Healthcare systems that leverage AI tools can not only improve operations and radiology quality, but also patient monitoring, which can result in greater staff efficiency, higher hospital admission rates, and improved access and outcomes for patients.
A collaboration between East Alabama Medical Center, Inflo Health and the American College of Radiology Learning Network has begun using machine language models and advanced natural language processions to extract data from radiology reports to improve follow-up of patients with pulmonary disease, while Stamford Health in Connecticut was able to extend additional radiology resources to all cardiovascular patients through automation.
It’s also worth noting that this week, Lunit, a provider of cancer diagnostics and treatment products, announced that two recent studies evaluating artificial intelligence-based mammography screening have shown that the technology can also estimate the development of breast cancer up to six years in advance positive diagnosis.
“If the results of commercial artificial intelligence algorithms developed for immediate cancer detection can estimate future cancer risk, then more right and reliable risk estimates in the brief term could lead to the development of tailored, personalized preventive measures, which would likely lead to earlier detection of breast cancer and less aggressive treatment. treatment,” European researchers said in a statement on Wednesday.
EAMC improves patient monitoring
An Alabama health organization announced Thursday that through a partnership to track radiology observations using artificial intelligence and by engaging primary care physicians in acute care communication, the implementation rate of its recommendations increased by 74%.
EAMC has partnered with Inflo Health, which uses radiology-specific language models and advanced NLP, and the American College of Radiology to augment patient engagement and physician productivity.
The AI-powered software is run according to measurement specifications defined in ACR’s ImPower program, which helps organizations develop leadership skills and improvement methods to achieve better results, helping EAMC radiologists identify additional imaging recommendations and actionable lessons learned, and also automating workflows in branches.
The goal of the collaboration with EAMC was to improve consistent follow-up of post-examination recommendations for incidentally detected pulmonary nodules, as well as to augment the proportion of examinations that received timely follow-up, the organizations said in a statement.
EAMC also implemented AI software adequacy measures, automating the process of identifying incidental lung nodules that met inclusion criteria.
According to Melinda Johnson, the organization’s director of radiology, these efforts have significantly streamlined EAMC’s processes, reduced manual effort and increased staff efficiency.
“It has also enabled us to expand the care navigator role into other clinical areas,” she said in a statement. “This partnership is an example of how the integration of advanced technology with strategic collaboration can set new standards in radiology practices and operational excellence.”
As a result, manual tasks were reduced from five hours a week to just 15 minutes, a 95% augment in productivity, say colleagues.
To streamline patient completion and communicate recommended imaging tests, EAMC eliminated operational barriers, including inconsistent communication between acute care and primary care. As a bonus, the effort generated approximately $9,000 in additional revenue per month.
“Leveraging technology to standardize and optimize clinical processes requires a collaborative effort between organizations and software vendors working in tandem to ensure the solution is built on an understanding of the problem,” added Judy Burleson, ACR vice president of quality management programs.
“The education and quality improvement support provided by the ImPower program, combined with EAMC’s commitment to improving patient outcomes and Inflo Health’s willingness to adapt its product, have made this progress possible,” she said.
Stamford Health increases access
Stamford Health, a nonprofit health care provider in Fairfield County, Connecticut, announced earlier this month modern automated cardiovascular screening tests that enable more timely and personalized follow-up care for at-risk patients.
Stamford Health’s Heart & Vascular Institute said in a statement that its AI-powered cardiovascular screening tool significantly improves the early detection and treatment of cardiovascular disease across its patient population.
The institute uses Bunkerhill Health’s advanced algorithm to identify the presence of calcium in coronary arteries by calculating total coronary artery calcium concentration, or Agatston Index, an indicator of the future risk of coronary artery disease in a specific patient population.
CAC screening would normally require a special order from a doctor, but the automated algorithm now runs in the background of all non-gated chest CT scans, such as those used to screen for lung cancer.
“We are focused on providing cutting-edge, sophisticated care to our patients,” said Dr. Ronald Lee, chief of radiology at Stamford Health.
Patients will automatically receive a CAC result during each noncontrast chest CT scan, and if an elevated CAC is detected, the patient’s primary care physician or cardiologist will be notified of their result and risk.
“This tool enhances our ability to detect early signs of cardiovascular disease and ensures patients receive the follow-up care they need to prevent serious health outcomes,” added Dr. David Hsi, chief of cardiology and co-director of the institute.
Testing artificial intelligence for predictive mammography
The accuracy of mammography screening has long been a challenge because radiology protocols often require double readings of scans. AI algorithms can flag areas of concern and provide breast and exam-level malignancy assessments to aid radiologists in image readings.
Lunit said Wednesday that researchers from the Cancer Registry of Norway and Odense University Hospital in Denmark, already using INSIGHT MMG tools, have shown that they can also improve the predictive value of national breast cancer screening programs, which will ultimately lead to earlier diagnosis and treatment of women.
A Norwegian retrospective testThe Artificial Intelligence Algorithm for Subclinical Breast Cancer Detection study, completed in August and published earlier this month online, analyzed imaging data from a cohort of 116,495 women ages 50 to 69 who had no history of breast cancer.
The Norwegian Cancer Registry, which has a contract with Lunit to research the operate of AI software, offers digital mammography screenings every two years. Patients in the retrospective cohort study underwent at least three consecutive biennial screenings between September 13, 2004 and December 21, 2018, at nine breast screening centers nationwide.
The researchers divided this cohort into three groups – women with breast cancer diagnosed after the third round of screening, women with interval breast cancer diagnosed after the third round of screening, and women without breast cancer diagnosed after three consecutive screenings and six years without a cancer diagnosis – detection of 1,265 cancers detected by screening and 342 interval cancers.
For people diagnosed with breast cancer – defined as ductal carcinoma in situ or invasive breast cancer – mean absolute AI scores were higher for developing breasts compared to those who did not develop cancer four to six years before their final detection. AI scores were also higher and increased more rapidly across three consecutive rounds of screening in women diagnosed with screen-detected cancer compared with interval cancer.
“These findings suggest that commercial artificial intelligence algorithms developed for breast cancer detection may identify women at high risk of developing breast cancer in the future, offering a path to personalized screening methods that may lead to earlier cancer diagnosis,” the researchers say.