To reduce data-cleaning mistakes, ActiveClean takes humans out of the two most error-prone steps of data cleaning: finding dirty data and updating the model.
More >>
Shared by Prathitha Biju
|10
93 3 |about 2 years ago
|
Although pioneer health care organizations jumped into risk sharing and fee-for-value without a good grounding in data, they have come to recognize the critical role analytics play over the past few years. Results of a 2015 survey of ACOs show that, “Nearly 85 percent of respondents report they have in place advanced analytics software to analyze disparate data sets.” The data tends to be limited (mostly claims and EHR data) and data sharing is still rare between organizations, but basic practices such as identifying high-risk patients are becoming more widely seen.
Philips has been in health care informatics for a long time, gradually building a data platform with analytics capabilities and basing more and more services on this platform. I talked to Dr. ck Andrade, Director of Product Management of Philips’ HealthSuite Digital Platform, to find how their basic analytics drive their services.
Like the ACOs mentioned earlier, Philips allows a single organization to combine and mine data of different types. Philips does not combine data from different unrelated organizations–in fact, to respect privacy, they don’t peek at user data at all. The platform is intended to aid institutions with precisely the types of data integration that are now so difficult. Now it is being incorporated by Philips into their own high-level services, showing how analytics can be a platform for building businesses.
Philips’s HealthSuite digital platform offers FHIR APIs. EHR data is read in through the vendors’ APIs when they’re available, by using the platform’s other interoperability capabilities, or through the CCD-A format. Imaging support was announced on February 18. Genomics is being pursued. Finally, device data can be taken in through several sources. Philips Device Cloud manages 8 million connected devices today, and a recently announced integration with Validic connects to data from 130 different device vendors over a wide range of protocols.
Clearly, all these data sets are interdependent. For instance, an image is of no value without the patient history that comes from an EHR.
More >>
Shared by Radhika Narayanan
|0
103 2 |about 3 years ago
|
There is little in Ruby’s life that is easy. Nearly blind and unable to walk more than a step or two, the 39-year-old struggles to raise three sons while dealing with a daunting array of health conditions, from diabetes that recently landed her in the hospital to pain from bulging spinal disks.
Without support, odds are she’ll end up back in a hospital. But Ruby, who asked that her last name not be used to protect her family’s privacy, is part of a growing effort to reduce those odds by arming home care aides and other non-medical workers with the power of data.
More >>
Shared by Radhika Narayanan
|11
91 1 |about 3 years ago
|
It’s one thing to understand the principles of big data analytics, but it’s another to ensure projects are successful.
As an early adopter of advanced and predictive data analytics, Hotels.com has gained in-depth knowledge on providing consumers with a personalised user experience and custom-made recommendations.
Drawing on data from clickstreams, reviews, personal preferences, and hotel profiles, we are able to build algorithms behind the booking procedure that understand the customer journey beyond just one session.
More >>
Shared by Radhika Narayanan
|18
25 54 |about 3 years ago
|
The demands of todays value-based payment arrangements rely on continuous improvement and that requires up-to-the-minute evidence-based recommendations
More >>
Shared by Radhika Narayanan
|8
80 6 |about 2 years ago
|
Health orgs trekking deeper into analytics should expect a new information wave, understand that crowdsourcing can pay off, know machine learning is real right now, buckle down on governance. And don’t hold out for perfection.
More >>
Shared by Radhika Narayanan
|19
69 3 |about 2 years ago
|
Google is using your health data to make Google Fit better -- and thats only going to continue as the app becomes your personal assistant
More >>
Shared by Radhika Narayanan
|32
57 2 |about 2 years ago
|
The biggest hindrance to progress is that tools like artificial intelligence, cognitive computing and machine learning conjure images of sci-fi movies rather than real-world uses. Here’s what one Harvard Medical School expert said needs to happen next.
More >>
Shared by Radhika Narayanan
|18
70 1 |about 2 years ago
|
Throughout 2016 the message from cybersecurity experts has been fairly consistent and increasingly urgentleaders at patient care organizations need to prioritize IT security And at the risk of sounding like a broken record a recent year-in-review report on health data breaches makes one thing quite clearhealthcare leaders are still not doing enough to protect patient dataAccording to a new Breach Barometer report from Baltimore-based healthcare cybersecurity vendor Protenus and in collaboration with DataBreachesnet the healthcare industry was plagued by breaches involving patient or health data in 2016 with hacking and ransomware incidents reminding us how vulnerable protected health information (PHI) remainsAccording to an analysis by Protenus and DataBreachesnet there were 450 data breach incidents either reported to the US Department of Health and Human Services (HSS) or disclosed in the media in 2016 thats more than one health data breach per day for the entire year and these breaches resulted in 27 million affected patient records If these trends continue 2017 can expect to see a continued average of at least one breach disclosed per dayA Healthcare Informatics news article about the Protenus report briefly highlights the key findings yet the report findings about insider wrongdoing caught my attention Many data security experts have pointed out that employees are the weakest link in the cybersecurity fence and with this in mind its important to review these data breach incidents with an eye toward lessons learned and to find a way forward for protecting patient privacyProtenus reported that 43 percent of the 2016 health data breaches (192 incidents) were a result of insiders and for the 162 incidents out of those 192 that Protenus has data for 2 million patient records were affected Now while hacking accounted for the majority of patient records breached in 2016 insider incidents resulted in a larger number of breach incidents (120 vs 192 respectively)According to the Protenus report the average number of breached patient records due to insider error was more than three times the number attributed to insiders with malicious intent However the report also noted that this figure was distorted by two large insider error incidents in August and December which when removed shows the two categories to have roughly similar averagesWhile it is reassuring that not all insider breaches are with ill-intent healthcare organizations need to make employee training frequent reminders and re-training a priority the report authors wroteOne key reason why I think the insider incidents should be highlighted is that there is mounting evidence that that problem of insider data breaches has largely gone unaddressed as healthcare organizations focus on catching up with the external threats Additionally insider breaches tend to fly under the radar and can go undetected for quite some time To this point the report authors noted that in one incident hospital employees were potentially inappropriately accessing patients medical information for years without being detected because the hospital didnt have technology in place to monitor or protect patient privacy The hospital found potentially inappropriate accesses to the medical records beginning no later than 2013 and possibly much earlierWithout technology in place to provide alerts when access to a medical record is inappropriate the organization now has to notify every single patient theyve encountered since 2013 which will probably end up being a very costly process the report authors wroteThe Protenus report findings also indicate that it took an average of 233 days for a healthcare organization to discover they had a health data breach Perhaps most troubling is that the time to discovery specifically in cases of insider wrongdoing was more than double that607 days It goes without saying that it is critical for healthcare organizations to have a more proactive approach to monitoring patient data as the sooner a breach is detected the quicker organizations can mitigate the risk of significant damage being done with their patients dataWhile limited budgets and resources are likely to blame for some organizations data breach detection capabilities the report authors also surmise that organizations are still taking a reactive rather than proactive approach to privacy monitoring and this can allow inappropriate access to the patient data to go unnoticed for extended periods of timeIn a recent interview Mac McMillan CEO of the Austin Tex-based CynergisTek consulting firm had a similar view of healthcare data security I think there are some folks who are beginning to be a bit more proactive but for the most part were still a very reactive industry he saidRegarding insider data breaches specifically McMillan said They are going to continue to be a problem until we realize as an industry that we need to move to behavioral modeling and behavioral analysis to stop the threat This is one of those situations where the methods we are using are antiquated Were typically monitoring users today based on rules so in other words somebody goes outside their prescribed boundary in terms of what they are doing or some known convention in the system in terms of their profile The problem is that most insiders that are perpetuating harm they know what those rules are and so they are careful not to cross those boundaries And if youre not actually looking at behavior youre not going to catch that
More >>
Shared by Radhika Narayanan
|14
66 6 |about 2 years ago
|
The healthcare industry amasses a tremendous amount of clinical data from which it gets far less value than it should. One issue is the lack of consistent, or perhaps I should say persistent, data stewardship with many errors and omissions negatively impacting clinicians. A second issue is a failure to put clinical data to work in meaningful ways, including the identification of trends and patterns (your most at-risk patients), or — at a much higher system level — reducing network leakage and creating effective measurement initiatives. Addressing these issues will be essential to achieving meaningful progress toward healthcare industry goals — and it’s really not as difficult as it seems.
More >>
Shared by Radhika Narayanan
|0
84 1 |about 3 years ago
|
A Fresno California medical center is rolling out some new-age technology to identify patients as they come in the door and prevent medical record confusion Community Regional Medical Center in Fresno is using eye-scanning technology to add each patients eyeprint to their medical record and help limit the number of manual corrections staff need to make to patient records
More >>
Shared by Radhika Narayanan
|9
73 0 |about 2 years ago
|
What impact will the transition to a Donald Trump administration have on HIPAA enforcement and other healthcare privacy and security regulatory activity? Experts
More >>
Shared by Prathitha Biju
|7
74 0 |about 2 years ago
|
PHILADELPHIA, Aug. 15, 2017 PRNewswire-USNewswire -- The Center for Data Driven Discovery in Biomedicine at Children's Hospital of Philadelphia (CHOP) will lead a new, collaborative effort funded by the National Institutes of Health Common Fund to discover the causes of pediatric cancer and structural birth defects through the use of big data. The Center will be known as the "Kids First Pediatric Data Resource Center" (DRC).
More >>
Shared by Radhika Narayanan
|0
80 0 |about 2 years ago
|
Apple updated its privacy website with the tool, which was unveiled earlier this year for users in the European Union in response to the regions General Data Protection Regulation, or GDPR. Apple will now let users in the United States, Canada, Australia and New Zealand see and download all information that Apple has collected on them. It also gives users a simpler way to make changes to the data, suspend their Apple account or even permanently delete it.
More >>
Shared by Radhika Narayanan
|79
0 0 |about 4 months ago
|
Dell survey finds connecting to public Wi-Fi to access confidential information using personal email for work and widespread use of public cloud services also pose risks to health information
More >>
Shared by Radhika Narayanan
|15
59 3 |about 2 years ago
|
Editor's Note: Buff Colchagoff is the CEO of RosettaHealth, a cloud-based health messaging and exchange platform. Colchagoff has over 16 years of Health IT experience with large projects, including building the VA's PHR MyHealtheVet, as operations manager for the Nationwide Health Information Exchange (NwHIN) which grew into the Sequoia Project, the Direct Project. Follow him on Twitter at @BuffColchagoff
You're the leader of a digital health startup born in 2015, ready, willing, and eager to revolutionize the healthcare industry with your groundbreaking products and/or services. But, fast-forward two short, yet, painful years later, and you find yourself contemplating the meaning of life from your corporate deathbed.
Even as funding has accelerated for digital health startups, a 2015 report from Accenture forecast that half of digital health startups are likely to fail within two years of launch.
So, as your colleagues gather around the office to pay their final respects, you can't help but reflect on your prognosis, and think about how you arrived at this very point in time. What went wrong?
The leading cause of death among digital health startups is a debilitating, disturbing disease known as data More >>
Shared by Radhika Narayanan
|14
51 11 |about 2 years ago
|
In many ways, fighting cybercrime is a lot like playing “Whack-A-Mole,” the ever popular arcade game. For every threat that is discovered and dealt with, a new one
More >>
Shared by Radhika Narayanan
|16
47 5 |about 2 years ago
|
Two years ago, the American Society of Clinical Oncology (ASCO) announced the launch of an initiative to build a big data platform, called CancerLinQ, as a database that provides oncologists with growing amounts of real-world cancer information. The CancerLinQ platform was designed to connect and analyze cancer data from electronic records to provide data to cancer providers in order to assist them with making more informed decisions about patient care. The CancerLinQ platform was co-developed with SAP utilizing the SAP Connected Health platform that runs on SAP HANA, a flexible, in-memory data management and application platform.
More >>
Shared by Radhika Narayanan
|26
40 0 |about 2 years ago
|
Healthcare has entered an era of major data transformation spurred by the use of advanced analytics and Big Data technologies The catalyst for this transformation includes both the move toward evidence-based medicine and value-based payments
More >>
Shared by Radhika Narayanan
|12
54 0 |about 2 years ago
|
The new platform leverages Oracle and Hadoop technologies to enable users to run analytics against large research data sets.
Designed to reduce the time researchers spend analyzing vast amounts of genomic and phenotypic data, the PHEMI Central Precision Medicine Edition leverages Oracle and Hadoop technologies.
Oracle Big Data Appliance and is built on Hadoop Big Data technology for scalability and ultra-fast query capabilities.
Running on the Oracle Big Data Appliance, in fact, enables PHEMI’s tool to ingest, index, annotate and search large amounts of genomic data and achieve sub-second query performance, Vancouver- based PHEMI said.
More >>
Shared by Radhika Narayanan
|16
47 0 |about 2 years ago
|