Issue link: https://beckershealthcare.uberflip.com/i/1090681
18 QUALITY IMPROVEMENT & MEASUREMENT How machine learning can reduce tests, improve treatments for ICU patients By Megan Knowles R esearchers from Princeton (N.J.) Univer- sity are using machine learning to design a system that could reduce the frequency of tests and improve the timing of critical treat- ments for intensive care unit patients. To create the system, the researchers used data from more than 6,000 patients admitted to an ICU between 2001 and 2012. e research team presented its results Jan. 6 at the Pacific Symposium on Biocomputing in Hawaii. e analysis looked at four blood tests mea- suring lactate, creatinine, blood urea nitro- gen and white blood cells. ese indicators help diagnose two serious problems for ICU patients: kidney failure and sepsis. "Since one of our goals was to think about whether we could reduce the number of lab tests, we started looking at the [blood test] panels that are most ordered," said co-lead study author Li-Fang Cheng. e team's algorithm uses a "reward func- tion" that encourages a test order based on how informative the test is at a given time. In other words, there is greater reward in giving a patient a test if there is a higher probability that the patient's state is significantly differ- ent from the previous measurement. To test the utility of the lab-testing policy they created, the researchers compared the reward function values that would have resulted from applying their system with the testing regimens that were actually used for the 6,060 patients in the study. e researchers found the policy that the machine learning algorithm generated would have yielded more information on the pa- tient's condition than the actual testing their clinicians followed. Additionally, when looking at white blood cell tests, the algorithm could have reduced the number of lab test orders by up to 44 percent. ey also found their approach would have helped alert clinicians to intervene some- times hours sooner when a patient's condi- tion started to deteriorate. "With the lab test-ordering policy that this method developed, we were able to order labs to determine that the patient's health had degraded enough to need treatment, on average, four hours before the clinician actually initiated treatment based on clini- cian-ordered labs," said senior study author Barbara Engelhardt, PhD. n 5 stats on the dangers of surgical smoke By Mackenzie Bean S moke from surgical tools can pose serious health risks for clinicians in the operating room. Here are five things to know about health hazards related to surgical smoke: 1. Surgical tools that cauterize or vaporize tissue can generate smoke that moves up to 40 miles an hour and contains toxic chemicals OR masks don't filter out, Nick Meginnis, a brand man- ager for Stryker Corp., told ABC Action News. 2. Surgical smoke can contain more than 150 hazardous chem- icals, including all 16 polycyclic aromatic hydrocarbons des- ignated as priority pollutants by the Environmental Protection Agency, according to an information sheet from the Association of periOperative Registered Nurses. 3. On average, daily exposure to surgical smoke is equivalent to the OR team smoking 27-30 unfiltered cigarettes, AORN said. 4. Perioperative nurses also report twice as many respiratory issues as the general population, according to AORN. 5. In June 2018, Rhode Island became the first state to legally require all hospitals and freestanding ASCs to use a smoke evacu- ation system for relevant surgical procedures. AORN said is work- ing with other states to implement similar regulatory changes. n Early intervention with infectious disease specialist linked to lower death rates By Anuja Vaidya P atients who received early intervention with an infectious disease physician experi- enced lower mortality rates and shorter lengths of stay, according to a study published in Clinical Infectious Diseases. Researchers conducted a retrospective analysis of administrative claims data from privately in- sured patients under age 65 years. They studied data from patients with an acute care stay in 2014 for selected infections who received early (by day three) or late (after day three) interven- tion with an infectious disease physician. The study shows patients who received care with infectious disease physician involvement by the third day of their hospitalization had a shorter length of stay, lower spending and lower mortal- ity rate in the initial stay as compared to patients who did not. Additionally, patients who received early infec- tious disease physician intervention had fewer readmissions and lower healthcare payments after discharge. n