Artificial intelligence has been near the top of many healthcare CIOs’ wish lists in 2019. It’s more than a bright, shiny object – it’s a set of technologies that can help healthcare provider organizations accomplish quite a bit on both the clinical and business sides of operations.

But not many provider organizations have made much progress with AI yet. Still, 2019 has seen a lot of progress being made by some forward-looking providers dipping their toes into the AI waters. And some of these providers have results to brag about.

Dealing with lung nodule findings

Summa Health is a nonprofit health system in Northeast Ohio. The Greater Akron Chamber documents Summa Health as the largest employer in Summit County with more than 7,000 employees. Summa Health provides comprehensive emergency, acute, critical, outpatient and long-term/home care.

The growing use of CT chest imaging has resulted in increased incidental lung nodule findings on imaging studies. These nodules have historically proved problematic for follow-up. According to the Journal of the American College of Radiology (February 2016), follow-up rates for incidental nodules range from 30-50%.

“Patients seen in the emergency department are particularly vulnerable to being lost to follow-up on their incidental findings, something unrelated to their original emergency visit,” explained Sandy Kohut, lead lung navigator at Summa Health. “Additionally, arranging follow-up care and further diagnostic studies for asymptomatic conditions such as lung nodules presents a challenge to healthcare organizations.”

However, earlier detection means earlier treatment, which means additional treatment options and increased rates of survival.

“As a result, a team at Summa Health launched a multi-pronged quality improvement project to improve identification and appropriate follow-up of incidental lung nodules identified in emergency patients,” Kohut said.

Natural language processing-driven analytics

Summa Health turned to health IT vendor Nuance Communications for help with this challenge. “Nuance’s mPower Clinical Analytics solution would provide us with automated data mining and reporting tools to help identify emergency department patients with incidental lung nodules for follow-up,” said Laura Musarra, senior business performance analyst at Summa Health.

“Summa leveraged both Nuance’s PowerScribe 360 reporting platform and Nuance’s mPower Clinical Analytics to enable the multidisciplinary team to improve follow-up around incidental findings, and in doing so, lead to improved care,” she explained.

Specifically, PowerScribe 360 Reporting is a real-time radiology reporting system that helps radiologists generate high-quality reports quickly and efficiently to increase physician satisfaction and improve patient care, said Musarra.

“mPower Clinical Analytics is a radiology-specific natural language processing-driven analytics platform,” she added, speaking of the AI technology NLP. “It enables users to easily query and analyze large amounts of unstructured or dictated notes and data in radiology reports, saving time and automating laborious data mining processes. It unlocks valuable data and provides insights, making it easier to monitor, understand and improve clinical and operational performance.”

A huge boost in identified patients

In the first six months, Summa Health’s quality improvement initiative helped realize a 662% increase in the number of patients identified each month for follow-up – from 8 per month to 61 per month.

“For patients with actionable lung nodules (>8mm), consultations to pulmonologists were expedited by lung navigators, with approval from primary care physicians to lung nodule clinics,” Musarra explained. “The increased number of patients contributed to the opening of a new lung nodule clinic.”

Most important, the multidisciplinary team established a best practice in dealing with incidental findings.

“They conduct regular review of CT scans of incidental lung nodules to prevent the issue of overdiagnosis,” Musarra explained. “The team carefully weighs additional and potentially risky testing or procedures for conditions that may be benign and could cause harm for conditions that would not lead to morbidity or mortality if they were never detected.”

Also in 2019 in the realm of healthcare AI, Sutter Health, a health system based in Sacramento, California, has made innovation a part of its mission. It’s made investments in many different technologies, research projects and medical advancements to improve the patient experience and patient outcomes.

Among other things, Sutter Health created and launched its Virtual Symptom Checker, a new artificial intelligence program to check symptoms based on severity and medical history. It reveals potential causes and next steps.

“Creating human connections is one of the most important things we can do as an integrated health system, being whenever our patients and their families need us the most,” said Dr. Albert Chan, chief of digital patient experience at Sutter Health. “Thus far, more than 50% of our symptom checker interactions happen after hours.”

With AI, the health system can take something meaningful like answering patients’ questions in the wee hours of the morning and make that systematic, he added.

“When you are concerned or sick, we aim to connect you to the care that you need – reducing friction one human interaction at a time,” he said.

Machine learning-enabled patient safety

Elsewhere on the healthcare AI front in 2019, Israel’s Sheba Medical Center, Tel Hashomer, one of the top 10 hospitals in the world according to Newsweek, announced the results of a study that validates the clinical impact of health IT vendor MedAware’s machine learning-enabled patient safety platform designed to minimize medication-related risks.

The findings were published August 7, 2019, in the Journal of American Medical Informatics Association (JAMIA) in a study entitled “Reducing drug prescription errors and adverse drug events by application of a probabilistic, machine-learning based clinical decision support system in an inpatient setting.”

Preventable errors account for 1 out of 131 outpatient deaths and 1 out of 854 inpatients deaths in the U.S., with direct costs of more than $20 billion and liability costs of more than $13 billion annually, according to Sheba research authors. Often errors that take place are the result of failures in computerized health information systems, according to the research.

Led by Dr. Gadi Segal, head of internal medicine, Sheba Medical Center researchers assessed the quality, accuracy and impact of MedAware’s medication safety platform.

Physicians at Sheba analyzed results in a single medical ward, from a hospital-wide live implementation of MedAware, which had been integrated into the center’s existing EHR system. The platform monitored all medical prescriptions issued over 16 months, with the department’s staff assessing all alerts for accuracy, clinical validity and usefulness, recording all physicians’ real-time responses to alerts generated.

The results of the study demonstrated a low overall alert burden, with MedAware-generated warnings for only 0.4% of all prescriptions. Additional findings included:

• 60% of warnings generated after a medication was already dispensed following changes in patient status.
• 89% of all alerts were considered accurate.
• 80% of all alerts were considered clinically useful.
• 43% of alerts caused changes in subsequent medical orders.

More AI to come in 2020

There are other cases of healthcare provider organizations doing AI work with positive outcomes in 2019. And 2020 promises many more healthcare AI projects.

Artificial intelligence is starting to mature in the healthcare industry, and healthcare CIOs, CMIOs and other leaders have a vast arena in which to experiment and prove that the complex technologies can improve healthcare delivery and operations.

Twitter: @SiwickiHealthIT
Email the writer: [email protected]
Healthcare IT News is a HIMSS Media publication.

Source: Read Full Article