AI News, How does machine learning work?

How does machine learning work?

Here’s an article containing a great example of how AI works when it’s applied to an individual industry: How AI is Smoothing the Road to Value-Based Care The road to value-based care is long and winding.

This is a monumental shift from traditional delivery models, which reimburse providers based on the amount of healthcare services they deliver.

Value-based care will mend a broken system Traditional reimbursement models paid physicians for every test, treatment, and service they provided.

In 2015, CMS introduced an effort to transition to a system that rewards value of care instead of volume of services.

The shift to value-based care has three key goals: Today’s healthcare challenges demand advanced technological capabilities Providing high value care is also critical for handling rising patient volumes.

AI will empower your clinicians and patients at every touchpoint Forward-looking healthcare leaders have already found ways to apply AI in the healthcare setting.

Advanced data analytics will support clinical decision making and save lives Hospitals are already collecting massive volumes of information.

Advanced data analytics within AI systems can support clinical decision making and reduce physicians’ cognitive burden.

AI will boost operational efficiency by taking over routine clinical activities AI can improve operational efficiency by assuming time-intensive responsibilities.

According to a study published in the Annals of Internal Medicine, ambulatory physicians spend 50% of their work day entering data into EMRs, and just 27% of their day interacting with patients.

Flagler Hospital in Saint Augustine, Florida, is using artificial intelligence tools to improve the treatment of pneumonia, sepsis and a dozen other high-cost, high-mortality conditions.

Usually, it’s large academic medical centers or wide-ranging health systems, not community hospitals, that so aggressively use AI in attempts to improve care and trim costs.

The AI tools automatically revealed new, improved care pathways for pneumonia and sepsis after analyzing thousands of patient records from the hospital and identifying the commonalities for those with the best outcomes.

It expects to save $1,356.35 per pneumonia patient in direct variable costs (35 percent savings) versus the status quo, while reducing length of stay by two days.

to develop new care pathways, from the original plan of tackling 12 conditions over three years to now tackling one condition per month.

Ayasdi uses a branch of mathematics called topological data analysis to group patients treated similarly and relationships between those groups, explained Michael Sanders, MD, chief medical information officer at Flagler Hospital.

“These events include all medications, diagnostic tests, vital signs, IVs, procedures and meals, and the ideal timing for the occurrence of each so as to replicate the results of this group.”

Flagler extracts the data the AI tools use from its Allscripts EHR, from its CPM analytics platform, from its enterprise data warehouse, and from its financial system through the use of 2,300 lines of SQL code.

“While this process could be replicated in a manual or semi-manual environment, it would have taken years of work to even come close to revealing part of this knowledge,”

As mentioned earlier, by implementing the new pneumonia pathway by changing the order set in its EHR, Flagler expects to save $1,356.35 per pneumonia patient in direct variable costs versus the status quo, while reducing the length of stay by two days.

For example, the Goldilocks group showed us that the faster we started a pneumonia patient who also had COPD on nebulizer treatments, the shorter the stay, the lower the cost and the lower the readmission rate –

Products like the AI tools Flagler uses show caregivers relationships that the caregivers might not otherwise find and answer questions they did not know to ask, Sanders concluded.

London hospital replacing doctors with AI to improve patient care

One of London’s top NHS hospitals, University College London Hospital (UCLH), has partnered with the UK’s national organisation for data science, the Alan Turing Institute, to use artificial intelligence to carry out tasks that are usually performed by nurses and doctors.

With A&E waits regularly exceeding four hours across the country, UCLH is not alone in finding that this department is a pressure point for hospital staff, and a trigger for wider resourcing problems.

“But what if, through analysis of thousands of similar scenarios, we were able to identify patterns in the initial presentation of the 20 percent with serious conditions, such as intestinal perforation or severe infections?

Researchers will apply AI and machine learning techniques to existing large data sets to ascertain where bottlenecks are forming, to help patients get seen faster and more effectively.

The partners are also looking at deploying machine learning techniques across hospital appointment data to help staff understand which patients may attend or miss outpatient neurology clinics or MRI scans.

The technology could also help staff examine the CT scans of 25,000 former smokers as part of an ongoing research project, and automate cervical smear tests.

The aim is to reduce deaths from prostate, ovarian, lung, and bowel cancer by 10 percent within 15 years – saving an estimated 22,000 lives a year.

Meanwhile, the Royal Liverpool and Broadgreen University Hospitals NHS Trust announced that it has embarked on a new AI programme to improve the treatment of patients who have had a heart attack, in a project that could see wider use of AI to inform treatment decisions across the organisation.

Dr Eric Topol, executive VP of private US healthcare research group, Scripps Research Institute, is leading the review, looking at opportunities to train existing staff, while also considering the impact that AI, robotics, genomics, and big data analysis may have on skills.

Healthcare with heart

Medical science continues to progress, allowing doctors to push the boundaries and always achieve more.

One such example is the implantation of heart valves via the groin (percutaneous valve replacement /TAVI) – a procedure which has reached full swing in recent years due to it shorter recovery period and less invasive nature.

When Dr Dujardin and his team wanted to know the average age of their patients or the rate of successful interventions, for example, they had to manually enter information in Excel from files, by hand.

Now, his team uses Lynxcare’s intelligent medical software, allowing users to consult the statistics of all past operations, including mortality rate, average age and the state of patients before and after their procedures.

All of this information is stored in a database that is updated in real time, and the system is based on the criteria of a major Dutch study on valve replacement operations, so that data from the Delta General Hospital can be compared to statistics from Dutch cardiology centres.

The team has particular expertise in the treating poor heart valves, replacing them via a groin catheter – or as Dr Dujardin puts it, “The old failing valve is pushed back by the new.” The system itself is able to process information and documents from patients who have received a new aortic valve in the past seven years.

“Ultimately, the question is whether patients with an average operative risk would have a better chance of survival with aortic valve replacement via the groin.

In addition, there are elderly people who are generally still suffering from other ailments, but who in many cases may, after such an operation, continue to live for a certain number of years in good conditions.

“Because the cost of an operation is at the same time high, it is particularly important to make a realistic assessment of the situation based on reliable and up-to-date practical data.

We are no longer relying solely on lessons learned from scientific studies, but we can now base our decisions on deep, well-thought-out real-time data.

Artificial Intelligence in Healthcare – It’s about Time | Casey Bennett | TEDxNashville

We need tools that can help us – both clinicians and patients – make better healthcare decisions. Yet in order to do so, those tools need to “think like we do” ...

Pieces Technologies | Clinical AI for the entire patient journey

Pieces Technologies improves patient outcomes across the full spectrum of care, from hospital treatment to ongoing community services and resources.

How is AI empowering healthcare today?

AI and intelligent systems is a gamechanger for health. Meet three Swedish companies leading the way to improved preventive care and a healthier every day ...

What healthcare will look like in 2020 | Stephen Klasko | TEDxPhiladelphia

This talk was given at a local TEDx event, produced independently of the TED Conferences. How will healthcare change in the future? Dr. Stephen Klasko ...

Quality Improvement in Nursing at Saratoga Hospital | A Philips Customer Story

To see quality improvement in nursing care at Saratoga Hospital, clinicians use Philips IntelliVue Guardian everyday. Learn more at ...

Artificially Intelligent Healthcare - Dr. Baber Ghauri, Salus Health Physician Services

This talk was recorded at H2O World 2018 NYC on June 7th, 2018. The slides from the talk can be viewed here: ...

AI in Medicine | Drug Discovery with GANs (TensorFlow Tutorial)

How do we use AI to cure drug discovery? This is apart of my AI for business series right here on Youtube. Subscribe to stay up to date! In this video I'm going to ...

Bringing AI and machine learning innovations to healthcare (Google I/O '18)

Could machine learning give new insights into diseases, widen access to healthcare, and even lead to new scientific discoveries? Already we can see how ...

AI-powered virtual assistants for care teams

Designed for all clinical workflows and medical specialties, Nuance's virtual assistant solution enhances interactions between clinicians and patients, improving ...

Better Medicine Through Machine Learning | Suchi Saria | TEDxBoston

Faster medical treatment saves lives. Machine Learning is already saving lives, by scouring a multitude of patients' data and comparing them to one patient's ...