Technology built and now deployed in Israel works to warn doctors if their patients’ uncoordinated treatment regimens could set them on course for hospitalization.
Significant numbers of elderly patients end up in hospital because of clashes between different drugs they are taking for preexisting conditions — or when their treatments are not adjusted based on the latest lab results. This is known in medical jargon as suboptimal polypharmacy.
Leumit Healthcare Services, one of Israel’s four healthcare providers, has deployed an artificial intelligence system developed by the Tel Aviv-based FeelBetter, which is designed to reduce instances of suboptimal polypharmacy harming patients. It was put in place in January, and there are no detailed statistics on its success yet — but a retrospective study suggests high effectiveness.
The study found that the system flags up to seven out of 10 elderly patients who are headed for such a hospitalization within three to nine months.
The research, which is not peer reviewed, looked at two decades worth of medical records for 153,000 Israeli managed care patients over the age of 65 who have more than one chronic condition and who take more than two prescribed medications.
The artificial intelligence tool generated lists of the patients who appeared, based purely on data, to be at risk of hospitalization due to suboptimal polypharmacy. Researchers then cross referenced their lists with data regarding which patients were actually hospitalized due to suboptimal polypharmacy, and found that the AI tool identified most cases.
“Many hospitalizations result from suboptimal polypharmacy, and our technology can give physicians the tools to identify 70% to 80% of those over 65 who are at risk of hospitalization, and to remove the gaps in their care,” Yoram Hordan, FeelBetter chief technology officer and co-founder, told The Times of Israel.
He added: “Suboptimal polypharmacy means that the regimen being used to take care of a patient’s chronic conditions isn’t the best fit for that specific patient’s needs. To address it, we look at all data related to their condition — lab results, medications and treatments, and this way we can identify gaps that may lead to hospitalization. The key is that the technology is constantly monitoring medical records.”
Leumit is FeelBetter’s first client, having integrated its artificial intelligence tool into its medical records system in January. The AI tool is now subject of a trial at Brigham and Women’s Hospital in Boston.
Hordan said that Leumit doctors have already received many alerts from the tool, prompting them to examine the treatment being given to specific patients. “We’ve already provided insights to clinicians recommending changes to treatment regimens for hundreds of patients,” he stated.
Dr. Avivit Golan, a senior official at Leumit, said that the technology advances the provision of medicine tailored to each patient’s needs, ensuring that the treatment given to patients best meets their specific needs. “It allows clinical pharmacists to play a critical and leading role in assessing overall health status and determining whether prescribed medications are optimally meeting the goals of care and individual patient needs,” she commented.