MS patients seems a very small amount of cases to detect useful patterns with Machine Learning algorithms.

Leave a Comment

Your email address will not be published. Required fields are marked *

Pin It on Pinterest

Share This