Altheia’s Mission

Altheia Angle

From the desk of Jolly Nanda, Altheia’s CEO.

At Altheia, we’re on a mission to improve the way clinical case managers prioritize, identify, and treat their members with chronic diseases as we introduce our product, Acuvia, to the market. It’s a simple concept but it has so many implications across the healthcare ecosystem.

Today, chronic disease management is done retrospectively using claims data as the standard and takes a one-size-fits-all approach to outreach. According to this McKinsey study, moving to a model where outreach is individualized through an intensity of care strategy, the people who could benefit from case management would be prioritized and that could prevent them from doing irreparable damage to their health while increasing ROI for care management companies.

Our new product, Acuvia, supplements traditional data sources with social determinants of health data and member-provided longitudinal data. Using this expanded dataset to not only surface already diagnosed patients, Acuvia also predicts who is undiagnosed and who might be at future risk. Acuvia then does a relative prioritization within the population, providing a full spectrum of risk profiles and priority to the care management company, and individualized risk assessments to the members across 5 chronic conditions.

If we dig deeper into what using this expanded dataset means in terms of our mission, we must take into consideration the systemic inequities and biases already inherent in the healthcare system.

Here are some examples of these:

In the US, women were not required to be included in clinical research until 1993 when the NIH Revitalization Act was passed by Congress.

Gender bias resulting in disbelief in symptoms: This 2018 study found that that gender bias in pain management found that physicians, irrespective of their own gender, viewed men with chronic pain as “brave” and/or “stoic” while women with chronic pain were viewed as “emotional” or “hysterical”.

This report from the Medical Research Foundation in the UK found that women are over 50% more likely to be misdiagnosed when suffering a heart attack, resulting in more serious outcomes, including death. This is attributable to the research around heart attack symptoms being done on men, and later understanding that women present differently in the clinical setting.

Racial bias resulting in decreased care: This Harvard article references a number of studies that show physicians underestimate the pain experienced by people of color and many avoid prescribing stronger pain medications based on an erroneous assumption that they are more likely to abuse drugs than white people.

This medically-reviewed article from Forbes highlights a growing issue around obesity bias. As Americans from the US are increasingly overweight, long-held beliefs that obesity is purely the result unhealthy decisions of the individual versus a complex disease that also involves the intricate interplay of genetics and environmental factors, is resulting in lower quality of care and poorer outcomes for more people.

These types of biases impact medical treatment for a vast number of diseases, including those we are currently focusing on here at Altheia: heart disease, diabetes, chronic kidney disease, hypertension and COPD. With more diversity in our data and an acknowledgement that these biases are both problematic and widespread, the healthcare sector can easily begin addressing these disparities and inequities without significant incremental cost in the underlying infrastructure: data is already being aggregated; patients are already being seen; and, studies are already being done. What we need across the ecosystem is awareness, education, and a systematic approach to technology that mitigates the risk introduced through systemic bias.

Care and disease management has been an important component in the healthcare ecosystem for two decades without much evolution beyond using historical medical data and segmenting at the population level. Acuvia will help companies in this sector approach population health management in a whole new way: individualized and relevant data at the right time, resulting in better care, lower costs and a healthier member.

In our predictive models, we are collecting a significant amount of data from claims, lab results, clinical chart data and social determinants of health data provided by members. Any incremental cost in bringing in the data diversity is negligible; however, the benefits of being able to use it are enormous. Not only can we see new correlations, but we can also use it to make our models even more individualized to improve outcomes for people.

And that brings us back to our mission: making healthcare personal and bringing a product to market that will address long-standing disparities and inequities in the healthcare sector. Making a difference for everyone is what drives us every day.

Jolly
AHA Pitch

AHA Pitch

Altheia Predictive Health Pitch at AHA – Empower to Serve MN – FAN FAVORITE 2022 WINNER

Jolly Nanda, the visionary behind Altheia Predictive Health was selected as one of 4 companies to compete for grant funding at the American Heart Association  EmPOWERED to serve Business Accelerator in Minnesota. This Business Accelerator looks for a diverse pool of social and digital health entrepreneurs and organizations who are driving change through health justice in their communities. Finalists participate in a six-week virtual business training and have a chance at grant funding. The event was held at the General Mills Headquarters and sponsored by Cheerios.

Analyzing the Covid-19 Vaccine Distribution Method and Experience

Analyzing the Covid-19 Vaccine Distribution Method and Experience

Analyzing the Covid-19 Vaccine Distribution Method and Experience

Introduction

As the Covid-19 vaccine begins to roll out for those who qualify for the initial distribution, the country as a whole is still seeing spikes and surges of cases, as well as high occupancy levels at hospitals and ICUs. The LA Times reported that “one hospital in southwest Los Angeles, Memorial Hospital of Gardena, is at 320% occupancy [and that] the 172-bed medical center has been in various levels of “internal disaster status” since March.”  That said, as the vaccine becomes more available to the general public, it is important to understand what type of analytics can help us bring these shocking statistics down and how we can understand if distribution plans are effectively working. 

Discussion

In evaluating the best way to roll out the vaccine, Accenture put together a list of relevant information to be collected for analysis. So what are the relevant data and statistics that go into a successful roll out? The first step in planning is forecasting and this is done by collecting data on a given population, this can be conducted at the county, city, state or regional level; relevant data in terms of the vaccine will include age and level of disease present in that population. From that information, distributors can decide where to locate dispensing sites and the supply necessary at each dispensing site. Once distribution starts, the next step will be adjustments which can be aided through artificial intelligence and machine learning. This would simply analyze the forecasting method used in the initial step and improve upon it so that new distribution centers are better prepared than the first ones. The final step is to evaluate the success of distribution which will vary based on the distribution leader, however, because the goal is to vaccinate as many people as possible and as quickly as possible, this will look at tiers that had the most waste in terms of vaccines and tiers that did not have enough vaccines to meet their demand. 

One of the main concerns when it comes to vaccine distribution, on every level including the country level, is equality in distribution. An interesting point of data is that “as of 15 November 2020, several countries have made premarket purchase commitments totaling 7.48 billion doses, or 3.76 billion courses, of Covid-19 vaccines from 13 vaccine manufacturers. Just over half (51%) of these doses will go to high income countries, which represent 14% of the world’s population.” This brings up questions of income disparity as it relates to population health and is something that can also be tracked through analytics. 

Conclusion 

As accessibility to the Covid-19 vaccine increases, we highly encourage you to consider getting vaccinated. The policies and practices in place in this country make the vaccinations very safe, in fact,“the US has the best post-licensure surveillance system in the world making vaccines extremely safe and not getting vaccinated puts yourself and others at risk.”  There is a lot of hesitation and concern when it comes to the vaccine which will make people less likely to get it on their own. To encourage you to get it as soon as it is made available to you, we are sharing the experience of Adiba Mobin, a UT Southwestern employee who has received both doses of the vaccine:

I received the first dose of the Pfizer COVID-19 vaccine on December 23, 2020, just 9 days after the initial vaccine rollout in Texas. I did not take any medication (Ibuprofen, Acetaminophen, etc) before getting the vaccine. A few hours after receiving the first dose my arm became sore at the injection site and the soreness soon spread to my entire upper arm (shoulder to elbow) so I took some Tylenol for the pain which helped with the pain. Within the next 24 hours the soreness had vanished and I had absolutely no other side effects. 

I received the 2nd dose on January 12, 2021, exactly 21 days later. This time I went prepared with a painkiller 30 minutes before getting vaccinated. The nurse administering my vaccine encouraged me to stay ahead of the possible side effects by taking Aleve or Tylenol specifically, as Ibuprofen might not be as effective. Once again, about 2-3 hours after receiving the second dose I had arm soreness at the site and at 5 hours post vaccination I could feel a headache coming on. At 8 hours post I took 1 extra strength Tylenol. The following day at 24 hours post-vaccination there was still arm soreness and a lingering headache but I did not take another Tylenol until 32 hours post vaccine, to help with some very minor muscle aches and arm soreness. All of my side effects were extremely manageable and nothing that took me away from my work for the day.” 

 

Putting Data Behind Healthy Decisions

Putting Data Behind Healthy Decisions

Putting Data Behind Healthy Decisions

Authored by Ayesha Rajan, Research Analyst at Altheia Predictive Health

Introduction

As we ring in 2021, we also ring in an abundance of New Year’s resolutions and the most common resolutions include health related goals such as improved eating habits and weight loss. In all of our articles that quantify diseases, we include tips for improved health. Many of them include eating a healthy, balanced diet and incorporating exercise in your lifestyle, as well as more specific tips. In today’s article, we will put some numbers behind some of these tips to encourage you to incorporate them into your New Year’s goals and to generally increase your knowledge and add perspective to these lifestyle choices. 

Discussion 

Though exercise is a highly recommended part of a healthy lifestyle, “less than 5% of adults participate in 30 minutes of physical activity each day; only one in three adults receive the recommended amount of physical activity each week.” This is a statistic that is highly concerning because exercise is a known preventative method for diseases such as heart disease, diabetes and more. In fact, “a 2013 noted that higher levels of physical activity were associated with a 21 percent reduction in coronary heart disease events for men and a 29 percent reduction…in women.” On the other side of things, lack of physical activity is “estimated to be the primary cause of approximately 21-25% of breast and colon cancers, 27% of diabetes and approximately 30% of ischaemic heart disease” globally. From this, we can see, through hard data, the importance of including physical activity in our lifestyles. 

According to the CDC, only “12.2% of adults in the USA meet the daily fruit intake recommendations [and] less than 10% of US adults adopt and stick to the recommended vegetable guidelines.” These statistics are made believable when paired with the fact that “117 million adults suffer from one or more chronic diseases due to improper nutrition.” There is a definite connection between our nutritional decisions and the status of our health. However, a healthy diet can mean different things to different people so consider consulting your physician or a nutritionist to see how you can improve your health through your diet.

Conclusion

Clearly, there is hard data behind the reasoning and importance of including physical activity and a nutritious diet into your lifestyle. If you are just starting to make changes in your lifestyle, simple steps such as going for a 30 minute walk or incorporating fruits and vegetables into your diet can be a great first step. If you are looking to improve your health and fitness, you can set goals for yourself such as incorporating a new type of workout into your routine or taking a look at and improving your macronutrient counts. 

 

https://www.hhs.gov/fitness/resource-center/facts-and-statistics/index.html

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3879796/

https://www.euro.who.int/en/health-topics/disease-prevention/physical-activity/data-and-statistics

Recommended Tools for Data Scientists in the Medical Field

Recommended Tools for Data Scientists in the Medical Field

Recommended Tools for Data Scientists in the Medical Field

Authored by Ayesha Rajan, Research Analyst at Altheia Predictive Health

Introduction

Data science is a field that is becoming increasingly applicable to nearly every aspect of our lives. From our online shopping habits to sports analytics, there are vast applications of this field. One application is in healthcare and, more specifically, in disease prediction and management. Each field that data science is applied to has specific tools that are best suited for the desired outcome – in this article we will explore data science tools that are especially relevant to the field of medicine.

Discussion 

One incredibly useful function for medical analytics is Support Vector Machines. SVM’s are algorithms with high accuracy levels that are used for classification and analysis; they are incredibly useful in the processing and learning of images which means they are useful tools when it comes to processing medical images such as x-rays, MRI’s and CT scans. 

Natural Language Processing is also a great tool to have in your toolkit. NLP is a field of artificial intelligence that seeks to decode and understand the human language and patterns within it. This is particularly useful in analyzing a physician’s digitized notes and picking up on commonalities used in their phrasing that can highlight trends in diseases, especially in the early stages of diseases. Natural Language processing is best conducted in Python and that is another great tool to have under your belt as a data scientist in the medical field. 

Another great tool for data science is SQL. SQL is a programming language that is used for relational database management systems. In overlapping the field of medicine and data science, SQL can be a powerful tool in its ability to store, process and execute functions on genomic data. To work with SQL, a researcher might create a database with genetic information and then map data from that database to predict the effect of a drug and isolate a specific gene that causes problems in issuing that drug therapy. They might also use it to isolate certain genes when studying a disease or to make connections between a person’s overall health profile and the health issues they may be facing. 

Conclusion 

Similar to every other application of data science, there are specific tools that are best utilized when working with medical and biological data. The tools we discussed in our article today are tools that are optimized to process, clean and understand data in a medical setting and are great skills for any entrepreneur working in this field to have. To support learning endeavors in this field, we’ve created a short list of resources to help gain traction in picking up these skills: 

Support Vector Machines Explanation and Functions: https://scikit-learn.org/stable/modules/svm.html

Natural Language Processing Explanation: https://becominghuman.ai/a-simple-introduction-to-natural-language-processing-ea66a1747b32?gi=257c3ee25a16 

Python Crash Course: https://www.youtube.com/watch?v=JJmcL1N2KQs 

SQL Crash Course: https://www.codecademy.com/learn/learn-sql