Patient hesitancy to seek care during the pandemic created the perfect storm for delayed care. But big data and analytics are driving population health at Southwestern Health Resources to close care gaps.

“There has been a dramatic decrease in willingness of people to seek healthcare, whether it’s for urgent, critical medical needs or routine screening,” Andrew Ziskind, MD, senior executive officer of Southwestern Health Resources told HealthITAnalytics. “Right now, there’s a public health crisis in the short term, but in the long term, there will be tens of thousands of new cancer cases because of a lack of screening.”

Four in ten adults reported avoiding care because of COVID-19, according to recent data from the Centers for Disease Control and Prevention. So closing care gaps required innovative thinking to manage populations. At the center of this strategy is actionable data.

“The first thing we can do for our existing members is to identify who has gaps,” Ziskind explained. “Our data is robust enough that we can see where the targets are geographically, age-wise, and so forth.”

As a clinically integrated network, Southwestern Health Resources has access to claims data and clinical data to inform these decisions.

“Claims data is a lagging indicator,” Ziskind argued. “But clinical data is probably the most important advantage of being a provider-based clinically integrated network. All of our primary care physicians are connected to us through a common electronic medical record.”

This connectedness allows for easy data sharing.

At traditional health systems, patients with diabetes who might have seen an ophthalmologist and closed a care gap during that visit may have forgotten to inform their primary care provider. While the gap in care is technically closed, the provider is unaware.

But an integrated data network eliminates this problem as the primary care providers can have access to all of the patient’s records.

“Documentation around gap closure is often very challenging. The more we can mine the data and identify alternatives, the better,” continued Ziskind. “We’re using the breadth of data that we have access to for identifying where the gaps are. Once we know what they are, we can then use a gap-targeted approach for each specific one.”

Southwestern Health Resources took a multi-pronged approach to targeting patients and closing their gaps in care. The network began by calling each patient with unfilled gaps, but the call center team members saw very low response rates.

“Patients are suspicious about phone calls. They sometimes are confused as to if the call is from the hospital or health system or insurance company,” highlighted Ziskind. “We found that the highest success rate is if the patient is contacted on behalf of their physician.”

Patients then had the option to seek care in person or have a provider come to their home. Patients who opted for in-office visits were given instructions on how to make an appointment and Southwestern Health facilitated services at home if the patient preferred.

“You have to customize at the level of the individual patient,” Ziskind emphasized. “We tried to get rid of any patient burden.”

Ensuring the information was culturally component was also critical. Not only does this include translating information into multiple languages, but it also means delivering messaging in a way that best suits patient need.

“There’s a component through local churches and community access. There’s traditional mail. There’s email. There’s social media,” Ziskind highlighted. “We’re really trying to take a multi-prong approach to enhancing awareness.”

These efforts began with data that allowed Southwestern Health Resources to identify gaps in care and thrived when data on individual patient preference was actionable. Customizing outreach improved gap closure and gave providers actionable information.

As gap closure efforts continue, Ziskind and team plan to focus on clinically relevant patient outcomes, including promoting preventive health screenings.

“More and more we’re trying to move upstream in the disease process. We’re focusing on risking risk as opposed to just the management of patients who have advanced, complex disease,” he concluded. “The earlier we can detect disease, the better the long-term outcome will be for the patient.”

The post How Big Data, Analytics Drives Population Health, Closes Care Gaps appeared first on Artificial Intelligence.

September 15, 2020 – While the rapid spread of COVID-19 has exposed many unflattering healthcare truths, the glaring health disparities highlighted by the pandemic are perhaps the most detrimental to patient health.

The virus has had a disproportionate impact on minority and underserved communities, shining a spotlight on existing clinical and non-clinical inequities.

“Minorities are more likely to suffer from chronic conditions like high blood pressure, diabetes, obesity, and heart disease. Additionally, these patient populations typically lack access to adequate healthcare, or have a limited understanding of the healthcare system,” said Sampson Davis, MD, an emergency medicine physician.

“These individuals also tend to work in the service industry – transportation, the food industry, or airports. In these jobs, there’s no work-from-home possibilities that can allow people to distance themselves socially. In that sense, there’s a heighted risk of exposure to COVID-19.”

In order to target and reduce the impact of the virus on minority populations, organizations have increasingly turned to data analytics techniques to better track COVID-19 spread.

“As healthcare experts, collecting data is invaluable in what we do. It allows us to track what is working and what is not. Without data, we will pretty much continue to do the same thing over and over again expecting a different outcome,” said Davis.

“In order to decrease the impact of this virus, we need to track which solutions work and which don’t work, as well as where the virus is currently having the biggest impact. The data also breaks down the tedious minutia needed for our pandemic response, because what works for one community won’t necessarily work for the next community.”

With data analytics tools, providers have been able to deliver the right care to the right patients at the right time. These technologies helped clinicians navigate the early months of the pandemic, allowing them to uncover essential information to appropriately treat their patients.

“We started off thinking medications like hydroxychloroquine would have an impact, which it hasn’t. What we have seen with the data collected is that a medication called dexamethasone has helped us to decrease the impact of the virus. We have also discovered that turning patients from a supine position on their back to lying on their chest or abdomen allows them to actively participate in their breathing, which improves their chances of recovery,” said Davis.

“The data has also enabled us to know where the hotspots were – that at one point in time the virus was surging in New York and New Jersey, and then it traveled south to Georgia and Florida, and then over to Texas and Colorado. When we know where these hotspots are, we can try to understand why these areas are impacted the most, and we can target interventions to mitigate the impact of the virus.”

In the coming months, as the country works to reduce the effect of COVID-19, Davis noted that the healthcare industry will need to use data to get ahead of the virus.

“We have experienced similar scenarios throughout history. We’ve seen polio, we’ve seen the flu, we’ve seen mumps and measles. These are all diseases that we now have vaccines for, and that is the result lot of discovering the technology to defeat the virus or the bacteria, but also collecting the data to know what works and what doesn’t,” said Davis.

“So now, we have to think about how we gather and share data across the country to pinpoint where the need is the greatest. And by knowing where the need is the greatest, we can then say that if we have a vaccine or treatment, we can start there to see what type of impact this treatment may have.”

Data sharing will also play a key role in mitigating the impact of coronavirus, Davis stated.

“The virus is ahead of us and we’ve had to do catch-up for the last six months. And now I feel like we’re starting to get to a place where things are balancing. Unfortunately, we have lost hundreds of thousands of lives. But at the same time, sharing the information liberally and equally across the table allows us to see where the greatest need is and how to make the greatest impact with the treatment of patients,” he said.

“When I started in medicine, we used paper charting, and now we have everything in a digital format with the latest information readily accessible. It goes without saying that data analytics are instrumental when it comes to healthcare delivery day in and day out, and it’s going to serve the same role in defeating this pandemic.”

The pandemic has highlighted the substantial care disparities that exist in healthcare, and many expect that the strategies developed during this period will endure even after the situation has waned.

“We will get past this moment with coronavirus. But it has shown us is that in order to achieve health equity, we have to defeat healthcare disparities. That means reducing the disproportionate numbers of minorities that suffer from high blood pressure, diabetes, heart disease, obesity, and other conditions,” Davis concluded.

“Coronavirus did not target one community or race or gender, but you can see those who are at greatest risk suffer the most. The beauty of collecting the data is not just that we have this information, but also that we can use this information to move forward. My hope is that we all step up and continuously push ourselves to be on the forefront of making a difference in our country.”

The post How Big Data Analytics Can Mitigate COVID-19 Health Disparities appeared first on Artificial Intelligence.

September 11, 2020 – A machine learning model was able to detect different clusters of gut bacteria that could potentially identify individuals with existing cardiovascular disease (CVD), according to a study published in the journal Hypertension.

Recent studies have found a link between gut microbiota, the microorganisms in human digestive tracts, and CVD, the leading cause of mortality worldwide. Gut microbiota is highly variable between individuals, and differences in gut microbial compositions between people with and without CVD have been reported.

“Based on our previous research linking gut microbiota to CVD in animal models, we designed this study to test whether it is possible to screen for CVD in humans using artificial intelligence screening of stool samples,” said Bina Joe, PhD, FAHA, the study director, Distinguished University Professor and Chairwoman of the department of physiology and pharmacology at the University of Toledo in Toledo, Ohio.

“Gut microbiota has a profound effect on cardiovascular function, and this could be a potential new strategy for evaluation of cardiovascular health.”

Researchers used data from the American Gut Project, an open platform for microbiome research based in the US. The team leveraged innovative machine learning methods to analyze microbial composition of nearly 1,000 stool samples. Approximately half of the samples were from people with CVD.

Researchers found that the model was able to identify different clusters of gut bacteria that could potentially help identify individuals with and without CVD. The results show the potential for machine learning and artificial intelligence to improve CVD screening.

“Despite the fact that gut microbiomes are highly variable among individuals, we were surprised by the promising level of accuracy obtained from these preliminary results, which indicate fecal microbiota composition could potentially serve as a convenient diagnostic screening method for CVD,” Joe said.

“It is conceivable that one day, maybe without even assessing detailed cardiovascular function, clinicians could analyze the gut microbiome of patients’ stool samples with an artificial machine learning method to screen patients for heart and vascular diseases.”

Researchers have previously used machine learning to improve cardiovascular disease treatment and detection. A study published in Cardiovascular Research showed that machine learning tools could predict patients’ long-term risk of heart attacks and cardiac deaths better than standard methods used by cardiologists.

In that study, researchers found that subjects’ predicted machine learning scores aligned accurately with the actual distribution of observed events.

“In this prospective trial, machine learning demonstrated high performance in risk assessment for myocardial infarction and cardiac death in asymptomatic subjects,” the researchers stated.  

“By objectively combining clinical data and quantitative CT measures, machine learning provided significantly superior risk prediction compared with the coronary artery calcium score. These promising results suggest that machine learning has a potential for clinical implementation to improve risk assessment.”

In a separate study published in 2018, a team from Stanford University were able to create a personal health management tool that combined EHR data and machine learning algorithms to accurately diagnose the heart condition known as abdominal aortic aneurysm (AAA).

Researchers used the hierarchical estimate from agnostic learning (HEAL) health management tool to analyze patients’ genome sequences and EHRs to identify individuals with the cardiovascular disease.

“For each individual, HEAL accurately predicted his/her AAA risk using personal genome and EHR data. On the other hand, for the same individual with newly adopted lifestyles resulting in physiological changes (e.g., from a high cholesterol to a low cholesterol diet), HEAL can immediately update his/her AAA risk upon corresponding changes conditioned on the person’s genome baseline,” Stanford researchers said.

“This allows us to further investigate the interplay between personal genomes and lifestyles underlying disease predisposition.”

As machine learning and AI become more widely used in healthcare, these tools could make the transition from research to clinical care for improved patient health and outcomes. 

The post Machine Learning Could Improve Cardiovascular Disease Screening appeared first on Artificial Intelligence.

March 24, 2020 – Researchers at the University of Massachusetts Amherst (UMass Amherst) have developed a portable surveillance tool that leverages machine learning and real-time data to monitor flu-like illnesses and flu patterns.

The device, called FluSense, can detect coughing sounds and crowd size in real time, and could add to the collection of tools used to forecast seasonal flu and other viral outbreaks. The team recently published the results of their research in the journal Proceedings of the Association for Computing Machinery on Interactive, Mobile, Wearable and Ubiquitous Technologies.

“This may allow us to predict flu trends in a much more accurate manner,” said Tauhidur Rahman, assistant professor of computer and information sciences and co-author of the study.

FluSense is run on an edge-computing platform, and processes information from a low-cost microphone and thermal imaging data. The platform stores no personally identifiable information like speech data or distinguishing images.

The team first developed a lab-based cough model, then trained a deep neural network classifier to draw bounding boxes on thermal images representing people and then to count them. Researchers then placed FluSense devices in four healthcare waiting rooms at UMass’s University Health Services clinic.

The FluSense platform collected and analyzed more than 350,000 thermal images and 21 million non-speech audio samples from public waiting areas between December 2018 and July 2019.

The results showed that the platform was able to accurately predict daily illness rates at the university clinic. Multiple and complementary sets of FluSense signals strongly correlated with lab-based testing for flu-like illnesses and influenza itself.

The researchers believe the tool could add valuable information to current influenza prediction efforts, including the FluSight Network, a group that uses predictive analytics models to forecast trends in influenza outbreaks with greater accuracy than historical baseline models.

“Our main goal was to build predictive models at the population level, not the individual level,” Rahman said.

“I thought if we could capture coughing or sneezing sounds from public spaces where a lot of people naturally congregate, we could utilize this information as a new source of data for predicting epidemiologic trends.”

FluSense creators also noted that the tool could help forecast other respiratory outbreaks, such as the COVID-19 pandemic or SARS.

With the rapid spread of COVID-19 across the US, policymakers have urged experts in AI and data analytics to develop tools that will help track and control the virus. The White House Office of Science and Technology Policy recently issued a call to action for researchers to build AI tools that can be applied to a new COVID-19 dataset.

“Decisive action from America’s science and technology enterprise is critical to prevent, detect, treat, and develop solutions to COVID-19. The White House will continue to be a strong partner in this all hands-on-deck approach,” said Michael Kratsios, US Chief Technology Officer, the White House.

“We thank each institution for voluntarily lending its expertise and innovation to this collaborative effort, and call on the United States research community to put artificial intelligence technologies to work in answering key scientific questions about the novel coronavirus.”

Innovative tools like FluSense, which combines AI and edge computing to enable real-time data analytics, could help accelerate outbreak tracking and understanding. Models like these could directly inform the public during a flu epidemic, and could help determine the timing necessary for flu vaccine campaigns, potential travel restrictions, or the allocation of medical supplies.

“We are trying to bring machine-learning systems to the edge,” said Forsad Al Hossain, PhD student and lead author of the study. “All of the processing happens right here. These systems are becoming cheaper and more powerful.”

The researchers plan to further develop and refine FluSense by testing it in other public areas and geographic locations.

“We have the initial validation that the coughing indeed has a correlation with influenza-related illness,” said Andrew Lover, a vector-borne disease expert and assistant professor in the School of Public Health and Health Sciences “Now we want to validate it beyond this specific hospital setting and show that we can generalize across locations.”

The post Machine Learning Tool Uses Real-Time Data to Monitor Flu Trends appeared first on Artificial Intelligence.

December 11, 2019 – Twenty-two percent of healthcare organizations use a software platform that provides artificial intelligence capability, according to a recent report from HealthLeaders Media.

This is an eight-point increase from 2017, the organization noted, indicating that AI use is steadily rising among health systems.

Thirty-one percent said they plan to have AI capability within the next three years, and 63 percent said their organizations plan to increase their investments in analytics technologies within the next three years.

HealthLeaders surveyed 128 individuals representing different healthcare provider organizations, aiming to measure AI and analytics use across the healthcare ecosystem.

Providers see a wide range of applications for AI, with 81 percent of respondents saying their organizations currently or plan to apply the technology to clinical data, 72 percent to financial data, and 59 percent to patient data.

Organizations also see potential in analytics capabilities. Sixty-three percent of respondents said they plan to increase their investments in analytics, while 35 percent said their investments would stay the same. Just two percent of respondents said their investments would decrease.

Health systems are also leveraging analytics strategies to extract insights from various sources of information. The report found that 78 percent of respondents said they use descriptive analytics for financial data, while 81 percent said they leverage descriptive analytics for their clinical data.

However, fewer participants use predictive capabilities for financial and clinical data analytics. Sixty-four percent said they apply predictive analytics to their financial data and 52 percent reported using predictive capabilities for clinical data.

Analytics investments have led to a strong return on investment for organizations: Forty-one percent describe their organizations’ return on investment on analytics as acceptable, while 30 percent describe analytics ROI as good and 14 percent describe it as very good.

Just 16 percent of respondents describe their analytics ROI as poor or very poor.

When asked about the most significant challenges in performing analytics, most respondents named issues involving human skills and staffing.

Forty-eight percent of participants see the need for timely analysis as the top challenge in performing analytics over the next three years. Forty-six percent said overcoming insufficient analytics skills would be the most challenging, while thirty-seven percent view insufficient funding as their biggest issue.

In addition to revealing staff education and training issues, these barriers also reflect investment challenges, researchers noted.

“Two of the top three tactical challenges are either indirectly or directly related to financial resources,” the report stated.

“For example, the solution to solving the problem of insufficient skills in analytics is investment in training or adding analytics staff, and insufficient funding in light of other priorities needs no explanation.”

These findings mirror statements from a February 2019 Kaufman Hall report, which said that financial executives should expand the scope of their responsibilities and investments in order to keep up with new technologies.

“Given the demands of the changing business environment, healthcare CFOs nationwide should be critically examining the role they and their finance teams play in their organizations. A singular focus on directing or managing financial operations and the related control/monitoring function is not sufficient going forward,” the report concluded.

“Finance executives must be integral to the development, execution, and monitoring of the organization’s vision and strategy, and be armed with the full breadth of data and analytics required for performance management in healthcare.”

Organizations also cited data-related challenges in performing analytics. Half of respondents said integrating internal clinical and financial data is a top challenge, and 46 percent said integrating external clinical and financial data is a major barrier.

The third most-cited challenge was improving EHR interoperability, with 43 percent of respondents naming this as a major barrier to building analytics capabilities.

Looking ahead, 62 percent of respondents said that the most promising area of analytics development would be clinical best practices, while 54 percent cited real-time delivery of actionable information as the most promising area of analytics.

This indicates that most health systems are interested in using analytics technologies to enhance care delivery and outcomes. Thirty-nine percent of participants also named improved quality of care as the primary goal they would expect to achieve through integrating financial and clinical data.

In September 2019, a survey from HIMSS Analytics and Dimensional Insight yielded similar results, showing that the future of the industry will focus on quality rather than quantity.

“As healthcare organizations move to value-based payment models, they are finding that focusing on clinical metrics, including readmission rates, infection control, and patient outcome improvements is critical for success,” George Dealy, vice president of healthcare solutions at Dimensional Insight, said at the time. 

“Analytics provides tremendous insight into these areas and can benefit healthcare organizations that are navigating this transition.”

The post 22% of Orgs Currently Use Artificial Intelligence Software appeared first on Artificial Intelligence.

November 26, 2019 – As the foundation of nearly every healthcare trend, process, and solution, data has a vitally important role to play in care delivery and success.

From risk stratification to chronic disease management, precision medicine and medical research, data is at the center of everyday healthcare tasks and broader industry improvements, making it an incredibly valuable resource for organizations.

“If you talk to any data scientist, they’ll tell you that the more quality, scientifically validated data they have, the more likely they’re going to be able to generate useful trends and insights,” said Todd Frech, CIO at Press Ganey.

“The core of everything we do is taking the vast amounts of data that we collect and creating value for hospitals that are trying to improve their operations.”

With healthcare quickly becoming a digital industry, more and more entities are gathering meaning from this big data using artificial intelligence and other advanced analytics technologies.

“The challenge that we’re trying to overcome is that we have more data than a human can process, and we’re trying to develop insights based on those volumes of data. This issue is a natural fit for AI, so the use of this technology is going to continue to accelerate,” Frech said.

“AI can augment humans’ understanding of data, not only from the perspective of generating new insights, but also in generating those insights faster than a typical human analyst processes.”

There are countless examples of AI outperforming humans in analyzing and extracting insights from clinical data. The technology’s potential to transform the industry has led to concerns about robots encroaching on healthcare jobs, creating an environment run entirely by machines and devoid of human interaction.

While AI may disrupt standard care delivery, it’s unlikely that advanced analytics tools will completely take over the role of clinicians. In a field where high-stakes situations and sensitive data are routine, technology can’t simply be left to operate on its own, Frech stressed.

“AI is going to play a bigger part in healthcare, and humans will also continue to play a big part,” he said.

“We can’t just assume that AI is making the right decisions without human validation. There’s a trend that you’re going to see more – what’s called AI augmentation, or human augmentation with AI, more than what you would call complete robotic AI, meaning that you’re letting the AI make decisions without human intervention.”

Recent research has demonstrated that when implementing AI tools, human intervention can lead to optimal results. A study conducted by a team at NYU School of Medicine and the NYU Center for Data Science showed that combining AI with analysis from human radiologists significantly improved breast cancer detection.

Using an AI augmentation approach could also help organizations analyze and measure unstructured data.

“We collect hundreds of thousands of survey data points in the forms of responses to questions, as well as unstructured data in the form of comments. We use AI to look at the comments that come in our surveys. Those comments are obviously in the form of unstructured text, and they convey information on perception of the providers and of the service,” explained Frech.

“Those aren’t yes or no questions. Those are questions that require some soft skills to interpret. We can use AI to do an initial sentiment analysis, and that provides a way for us to really measure this type of data, which is not as binary as some of the data we typically evaluate.”

However, data-driven technologies can’t improve care if they’re fed inaccurate or incomplete information – in fact, this could have the opposite effect.

“Never underestimate the importance of data quality,” said Frech.  “No AI tool is going to work well without high-quality data. People talk about data lakes and unstructured data, and these things are great tools. But without quality data, you’re going to have more of a data swamp than a data lake.”

“If you’re trying to use AI to gather insights without high-quality data, obviously the results aren’t going to pan out. Or even worse, the results could potentially offer dangerous recommendations that could negatively impact people,” he added.

Having a solid data ecosystem ensures that any innovative tools will contribute positively to a health system’s operations, Frech said, as well as communicating openly with other organizations.

“When implementing artificial intelligence or any new technology, make sure that the foundation is strong. Make sure that there’s testing and validation. If that doesn’t happen, there is potential for organizations to take steps backward rather than forward,” he said.

“Find opportunities with your peers, find case studies, talk to people who are using the technology. The more that your organizations can collaborate and learn from each other, the more ideas and successes will increase.”

AI has massive potential to revolutionize the way providers deliver care and make treatment decisions. The road to industry-wide adoption won’t be without its challenges, but the technology will likely make its way into regular clinical care.

“There are a lot of different ways to use AI, and there has been a lot of experimentation. Over time, there will be more and more successes, and those successes will come in fits and starts, depending on how the data in the market mature. There’s too much investment in AI right now to not have some of those successes come into play,” Frech concluded.

The post Artificial Intelligence Success Requires Human Validation, Good Data appeared first on Artificial Intelligence.