Data Med Solutions specializes in analytic approaches to the medical and health fields, focusing on customized and cost-efficient solutions for research and analytic needs.

Data Med Solutions

IOMED operates a Data Space Platform powered by AI, created to enable Data Spaces and mediate health data for secondary use, ensuring compliance.

IOMED

DataMed Solutions | 885 followers on LinkedIn. DataMed Solutions provides timely, cost-efficient, and customer focused HEOR solutions for its clients worldwide | DataMed Solutions is a preferred provider of Health economics and outcomes research to many of the largest pharmaceutical companies in the world.  We work in a networked environment with over 200 affiliate organizations to provide customized solutions to client&#39;s research, analytics and data modeling needs.

Leading Success using Data: Chief Data Scientist, Health Economist, Columbia University - my latest book is Winning with Data Science

Howard Friedman

DataMed Solutions

We are proud to announce that Howard Friedman will be discussing his Pulitzer-Prize nominated 𝑾𝒊𝒏𝒏𝒊𝒏𝒈 𝒘𝒊𝒕𝒉 𝑫𝒂𝒕𝒂 𝑺𝒄𝒊𝒆𝒏𝒄𝒆 (2024) at the Gates Foundation today. We thank the Gates Foundation for being such generous hosts during out time in here in Seattle.

Excellent collaboration with Papa Inc., on exploring the cost impact of companion care programs among Medicare Advantage patients' unhealthy physical and mental health days.

Real-world evidence spans well beyond the world of pharmaceuticals - at DataMed Solutions we are proud of our work in the pharma space as well as our partnerships in 𝐦𝐞𝐝𝐢𝐜𝐚𝐥 𝐝𝐞𝐯𝐢𝐜𝐞𝐬 as well as 𝐡𝐞𝐚𝐥𝐭𝐡 𝐚𝐧𝐝 𝐬𝐨𝐜𝐢𝐚𝐥 𝐬𝐞𝐫𝐯𝐢𝐜𝐞𝐬. In a recent publication with Papa, a retrospective study showed the association between self-reported physically and mentally unhealthy days with health care costs among a Medicare Advantage population. Each additional unhealthy day reported was associated with an increase in 30-day medical costs of $60 and $34 for physically and mentally unhealthy days, respectively. Thank you to the great collaboration with Kelsey McNamara Ellen Rudy John Rogers, Zachary N Goldberg and David B Nash. More information is available at The Cost of Unhealthy Days: A New Value Assessment, Population Health Management, 2024 Aug 27

We previously discussed the use of antisense oligonucleotides (ASOs) and their therapeutic use to manage a variety of conditions. Just to recap, ASOs are chemically synthesized short strands of DNA or RNA that are designed to primarily bind with messenger RNA (mRNA), which in turn, is very important for protein synthesis in cells. There are two distinct ways currently developed ASOs exert their i.e. via an ‘occupancy’ mechanism or via an RNA degradation mechanism. The ASO ‘occupancy’ mechanism has many potential forms but the most common may include stearic blocking of the RNA by the ASO to prevent translation of the RNA strand or by splicing mechanisms of axon skipping or axon inclusion by the ASO onto the RNA strand, thereby modulating the activity of the RNA strand. Most ASOs that are currently being developed impact the second mechanism i.e., RNA degradation, by interfering with the enzymes RNase H1 or Argonaute2 (Ago2) in the cell that are involved in RNA degradation processes. Both of these mechanisms tend to impact the mRNA translation activities, that in turn impact protein synthesis. One of the challenges that hindered the development of ASOs as effective therapeutic agents had been the rapid elimination of ASO particles in the body. However, rapid advances in the medicinal chemistry of ASOs have tried to address this issue by improving better protein binding, increasing cellular uptake and preventing early nuclease enzymatic breakdown through chemical modifications of the ASO molecules. Approaches such as using conjugate linking, adding sugar moieties to the ASO, modifications on the backbone of ASOs, base modification on the ASOs, and encasing ASOs in lipid nanoparticles all have helped improve and extend the elimination half-lives of ASOs, which has also improved their clinical potential. One major benefit of a longer ASO half-life is that the dose of the ASO can be greatly reduced, and doses can be administered far less frequently. However, it should be noted that there are ongoing concerns about potential toxicities and increased pro-inflammatory response by the body to these chemical modifications. As stated before, drug development in this area is quite intense, with work currently focusing on new target indications and on improving the medicinal chemistry of ASO molecular stabilization and modifications to improve safe and effective clinical use. With more ASO market entrants, the evidentiary requirements for market access and price justification will likely grow. DataMed Solutions LLC is ideally positioned to provide the necessary expertise in evaluating both the safety and effectiveness of this class of targeted therapies, given our experience in this area. #antisense #oligonucleotides #targetedtherapies Photo courtesy of the CDC

Let's talk about model 𝐛𝐢𝐚𝐬 It’s easy to think that all data is objective, but if the underlying data or decisions made when collecting data were 𝐛𝐢𝐚𝐬𝐞𝐝, then the machine learning model is going to reflect the same 𝐛𝐢𝐚𝐬𝐞𝐬. Machine learning models are designed by humans, so it’s not a surprise that human 𝐛𝐢𝐚𝐬𝐞𝐬 could be baked into the machine learning models. In other words, the biases and underrepresentation that are present in the media end up getting baked into the machine learning model. One way to quantify the fairness of a machine learning model is to measure the performance of the model across groups of interest. Often in fairness analysis, we are interested in the performance of a model across certain demographic groups, such as by race, gender or income. One metric is called group fairness. It measures whether subjects in each group have an equal probability of being assigned to a certain outcome class. For example, if we used a machine learning algorithm to help decide which candidates we should hire, we would want to make sure that our model does not perpetuate biases that may disadvantage women or people of color. Another measure of model fairness is whether the accuracy of the model is comparable across groups of interest. If we built a model to recommend who should receive a certain treatment, we would want to make sure that the accuracy of the model is comparable between white people and people of color. We want to know “If we use this model, will it improve outcomes for patients of color just as much as it will for white patients?” Addressing model 𝐛𝐢𝐚𝐬 can be approached in several ways. One method involves identifying and removing biased data sources, then retraining the model. For instance, if a fairness analysis reveals that a model performs differently for white patients compared to patients of color, adjustments might be needed. This could mean selecting a less biased outcome or altering the model's predictive process for different racial groups. Other strategies to mitigate 𝐛𝐢𝐚𝐬 include adversarial debiasing, fair representation learning, and fairness-constrained optimization. These methods integrate fairness considerations directly into the model development and training stages. (Image reposted from Telus International website) #bias #datascience #ai

In our continuing series on target therapies, we shall now focus on antisense oligonucleotides (ASOs) and their therapeutic use to manage a variety of conditions. ASOs are chemically synthesized short strands of DNA or RNA (usually around 12-30 nucleotides) that are designed to bind with messenger RNA (mRNA), which in turn is very important for protein synthesis in cells. After ASO binding to mRNA, these targeted ASOs can either impact mRNA degradation (modulate the levels of the mRNA in the cell and thus impacting the efficiency of protein synthesis) or to interfere with the mRNA translation process, whereby the specifically encoded mRNA directs the generation of the right cellular protein for action in the cell and beyond. Why this is important is that the modulation of some types of protein synthesis brought upon by defects in certain genes can drastically improve patient outcomes, especially in rare genetic conditions. For example, patients with hereditary transthyretin (TTR) benefit greatly from inhibition of production of TTR protein due to a defective gene by the ASO agent, inotersen, or patients with spinal muscular atrophy (SMA) that benefit from axonal alterations on the defective SMN1 gene by the ASO, nusinersen. There are at least 19 approved ASOs in 2024 and many more in the pipeline, targeting quite a number of therapeutic indications. Work continues in developing additional targets for ASOs as well as improving the medicinal chemistry of these agents for safe and effective clinical use. Additional real-world evidence of safety and effectiveness over longer time horizons may also be needed to justify pricing and continued market access, especially with more market entrants. DataMed Solutions LLC has considerable experience conducting real-world observational studies that have focused on the safety and effectiveness of targeted therapies across a number of indications #antisense #oligonucleotides #targetedtherapy Photo courtesy of GoogleDeepmind on Unsplash

Interested in learning about Data Science? DataMed Solutions offer online and in-person training in a large number of data science, analytics, HEOR and statistics topics. Our senior partner, Howard Friedman is launching his latest LinkedIn Learning course, The 80:20 Rule of Data Science, at the end of this month.

One of the most common questions I get is "𝐌𝐲 𝐩𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐯𝐞 𝐦𝐨𝐝𝐞𝐥 𝐢𝐬𝐧'𝐭 𝐰𝐨𝐫𝐤𝐢𝐧𝐠 𝐰𝐞𝐥𝐥 𝐞𝐧𝐨𝐮𝐠𝐡...𝐰𝐡𝐚𝐭 𝐬𝐡𝐨𝐮𝐥𝐝 𝐈 𝐝𝐨?" If model performance is disappointing, there are three main levers that we can pull to try improving the performance. 🔷 The first and most powerful lever is changing the data that the model is using. We can add more features to the model or by transforming the features that we’ve already included. In my experience, this is the most powerful of the levers. 🔷 Another lever we can pull is changing the type of model or the type of feature selection. If we see that a regression model isn’t working well, we can try a decision tree, for example. We can also try using a penalized regression model that performs feature selection automatically during the modeling process. 🔷 The other lever is tuning the hyperparameters. A hyperparameter is like a setting knob on a model. It adjusts the model's rules so changes in the hyperparameters produce models with very different results. Any combination of these three levers may be used to improve model performance. Depending on what data is accessible, it may not be feasible to add more features, so the data scientist must rely on hyperparameter tuning and model selection to improve the quality of predictions. Please drop us a note if you want to talk more about predictive modeling and HEOR

We last reviewed the mechanism of action and the use of Antibody Drug Conjugates (ADCs) in medical care, most notably in oncology. This current post shall discuss factors associated with ADCs that impact either clinical effectiveness or safety. There are many advantages with ADCs in treating certain types of cancer. ADCs will likely have better tolerability, with lower off-tumor effects and also since ADCs are targeted therapies, a much lower dose of the SMC agent is needed, leading again to a lower risk of adverse events. Tolerability of ADCs is also improved since ADCs are generally stable in the blood stream but are designed to release their payloads within cells in the tumor microenvironment (TME), reducing the potential spill-over to healthier ‘normal’ cells. In addition, the antigen-specific antibodies used in ADCs may also stimulate the body’s immune response by mobilizing T-cells, macrophages and other immune processes to achieve an additive effect in killing tumor cells. Other advantages include a ‘bystander’ effect where the SMC released in a cell can also impact other cells in the TME, broadening the cytotoxic effect. This advantage is usually seen with ADCs that use a cleavable ‘linker’. In addition, there are synergies when used in combination with other therapeutic agents such as immunotherapy agents and anti-angiogenesis agents. However, ADCs do have some drawbacks as well. ADCs do have adverse drug events (ADEs), some of which can be serious and mostly attributable to the SMC payload. There is the potential that an ADC with a cleavable ‘linker’ may release the SMC payload before reaching the target tumor cell, leading to ADEs. This is less of a problem with non-cleavable ‘linker’ ADCs. There is also the potential of ADCs to elicit an immune response by the body given potentially large molecular sizes of the ADC complex, leading to premature release of the payload. There also has been recent evidence that cancer cells may have also developed resistance mechanisms to some ADCs. Of late, there have been concerns by the FDA regarding ADC manufacturing issues. ADCs need to adhere to a specific drug-to-antibody ratios (DAR) for clinical effectiveness and this can be challenging to ensure in the production of these agents. The ADC market is projected to grow spectacularly over the next decade and beyond. As antibody and linker technologies improve, the targeting specificity and efficacy will improve, and the adverse event issues may be reduced. With our work in Oncology, DataMed Solutions LLC is uniquely positioned to assist clients with their real-world evidence generation needs as well as health economic support in this exciting new area of cancer therapeutics. #healthoutcomes #antibodydrugconjugates #targetedtherapy Photo courtesy of the National Institute of Allergy and Infectious Disease

With recent advances in immunology and biotechnology, there has been a lot of excitement and interest in developing highly specific targeted therapies in the management of disease, notably in cancer. We intend to review some of the more novel targeted therapy approaches over the next few posts, starting with Antibody Drug Conjugates (ADCs). Cancer is a leading cause of death worldwide, accounting for 10 million deaths in 2020. Small molecule chemotherapeutic (SMC) agents and combinations of these agents are the mainstay of cancer treatment. One major drawback with the use of these agents is the lack of specificity that leads to modest efficacy and also significant off-tumor effects that in turn can cause adverse events. An interesting recent development in targeted cancer treatment are ADCs. As of early 2023, 13 different ADCs have been approved for clinical use in managing hematological and solid tumor cancers, and there are many ADC agents that are being developed or are in pre-clinical testing. ADCs comprise of three distinct parts, i.e., an antibody molecule that is designed to target a specific tumor cell antigen, which is either over-expressed or highly prevalent in the target tumor micro-environment (TME); a ‘linker’ molecule that is designed to connect the antibody to the ‘payload’. The ‘payload’ usually consists of SMC agents that either disrupt DNA synthesis or mitotic activity of cells in the TME. ‘Linker’ molecules are pharmacologically inert and may be either cleavable or non-cleavable, The cleavable ‘linkers’ are broken down either by chemical or enzymatic processes after internalization into the tumor cell. Non-cleavable ‘linkers’ maintain the chemical bond with the SMC payload right up to deployment within the cell. The significance of the type of ‘linker’ for clinical efficacy and safety will be discussed in the next post. However, one unique feature of ADCs is that any number of SMC candidate ‘payload’ agents as well as other agents (for example, radioactive agents) can be ‘linked’ to the antibody scaffold or even on multiple sites on the antibody. The mechanism of action of ADCs is that the antibody latches onto cells in the TME and is internalized into the cell where the cytotoxic payload is released, killing the tumor cell. The versatility of the design of ADC agents allows ADC agents to be developed for other therapeutic areas. There are also Antibody-Antibiotic Conjugates being developed for infectious disease, as well as ADCs for the management of auto-immune disease. Needless to say, the potential market for ADCs is expected to grow substantially. With our work in Oncology, DataMed Solutions LLC is uniquely positioned to assist clients with their real-world evidence generation needs as well as health economic support in this exciting new area of cancer therapeutics. #targetedtherapy #antibodydrugconjugate #healthoutcomes Photo courtesy of Silvan Arnet via Unsplash

Metric
Company Name	Data Med Solutions	IOMED
Symbol
MSH ID	COM:DATAMEDSOLUTIONS	HEALTH:IOMED
Market	PRIVATE	PRIVATE
Sector	Healthcare & Health Services	Healthcare & Health Services
Industry	Health Economics	Health Technology
Country	US	ES
Stage
Employee Count
Website	datamedsolutions.com	iomed.health
LinkedIn	datamed-solutions	iomed
Founders

Metric
Market Cap
Enterprise Value
Monthly Web Traffic	311
Web Traffic Growth	2.70
Valuation
Raised Capital		1.08M

Metric
Revenue
Revenue (LTM)
Revenue (NTM)
Gross Profit
EBITDA
Operating Income
Net Income
EPS
Diluted EPS
Revenue 2022
Revenue 2023
Revenue 2024
Revenue 2025
Revenue 2026

Metric
Revenue Growth (LTM)
Revenue Growth (NTM)
Gross Profit Growth (LTM)
EBITDA Growth (LTM)
Net Income Growth (LTM)
14-Day Growth Score
28-Day Growth Score
90-Day Growth Score
365-Day Growth Score

Metric
Gross Profit Margin
Operating Profit Margin
EBITDA Margin
Net Profit Margin
Return on Equity
Return on Assets
Return on Capital Employed

DATA

COM:DATAMEDSOLUTIONS

Data Med Solutions

Company Overview

Market Metrics

Financial Performance

Growth Metrics

Profitability Ratios

Valuation Multiples

Operational Metrics

Cash Flow Metrics

Balance Sheet Metrics

Efficiency Metrics

Metric
P/E Ratio
P/B Ratio
Revenue Multiple (LTM)
Revenue Multiple (NTM)
EBITDA Multiple (LTM)
EBITDA Multiple (NTM)
Price to Sales Ratio
EV Multiple

Metric
Days Sales Outstanding
Days Payables Outstanding
Days Inventory Outstanding
Operating Cycle
Cash Conversion Cycle
Asset Turnover

Metric
Operating Cash Flow
Free Cash Flow
Cash Flow to Debt
Operating Cash Flow/Sales
Free Cash Flow Yield

Metric
Cash & Equivalents
Accounts Receivable
Inventory
Goodwill
Debt to Capitalization
Debt to Assets
Current Ratio
Quick Ratio

Metric
Rule of 40 (LTM)
Rule of 40 (NTM)
Stock Comp to Revenue
R&D to Revenue
SG&A to Revenue