Comcast to enforce 1.2TB data cap in entire 39-state territory in early 2021 | Ars Technica

2021 will see increased fees for heavy users of Comcast broadband. Comcast already has data caps in 38 states and is extending it to all i's regions beginning in January 2021. 

Comcast's 1.2TB monthly data cap is coming to 12 more states and the District of Columbia starting January 2021. The unpopular policy was already enforced in most of Comcast's 39-state US territory over the past few years, and the upcoming expansion will for the first time bring the cap to every market in Comcast's territory.

Comcast recognized the law of supply and demand as COVID 19 expanded in 2020. COVID19 pandemic is a global phenomenon impacting the entire world.  The internet is a truly global enterprise connecting far-flung businesses and people.  Several events conspired to cause an exponential increase in information flow.

1. Social distancing and limits on group size eliminated in-person meetings

2..Remote work and remote learning are facilitated by the internet.

3. Health information technology places additional demands on messaging, telehealth, and especially video conferencing which requires high data flow.

Until 2010 health information technology was a laggard in information technology adoption. Federal incentives stimulated an explosion of interest in electronic health records and information exchange.

Broadband power users, defined as subscribers who use 1 TB per month or more, are growing dramatically, according to the latest OVBI report from OpenVault. Broadband users are also adopting faster speeds, according to OpenVault data.

The firm’s third-quarter OpenVault Broadband Insights (OVBI) report said that three important year-over-year performance indices illustrated the trend. There was a 110% increase in power users who use 1 TB or more of data (to 8.8% overall), a 172% increase in extreme power users consuming 2 TB or more of data (to 1% overall), and an increase of 124% in gigabit subscribers (to 5.6% overall). 

Power users

Comcast reports that only about 5% of current customers exceed 1.2 TB per month. But that percentage is most likely on the rise. Recent data from OpenVault reports surging growth in power users, who are defined as subscribers who exceed 1 TB of usage per month.

As of November 12,2020, 50% of broadband users use 250GB/month, 10% use 1TB or more already.

The increase of expense for broadband will be offset by decreases in transportation expenses, the lower overhead for office space, and other secondary gains from remote work.

Comcast to enforce 1.2TB data cap in entire 39-state territory in early 2021 | Ars Technica

Artificial Intelligence for the Health Community: Don't leave Home without It

Today all physicians need to know about artificial intelligence, such as deep learning, machine learning, image processing and analytics.  Few health providers know much about artificial intelligence, and for clinicians there is little need to know the details, other than to select a ready made solution out of the box, downloadable from the interweb.  A.I. is developing rapidly and is undergoing rapid adoption by hospitals, clinics and some providers.

IBM Watson and MD Anderson Cancer entered into a joint venture for treatment of cancers.  The effort failed because neither partner quite knew what AI was not capable of accomplishing at this early iteration.  There is a learning curve that takes substantial time.  The algorithms must be written and then instructed with experience.  Each step adds to the database making the application smarter. 

This edition of Digital Health Space will attempt to guide the  learner in acquiring some skills in using artificial intelligence, and to take a look 'under the hood'.  Few practitioners will have time or resources to learn programming and/or machine learning.  

Despite what you may hear AI is not for the average provider. It has become a buzzword, and using the word loosely announces true ignorance of the tool. 

Anyone serious about AI should start with a skill set in programming, systems and computer languages. If you are interested in medicine acquiring this skill in undergraduate and/or graduate education will bring a powerful tool to medical practice, and research.  

A.I. is being applied in genomics, proteomics, cardiology, imaging, neural networks and about every basic science or clinical specialty.  Natural language processing as demonstrated in Siri, Alexa and Nuance is one example of artificial intelligence

One must have a clear vision of what you want to accomplish.  It will nor replace physicians. It may increase efficiency, decrease errors, and allow for more cost effective medicine.  It has application for health insurance, health policy, epidemiology, and predictive analytics.  It may be the alphabet soup of intelligence. 

The accompanying information allows the reader to review educational courses and determine what would be appropriate for their need.

Every decade or so there is a technological tsunami that transforms multiple industries.

Artificial Intelligence (AI) is that wave sweeping the technology world today. If you want to join this revolution but do not have the skills yet, this series of courses are right for you.

OpenCV.org supports the largest computer vision library in the world. We are on a mission to create the most comprehensive online courses in AI to educate a global workforce.

These courses are designed for Working Professionals and Students alike. The only prerequisite for taking these courses is a basic understanding of Python or C++.

The courses require 3-4 months to complete if you commit 5-8hrs/week for learning.

Courses and Bundles

Download Syllabus

About this Course

What Is Machine Learning - A Complete Beginner's Guide

Certification is available for the course(s)

What Is The Difference Between Artificial Intelligence And Machine Learning?

Artificial Intelligence And Machine Learning In Healthcare

(20) AI courses by OpenCV

Effect of a Machine Learning–Derived Early Warning System for Intraoperative Hypotension vs Standard Care : Are we ready ?

Artificial intelligence, machine learning, and deep learning are topics being bandied about in clinical medicine.  We are aware of some early failures of studies in oncology by M.D. Anderson and IBMs Watson AI system. After working with Watson the Oncology Group at M.D. Anderson Clinic abandoned its use. Many of the reasons were due to logistics for using the "Oncology Expert" IBM model.  IBM maintains the program was successful.

4 reasons MD Anderson put IBM Watson on hold

Here are four things to know about why the project was put on hold.

1. One of the main challenges the audit cites is that the Oncology Expert Advisor's focus changed multiple times. The initial project focused on leukemia; however, it later shifted to lung cancer. Rob Merkel, general manager for oncology and genomics at IBM Watson Health, told the Wall Street Journal the focus changed because the project was in an "evaluation phase" at the time.

2. Another challenge for MD Anderson arose due to EHRs. The Oncology Expert Advisor was initially trained on MD Anderson's old EHR system, which was changed during the course of the project. The IBM product no longer works with MD Anderson's EHR system, and since its data has not yet been integrated with the new system, some of its information is outdated.

3. The Oncology Expert Advisor has not been piloted at additional hospitals, even though this step was included in a contract with PricewaterhouseCoopers. MD Anderson paid PwC $23 million to create a business plan for the system. Lynda Chin, the former chair of genomic medicine at MD Anderson, told the Wall Street Journal that partner hospitals showed a "lack of engagement or interest."

4. In total, the project cost MD Anderson more than $62.1 million. This figure includes payments made to external firms for planning, project management, and development for the Oncology Expert Advisor product, along with an initial MD Anderson and IBM contract of $2.4 million and $39 million in contract renewal fees.

MD Anderson is actively looking to other software contractors to potentially replace IBM's role in the project, having sent out a request for proposals that closed last month. The request specified that previous vendors could also submit proposals, but IBM declined to tell the Wall Street Journal whether it had submitted a bid.

"When it was appropriate to do so, the project was placed on hold," an MD Anderson spokesperson told Forbes in an article published last month. "As a public institution, we decided to go out to the marketplace for competitive bids to see where the industry has progressed."

These factors were wrought with logistical challenges, such as changes in focus on diseases, (from leukemia to lung cancer) and a change in EHR at MD Anderson.

Digital Health Space attributes the failure to naivete on the part of the vendor and the clinic. This was a first attempt to merge aspects of machine learning with the treatment of complex diseases with a myriad of possible combinations of anti-cancer drugs. The field itself has undergone the revolution of using powerful cellular poisons with severe side effects to precision medicine-based upon focused tools using molecular antibodies.

Predictive methods for reducing hypotensive episodes utilizing machine learning.

This study of hypotension and its role in morbidity in anesthesia was limited by the limitations of using intraarterial blood pressure monitoring. This method of monitoring blood pressure is usually limited to high-risk surgery, which excludes it from routine procedures in healthy patients.  It did provide accurate assessments and was an improvement over standard non-machine learning tools.

The HYPE Randomized Clinical Trial

Effect of a Machine Learning–Derived Early Warning System for Intraoperative Hypotension vs Standard Care on Depth and Duration of Intraoperative Hypotension During Elective Noncardiac Surgery: The HYPE Randomized Clinical Trial | Anesthesiology | JAMA | JAMA Network

Digital transformation is hot, the success rates are not, says BCG data | ZDNet

Digital transformation efforts, which are critical during the COVID-19 pandemic and new normal, need some work.

Only 30% of digital transformation projects met or exceeded their target value, according to a report from Boston Consulting Group.

BCG based its analysis on 895 digital transformation projects.

However, BCG said that another 44% created some value, but didn't hit targets and resulted in only limited long-term change. BCG also noted that 26% created a value of less than 50% of the target and produced no sustainable change.

It used to be said if there was a problem throw enough money at the challenge and it would be solved.  Today technology seems to have replaced that old adage. Anyone who has implemented that philosophy knows tech is not cheap.  Few even bother to analyze if there will be a return on investment.  What is your end game?  Do you want to increase efficiency by increasing productivity, or decrease the number of employees? 

The addition of tech involves two things. One, the initial capital investment, and two maintenance either in hardware or software upgrades.  Hidden personnel costs for training are essential.

Even in normal times, digital transformations can be challenging. Slower transformations allow study, comparison, and measurable outcomes. Crises such as covid 19 add workload to an already busy system. Evidence-based change and user experience in normal times allow for better study and planning prior to any implementation.  All of this occurs in covid times as background noise.

These facts reveal the minimal chance of success. In addition to those known factors, the unknown challenges such as societal disruption, distancing, and disruption of supply chain logistics compound acquisition and implementation of any technology solutions.

Can A.I. help?

According to BCG, most transformation efforts start off well, but ultimately lose focus. "When trying to bring everyone along with the overall plan, it can be easy to compromise and lose focus on the transformational aspiration. This is where the trouble usually starts," said BCG in its report.

There is a bright side in that a few best practices can flip the success rate to about 80%, said BCG.

Success factors include:

Research: Digital transformation plans shift due to COVID-19

A strategy with clear goals and business outcomes with the why what and how.

Commitment from the CEO to middle management for accountability. BCG noted that middle managers are often overlooked.

Deploying high-caliber talent and freeing up resources.

Address roadblocks quickly and adapt to contexts and missions.

Monitor progress toward outcomes with clear metrics and targets around processes.

A business-led modular technology and data platform.

It is crucial to address all six factors. Companies that adequately addressed only three or four failed. Of all of the possible combinations examined, none had the same impact on success as these six.

Digital Transformation:  Success or Failure?

An additional factor is whether the COVID 19 PANDEMIC will persist and for how long? Will it become the 'new norm?  The new spike in cases that exceeds the original pandemic of   April 2020 is now in progress.  Public health officials are pessimistic about the length and recurrence of spikes in COVID19.

Investment in technology should yield a good ROI if an enterprise is committed and has a long term plan.  Some technologies already exist and are in daily use.  Data analytics, Mapping software, Viral testing, Covid19 testing logistics as well as machine learning applications 

Digital transformation is hot, the success rates are not, says BCG data | ZDNet