FDA unveils open source code for collecting patient data

The U.S. Food and Drug Administration on Tuesday posted open source code for its MyStudies App to enable researchers to collect patient-provided data.  Researchers can customize and rebrand the agency’s MyStudies App for their own clinical trials or observational studies.

Straight from the FDA: “MyStudies is designed to facilitate the input of real world data directly by patients, which can be linked to electronic health data supporting traditional clinical trials, pragmatic trials, observational studies and registries.”

The full Healthcare IT News article can be viewed at this link.  

A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain

In this study, we aimed to evaluate whether a deep learning algorithm could be trained to predict the final clinical diagnoses in patients who underwent 18F-FDG PET of the brain and, once trained, how the deep learning algorithm compares with the current standard clinical reading methods in differentiation of patients with final diagnoses of AD, MCI, or no evidence of dementia. We hypothesized that the deep learning algorithm could detect features or patterns that are not evident on standard clinical review of images and thereby improve the final diagnostic classification of individuals.

Overall, our study demonstrates that a deep learning algorithm can predict the final diagnosis of AD from 18F-FDG PET imaging studies of the brain with high accuracy and robustness across external test data. Furthermore, this study proposes a working deep learning approaches and a set of convolutional neural network hyperparameters, validated on a public dataset, that can be the groundwork for further model improvement. With further large-scale external validation on multi-institutional data and model calibration, the algorithm may be integrated into clinical workflow and serve as an important decision support tool to aid radiology readers and clinicians with early prediction of AD from 18FFDG PET imaging studies.

The full pdf can be downloaded below.  

Lowering costs and improving health outcomes are two of the biggest drivers of expanding the artificial intelligence market in health care. eHealth Initiative, a nonprofit organization working at the intersection of health and technology, and Cerner, a global leader in health care technology, explore this evolving role of AI in a new report titled, “Artificial Intelligence (AI) in Healthcare.” 

The brief identifies three key areas for AI implementation in health care: physicians’ clinical judgment and diagnosis, AI-assisted robotic surgery and virtual nursing assistants. The publication also cites key data that indicates a growing demand for AI in health care throughout the next decade, while presenting cost savings to the health care system. Experts estimate AI applications could potentially create $150 billion in annual savings for the country’s health care economy by 2026.

The report explores several areas providers should consider for successful adoption of AI, including:

• Institutional Readiness and Network Capabilities
• Ethical Standards for Privacy and Safety
• Data Governance
• Data Types
• Access to High-Quality and Unbiased Data
• Evaluation of Technology Models
• Cost Savings

Slides by William T. Thorwarth, Jr., MD, FACR, CEO, American College of Radiology presented at eHI's October 31, 2018 Prior Authorization Workshop.

Presentation reviewed appropriate use criteria (AUC), key goals for imaging AUC policy, AUC and congress's Protecting Access to Medicare Act (PAMA), the Fundamentals of PAMA, CMS rules for AUC program, and an example of their CDS EHR integration.

Breaking Borders in Patient-Centric Medicine

Patient-centric care means faster, more accurate, painless and hopefully, failsafe delivery of medical care to patients with the smallest margin of error possible. This type of care is continuously evolving.

A number of companies have created systems that personalize patient care while ensuring all data regarding each and every patient is accurate, protected, and easily accessible 24/7. In an industry that is so huge, one thing modern technology brings back to the medical arena is personalized care—but with the accuracy, speed, and interface of modern technology.  

This article highlights a number of topics, including: 

1. Introducing telemedicine
2. Continuous patient monitoring
3. Wind tunnel technology fights lung disease
4. Biosensor monitors critical signs
5. Needle free blood collection

The full ECN article can be viewed at this link.  

How Is AI Revolutionizing Elderly Care

There is an unprecedented growth in the percentage of aging population throughout the world, particularly in growing economies such as Europe, Japan and China. Form 2000 to 2050, the percentage of the world’s population who is 60 years of age and older will approximately double from about 12% to 22% (from 605 million to 2 billion). During the same period, the number of people aged 80 years and older will quadruple. In the USA, 14.5% of the population is 65 years or older, but by 2030 these number is anticipated to grow to 20%.

This rapid aging demographic will directly affect social, economic and health outcomes for these growing economies. Particularly healthcare delivery pathways need to be readjusted, keeping in mind the prevalence of chronic diseases, comorbidities and polypharmacy requirements of the elderly and geriatric patients. Geriatric diseases such as atherosclerosis, osteoporosis, cardiovascular diseases, obesity, diabetes, dementia and osteoarthritis require quick diagnosis and continuous supervision by a professional caregiver. This is coupled with the fact that we are not training enough physicians and caregivers to account for the increased demands of healthcare. The US will face a shortage of between 40,800 and 104,900 physicians by 2030.

Given the situation, healthcare providers are starting to offload certain parts of the care-pathways to artificial intelligence (AI) based automatization. AI can now be found in every step of the care-pathway, starting from intelligent tracking of biometric information to early diagnosis of diseases. AI is helping patients and their families understand the treatment pathways. AI is also helping clinicians to treat the conditions more efficiently.

Here are 5 ways in which AI is revolutionizing elder care:

1. At home health monitoring
2. Smart device assisted daily living
3. Smart device assisted fall detection
4. Virtual companions
5. Anti-aging research

The detailed Forbes article can be viewed at this link.  

The opportunities and challenges of data analytics in health care

This report is part of "A Blueprint for the Future of AI," a series from the Brookings Institution that analyzes the new challenges and potential policy solutions introduced by artificial intelligence and other emerging technologies.  This report specifically addresses topics such as sensitivity of care decisions, problematic data conventions, institutional practices, misaligned incentives, and ultimately concludes with policy recommendations.

The full report can be viewed at this link.  

5 Surprising Ways In Which Telemedicine Is Revolutionizing Healthcare

“Telehealth is not a specific service, but a collection of means to enhance care and education delivery,” says the Center for Connected Health Policy (CCHP). CCHP further classify telehealth into four types of services, live-video conferencing, mobile health, remote patient monitoring, and store-and-forward. Most telehealth platforms provide one or more of these services, to a niche patient or consumer segment.

Here are five surprising ways in which telehealth is revolutionizing healthcare.  

1. Remote elderly monitoring
2. Remote psychiatric care
3. Getting a second opinion
4. Care in remote locations
5. Redefining health insurance

The full Forbes article with details on these points can be viewed at this link.  

Using Previous Medication Adherence to Predict Future Adherence

Medication nonadherence is a major public health problem. On average, up to 50% of patients do not adhere to their prescribed therapies. Less than half of patients persist with cardiovascular drugs for a year following a heart attack, despite compelling evidence of the clinical benefits of these life-saving treatments. Poor adherence has substantial clinical and economic consequences. In the United States, suboptimal adherence accounts for 33%-69% of medication-related hospital admissions and $100 billion of potentially avoidable health spending each year.

In this study, previous adherence to chronic medications was a strong predictor of future adherence to newly initiated statins and was a stronger determinant than demographic variables, clinical variables, and other medication-based measures. When predicting medication adherence in administrative claims data, whether for targeted adherence improvement interventions or to better design comparative effectiveness research studies, models should include measures of previous medication adherence, such as mean PDC.

The full pdf can be downloaded below.  

This paper helps the healthcare industry debunk several myths surrounding SDOH and it's uses.