Technology built in Israel and now being deployed works to alert doctors if their patients’ uncoordinated treatment regimens could put them on the path to hospitalization.
Significant numbers of elderly patients end up in hospital because of clashes between different drugs they take for pre-existing conditions – or when their treatments aren’t adjusted based on the latest lab results. This is known in medical jargon as suboptimal polypharmacy.
Leumit Healthcare Services, one of four healthcare providers in Israel, has deployed an artificial intelligence system developed by Tel Aviv-based FeelBetter designed to reduce cases of sub-optimal polypharmacy harming patients. It was introduced in January and there are no detailed statistics on its success yet, but a retrospective study suggests high effectiveness.
The study found that within three to nine months, the system will flag up to seven out of ten elderly patients who are on their way to such a hospitalization.
The study, which has not been peer-reviewed, looked at medical records from two decades of 153,000 Israeli healthcare patients over the age of 65 who have more than one chronic condition and are taking more than two prescription drugs.
The artificial intelligence tool generated lists of the patients who, based purely on data, appeared to be at risk of hospitalization due to suboptimal polypharmacy. Researchers then referenced their lists of data on which patients were actually hospitalized for suboptimal polypharmacy, and found that the AI tool identified most cases.
“Many hospitalizations are the result of sub-optimal polypharmacy, and our technology could give physicians the tools to identify 70 to 80 percent of people over 65 who are at risk of hospitalization and to close the gaps in their care,” says Yoram Hordan, FeelBetter’s head of technology. officer and co-founder, told The Times of Israel.
He added: “Sub-optimal polypharmacy means that the regimen used to care for a patient’s chronic conditions may not best suit that particular patient’s needs. To address this, we look at all the data with regarding their condition – lab results, drugs and treatments, and in this way we can identify gaps that could lead to hospitalization.The key is that the technology is constantly checking medical records.”
Leumit is FeelBetter’s first customer, which in January integrated its artificial intelligence tool into its medical record system. The AI tool is now the subject of a trial at Brigham and Women’s Hospital in Boston.
Hordan said Leumit doctors have already received many warnings from the tool, prompting them to investigate the treatment being given to specific patients. “We have already provided insights to clinicians recommending changes in treatment regimens for hundreds of patients,” he stated.
dr. Avivit Golan, a senior official at Leumit, said the technology promotes drug delivery tailored to each patient’s needs so that the treatment given to patients best suits their specific needs. “It enables clinical pharmacists to play a critical and leadership role in assessing overall health status and determining whether prescription medications optimally meet patients’ goals of care and individual needs,” she noted.