Questions? Feedback? powered by Olark live chat software healthcare Archives - eMedics

Welcome to eMEDICS! your IT partner for Patient Management

Opening Hours : Monday to Friday - 9am to 5pm
  Contact : +44 74 58 03 89 49

All Posts Tagged: healthcare

Machine Learning – MIT professor’s quick primer on 2 types

By Mike Miliard

Machine learning – There are two main approaches – supervised and unsupervised – and each has specific applications in the context of healthcare.

And even though machine learning tools impact has not yet sent shockwaves through the industry, the potential of each is enormous, according to John Guttag, head of the Data Driven Inference Group at MIT’s Computer Science and Artificial Intelligence Laboratory.

At its basic level, machine learning involves looking at data, and from that data finding information that is not readily visible. Example: Applying machine learning to data about patients infected with Zika or another virus and using what we can learn about what happens to those people to inform care decisions regarding the best ways to treat people who get infected in the future.

“Typically we use machine learning to build inference tools, where we find patterns in existing data that allow us – when presented with new data – to infer something interesting about that data,” said Guttag. “Machine learning is driven entirely by the data, rather than by, say, human intuition.”

Here’s a look at the two main types of machine learning and why they matter to healthcare.

Supervised machine learning
“In supervised machine learning, we’re given the data and some outcome associated with the data,” Guttag explained. “We’re given all the people who have Zika infections and then we know which of the women have children with birth defects and which don’t. And maybe from that we could build a model saying that if the woman is pregnant and has Zika, what’s the probability that her baby has a birth defect. And it might be different for 30 year old women than for 40 year old women. Who knows what the factors would be. But there we have a label – all sorts of details about the woman, and was the baby healthy or not. So that would be supervised learning: We have a label about the outcome of interest.”

Unsupervised machine learning
Unsupervised learning, on the other hand “means we wouldn’t have a label,” he said. “We just get data, and from that data we try to infer some hidden structure in the data. So for example you get a bunch of healthcare data and you find patients who look ‘similar.’ Typically the nice thing about unsupervised learning is you find things you weren’t even looking for. It’s also useful for when, for one reason or another, the data is impossible to label.”

The case for using emerging tech today
Guttag added that machine learning is among the fastest growing parts of computer science right now in the world. As healthcare entities continually ramp up their analytics and big data efforts and gird for precision medicine and population health, machine learning as well as artificial intelligence and cognitive computing are poised to become even more valuable.

While vendors such as IBM Watson, Google, Microsoft, and other tech giants are bringing new technologies to market, most of the progress made in machine learning is happening in financial services, retail and other industries, and has been for about a decade.

Healthcare, true to its reputation for slowly embracing new technologies, is a bit late to the party.

One of the challenges unique to healthcare is the long gap between when new knowledge is obtained and when clinicians and doctors can put it to use treating patients, which is among the reasons Guttag urged major healthcare providers to more aggressively integrate today’s machine learning tools into their workflows now.

“People should be using today’s technology to do things today,” Guttag said. “Machine learning is a huge deal. And we’re going to see some pretty dramatic changes over the next few years.”

Read More
wireless sensors

Sensors, one of top 10 healthcare technology for 2016

Wireless sensors and Mobile stroke units among key advances that will transform industry.

Wireless sensors will transform the Healthcare industry and eMEDICS.org is part of this transformation. We found an interesting article regarding this hot topic, written by Jessica Davis on January 07, 2016, Twitter: @JessiefDavis

The Affordable Care Act’s new payment models have hospital leaders searching for effective ways to reduce costs, while increasing care quality. As the 2016 technology market will be inundated with innovations, ECRI Institute has released its annual list of the top technologies, many pointing the way toward value-based care.

“Hospital leaders have to deal with a lot of new technology issues – and demands from different departments in their facilities,” said Robert P. Maliff, director of ECRI’s applied solutions group, in a press statement. The list is meant to assist leaders attempting to update and implement new technology.

ECRI takes an “evidence-based” approach in their assessments of healthcare innovations over the course of the year, officials say.

“We present hospital leaders with unbiased guidance to support informed decision making and help them understand how new innovations will affect care delivery,” said Diane C. Robertson, ECRI’s director of health technology assessment, in a statement. The topics and trends  it expects will most affect healthcare over the next year:

1. Mobile stroke units. MSUs use specially-outfitted ambulances and staff members, in conjunction with telemedicine to perform blood tests, CT scans and TPA tests before the patient arrives at the hospital.

2. Medical device cybersecurity. Most healthcare IT leaders integrate stringent security features for network infrastructures and EHRs – but not for their mobile devices. As many devices are attached to patients’ EHRs, C-suite members must perform threat assessments and know the devices and software connected to crucial patient data.

3. Wireless wearable sensors. As an increasing number of consumers turn to wellness apps, devices and wearable sensors, healthcare officials must learn how to utilize this data to reduce hospital stays and readmissions for those with serious and chronic conditions.

4. Miniature leadless pacemakers. Next-generation pacemakers are 10 percent of the size of conventional pacemakers and are designed for only one heart chamber. It’s more effective than traditional models, but only ideal for 15 percent pacemaker patients.

5. Blue-violet LED light fixtures. These lights provide continuous environmental disinfection technology to kill harmful healthcare-related bacteria – a major cause of morbidity, mortality and increased healthcare costs in the U.S.

6. New high-cost cardiovascular drugs. Three newly-approved homecare cardiovascular drugs are expensive compared to standard-of-care medications, but short-term data has lauded efficacy.

7. Changing landscape of robotic surgery. The robotic surgery landscape is rapidly changing; vendor competition is set to explode in early 2016 with a switch from mainframe to tablet-type programs.

8. Spectral computed tomography. Spectral computed tomography will reenter the health tech conversation due to new tools and increased marketing. The tool builds on traditional CT scans by adding depth to the physiologic function of soft tissue with a dual-layer detector.

9. Injected bioabsorbable hydrogel (SpaceOAR). Approved for prostate cancer patients, SpaceOAR is designed to protect tissue and healthy organs from radiation treatment. Currently there is limited reimbursement for this product’s use, but studies have shown the barrier to be highly effective.

10. Warm donor organ perfusion systems. New technology provides warm perfusion of lungs and hearts to eliminate the issue that two-thirds of organs are never used by hospitals, as viability deteriorates harvesting, preserving and transporting.

Read More
hospital predictions

Healthcare predictions – IDC releases top 10

HealthCare IT News and top 10 predictions, Nov 2015

There has never been a more exciting time to be in healthcare IT and its predictions. There has never been a more pivotal and stressful time to be in healthcare IT. IDC’s latest healthcare IT predictions illustrate this and could not ring more true. U.S. healthcare spending as a percentage of GDP is almost double that of any other nation putting continued legislative focus on reforming the system and IT is truly in the driver’s seat.

These predictions highlight the multitude of transformational innovations that will help us get to much needed efficiencies through proactive personalized care, intelligence driven protocols, machine to machine learning and scaling to deliver care outside provider settings.

IDC FutureScape: Worldwide Healthcare 2016 Predictions

1.      Downward pressure of the healthcare economy will increase risk based contracting to 50% of provider payments by 2017 resulting in premium increases in the 2% to 3% range.

2.      By 2018 industry cloud creation will be the top market entry strategy for tech providers and industrial companies, as leaders of IT and industry domain unite to tear down traditional barriers to entry.

3.      By 2018 physicians will use cognitive solutions to identify the most effective treatment for 50% of complex cancer patients resulting in a 10% reduction in mortality and 10% in cost.

4.      By 2017, surgeons will use computer assisted or robotic surgery techniques to assist in planning, simulating and performing 50% of the most complex surgeries.

5.      One out of the three individuals will have their healthcare records compromised by cyberattacks in 2016.

6.      By 2018, due to more frequent drug launches, pharma adoption of global launch sequence optimization solutions will grow by 50%, saving the industry billions in potential lost revenue.

7.      By 2018, 80% of customer/patient service interaction will make use of IoT and bid data to improve quality, value and timeliness. Virtual care will become routine by 2018.

8.      By 2018, 30% of WW healthcare systems will employ real time cognitive analysis to provide personalized care leveraging patient’s clinical data, directly supported by clinical outcomes and RWE data.

9.      Reluctantly, through 2017 healthcare IT services buyers will consolidate IT services spending in the hands of the 5-10 largest service providers for each sub-vertical at double industry growth rates.

10.    2016 will see 3rd platform acute care HIS and EHR begin to come to market and early adopters will get started on digital transformation in 2017 – 2019.

Healthcare is beginning to harness and integrate previously untapped intelligence. There will soon be a tsunami of medical innovation driven by distilling intelligence from mass digitized PHI and the pressure for providers to deliver, and get paid on, quality outcomes. Improving patient care and creating better quality of life is what it is all about and for IT to be such an integral part of this evolution is what makes it such and exciting, albeit stressful, time to be in healthcare IT.

Read More

Health Sense: Group tries to reduce hospital readmissions

Group tries to reduce hospital readmissions

MADISON.com: Under the Affordable Care Act, Medicare penalizes hospitals that have too many readmissions, or admissions within 30 days of discharges, for patients with pneumonia, heart attack and heart failure.

But hospitals aren’t the only places that influence whether patients return. Nursing homes, home health agencies, home care agencies, aging agencies, hospices, pharmacies, ambulance services and others have an impact.

That’s a key motivation for the Dane County Community Transitions Coalition. Started in 2012, the group includes representatives from about 30 facilities or agencies that care for the elderly or chronically ill. The coalition meets monthly in an effort to improve transitions of care and keep readmissions down.

“We’re sending these people home and often they’re falling off the radar,” said Maria Brenny-Fitzpatrick, transitional care program director at UW Health and a co-leader of the coalition.

Preventing patients from returning to the hospital isn’t only about avoiding Medicare penalties. It’s also better for patients, Brenny-Fitzpatrick said. “Readmissions, on the patients, are very traumatic and very difficult,” she said.

One tool the coalition developed is an emergency medical information form that patients or loved ones can keep at home and give to paramedics and emergency room staff when needed.

The form includes major diagnoses, a list of medications and contact information for a care coordinator. It says whether the patient needs glasses or hearing aids to communicate or a cane or walker to walk.

Another information sheet, explaining supportive home care services, was developed by six agencies that provide such care in the county: BrightStar, ComForcare, Comfort Keepers, Home Instead, Midwest Home Care and Senior Helpers.

Other handouts focus on heart failure, when the heart doesn’t pump enough blood. One includes warning signs that should prompt patients to call a doctor or nurse, such as trouble sleeping or shortness of breath with regular activity. The handout also includes “red zone” symptoms requiring a 911 call, such as chest pain or a fainting spell.

In a related effort, Safe Communities of Dane County and the Wisconsin Institute for Healthy Aging plan to offer a Living Well workshop next spring focusing on heart failure.

Living Well workshops “build participants’ confidence in their ability to manage their health condition to maintain active and fulfilling lives,” according to the institute’s website. For more information about the workshops, contact Lynne Robertson, Safe Communities’ outreach specialist, at 608-836-9810 or lynnerob@charter.net.

Dane County’s readmission rate, of about 37 per 1,000 Medicare beneficiaries, hasn’t changed much in recent years. It’s lower than the state and national averages but higher than two-thirds of counties in Wisconsin.

Alzheimer’s research

I wrote an article in November about a study at UW Hospital of whether an experimental drug can protect healthy seniors whose brain scans show signs of risk for Alzheimer’s disease.

Now UW Hospital is part of a different study to see if another drug might slow the progression of the disease in people with mild to moderate Alzheimer’s. Patients who are ages 55 to 85 and have been taking the drug Aricept for at least six months might be eligible.

Read More
October 10, 2015 / Posted by / Health Sense: Group tries to reduce hospital readmissions