The Present And Future Of Computer Vision

Computer vision, or the ability of artificially intelligent systems to “see” like humans, has been a subject of increasing interest and rigorous research for decades now. As a way of emulating the human visual system, the research in the field of computer vision purports to develop machines that can automate tasks that require visual cognition. However, the process of deciphering images, due to the significantly greater amount of multi-dimensional data that needs analysis, is much more complex than understanding other forms of binary information. This makes developing AI systems that can recognize visual data more complicated.

But, the use of deep learning and artificial neural networks is making computer vision more capable of replicating human vision. In fact, computer vision is becoming more adept at identifying patterns from images than the human visual cognitive system. For instance, in the field of healthcare, computer vision-based technology has said to have exceeded the pattern recognition capabilities of human physicians. Researchers have tested an AI that can detect neurological illnesses by reading CT scan images faster than radiologists.

The full Forbes article can be read at this link.  

When Hospitals Sue For Unpaid Bills, It Can Be 'Ruinous' For Patients

"Hospitals were built — mostly by churches — to be a safe haven for people regardless of one's race, creed or ability to pay. Hospitals have a nonprofit status — most of them — for a reason," says Martin Makary, one of the JAMA study's authors and a surgeon and researcher at Johns Hopkins Medicine. "They're supposed to be community institutions."

There are no good national data on the practice, but journalists have reported on hospitals suing patients all over the United States, from North Carolina to Nebraska to Ohio. In 2014, NPR and ProPublica published stories about a hospital in Missouri that sued 6,000 patients over a four-year period.

The full NPR article can be viewed at this link.  

How This Founder Is Using Technology To Reduce Racial Disparities In Healthcare

The inequalities in the healthcare industry are widely documented, with the Center for Disease Control and Prevention reporting earlier this year, for example, that there are massive racial disparities in pregnancy-related deaths. There is a lack of diversity in the medical field with only about 4% of U.S. doctors being black/African American and 5% being Hispanic; Latinos are currently one of the fastest growing ethnic groups in the U.S., which makes the latter statistic particularly problematic. With these health disparities in mind, a new platform, Hued, was developed. Hued is a platform that “diversifies the patient/doctor connection by connecting patients (of color) with health and medical professionals (of color) that specifically understand their cultural, physical and mental needs.” Hued founder Kimberly Wilson sat down to discuss the platform, why it was started and how it will impact diversity and inclusion in the field of medicine.

The full Forbes article can be found at this link.  

This App Listens In And Fills Out Paperwork So Doctors Can Focus On Patients

Since the shift to electronic health records (EHRs) in the United States accelerated a decade ago, the day-to-day impact on doctors is staggering. To keep records current and useful, physicians have to ensure all records of patient interactions get recorded, meaning that a large chunk of their day is spent staring at a screen rather than taking care of their patients. Recent studies show that doctors may spend as much as half of their work day filling out the records of their interactions with patients.

“In an ideal world, physicians would just interact with patients,” Saykara founder and CEO Harjinder Sandhu told Forbes. “That’s what they want to do. They don’t want to type notes.”

His Seattle-based company’s solution is an app that records a doctor’s interactions with patients, using AI and machine learning to hone in on key points of the doctor’s side of the conversation and appropriately document on the EHR, leaving the doctor free to focus on the patient. A new update to Saykara software passively records in the office without requiring activation, making operation even easier for doctors, who previously had to start recordings manually. 

The full Forbes article can be viewed at this link.  

Integrating Telemedicine Into Training: Adding Value to Graduate Medical Education Through Electronic Consultations

Lack of timely access to high-quality specialty care in the United States remains an enormous challenge, especially for uninsured and rural populations. Over 70% of federally qualified health centers reported barriers to specialty care for their patients, leading to diagnostic delays and poor health outcomes. A recent study found that 86% of referral coordinators in a community health center cited patient insurance as the most important driver of poor access to specialty care. The increasing pressure for primary care clinicians to manage complex patients in shorter visits may also incentivize over-referrals: The US referral rates doubled from 1999 to 2009. These trends, as well as an ongoing national emphasis on cost savings in health care, have led to a recent increase in the use of telemedicine. Learning how to utilize telemedicine has become more relevant for trainees preparing to enter the physician workforce. Integrating telemedicine into graduate medical education (GME) curricula provides an important mechanism for improving trainee education on value-based care and increasing access to specialty care.

The full article can be downloaded below.  

DigiVoice: Voice Biomarker Featurization and Analysis Pipeline

In recent years, data-driven models have enabled significant advances in medicine. Simultaneously, voice has shown potential for analysis in precision medicine as a biomarker for screening illnesses. There has been a growing trend to pursue voice data to understand neuropsychiatric diseases. In this paper, we present DigiVoice, a comprehensive feature extraction and analysis pipeline for voice data. DigiVoice supports raw .WAV files and text transcriptions in order to analyze the entire content of voice. DigiVoice supports feature extraction including acoustic, natural language, linguistic complexity, and semantic coherence features. DigiVoice also supports machine learning capabilities including data visualization, feature selection, feature transformation, and modeling. To our knowledge, DigiVoice provides the most comprehensive voice feature set for data analysis to date. With DigiVoice, we plan to accelerate research to correlate voice biomarkers with illness to enable data-driven treatment. We have worked closely with our industry partner, NeuroLex Laboratories, to make voice computing open source and accessible. DigiVoice enables researchers to leverage our technology across the domains of voice computing and precision medicine without domain-specific expertise. Our work allows any researchers to use voice as a biomarker in their past, current, or future studies.

The full article can be downloaded below.  

As Deep Learning Comes For Medicine How Do We Work Around Its Brittleness?

Deep learning is revolutionizing medicine. Algorithms are increasingly doing everything from triaging medical imagery to predicting treatment outcomes. Yet as hospitals undergo the same AI revolution affecting other fields, the dangers of AI bias and errors and the life-or-death consequences of medicine lends unique risk to these experiments, suggesting caution.

One of the fastest-growing uses of AI in medicine today is the analysis of medical imagery. Human analysis of imagery is slow, difficult to scale and error-prone. Replacing or augmenting human analysis with algorithmic analysis could even eventually allow medical imaging devices to diagnose patients in real-time as they are being imaged and direct technicians to collect additional imagery to narrow the diagnosis while the patient is still lying the imaging system.

The problem is that today’s correlative deep learning systems require vast amounts of extremely diverse training imagery, which can be hard to acquire in hospital settings where there may be more uniformity in patient conditions, demographics and imaging systems. Most dangerously, AI algorithms can easily learn characteristics unrelated to the actual disease itself, lending to false positives and negatives that can cause adverse patient outcomes or even death.

The full Forbes article can be viewed at this link.  

How Millennial Doctors Are Transforming Medicine

Changing healthcare models, groundbreaking advancements in the health technology sector, and shifting standards of patient care—they’re all contributing to a new era of medicine. But arguably one of the biggest changes will be the faces that greet us at a clinic or hospital.

Today’s infographic from Publicis Health illustrates the emerging generation of millennial doctors, and why they’re on the cusp of transforming the healthcare industry.

The full Visual Capitalist article and Publicis Health infographic can be viewed at this link.  

How Blockchain And AI Can Help Master Data Management

Master data is easily one of the most critical assets that a business possesses. With continuous digitization and the advent of the fourth industrial revolution, the value of master data and the importance of master data management are only going to grow. Before we proceed into the importance of master data management, let’s understand what master data is.

Gartner defines master data as “...the consistent and uniform set of identifiers and extended attributes that describes the core entities of the enterprise including customers, prospects, citizens, suppliers, sites, hierarchies and chart of accounts.”

Essentially, master data refers to all the static information that is used to identify the critical elements of a business. This can include the names of products, people (customers, suppliers, employees, leads, etc.), special equipment and tools, facilities, etc. Master data is different from transactional data such as invoice numbers, invoice amounts, dates, process parameters, etc. The purpose of master data is more about identifying and less about measuring.

The full Forbes article can be read at this link.  

MetLife Plans To Disrupt $2.7 Trillion Life Insurance Industry Using Ethereum Blockchain

When a family loses a loved one, it faces a litany of immediate tasks such as planning the funeral and placing an obituary in the local newspaper. All of this must be done while the bereaved is processing the emotional components of the individual’s passing. Amidst all of the raw feelings and deluge of family, it is natural for more mundane tasks such as filing a life insurance claim to fall by the wayside. Sometimes the family may not even know that the deceased has a life insurance policy.

This opaqueness does not serve the claimants or insurers well, and leading global insurer MetLife is utilizing the live public Ethereum blockchain to add transparency and efficiency to the claims process. In what is believed to be the first pilot program in the world focused on the life insurance industry, MetLife’s Singapore-based incubator LumenLab is collaborating with Singapore Press Holdings (SPH) and NTUC Income (Income) on a platform of smart contracts known as ‘Lifechain’ to help loved ones quickly determine if the deceased was protected with a policy and automatically file a claim.

If successful, this program has the potential to transform the insurance industry as a whole, creating new markets, products, and the ability to serve a more diverse set of customers at lower price points.

The full Forbes article can be viewed at this link.