Monthly Archives September 2013

Predicting Product Demand: Leveraging an Integrated Approach

The analytics team at Snowfish has worked with multiple life science companies helping identify patterns in large quantities of data. As part of our offerings we have assisted companies in demand planning. Predicting and planning for demand is a common and critical challenge pharmaceutical companies confront. Multiple factors can affect demand including the product category and exogenous events. Demand for products such as flu vaccine varies tremendously from year to year depending on the severity of the flu that year and the amount of media coverage. Demand for allergy therapies is highly seasonal. Furthermore, the seasonality may differ by geographic region and may in fact vary in the same region from year to year depending upon weather patterns. Variation in demand may even be evident at the individual physician level for infrequently prescribed therapies such as oncology where treatment regimens can vary significantly. Therefore, predicting demand for the overall market, individual products, and individual physicians can be particularly challenging.

The Right Approach is Critical
In all cases, it is important to first pick an approach that is most appropriate for the challenge. It is all-too-tempting to throw all of your data into an algorithm without first analyzing the nuances of the situation. If seasonality is a major concern, then it will be necessary to first discover seasonality trends in past years. Keep in mind that those trends may shift in time and magnitude from one year to the next and may even vary depending on geographic region within a single year. Once seasonal trends are identified, the next step is to see how they fit the current year in both timing and magnitude. In some years the flu may peak early, and in other years it may peak late. How this year fits past trends can be used to predict the next several weeks.

For infrequently prescribed medicines, it may be necessary to simply predict the probability that a particular physician is going to prescribe at all in the next three, six, or twelve months. Such predictors include whether the physician has ever prescribed a particular medicine in the past, how recently, and their overall level of prescribing of all related drugs. For new products, it is helpful to determine if certain physicians have been early adopters of other therapies when they were new. A physician that lagged his peers in the past in prescribing new medicines is likely to lag on future new products even if he eventually ends up being a high-volume customer. Likewise, if a physician has been an early adopter in the past, this increases his chances of being a leader in prescribing new products.

Data Is Often Incomplete: Do Not Rely on a Single Data Source
Incomplete and/or incorrect data are limitations that are going to negatively impact any technique. Certain sales channels may not be reported to data vendors. This tends to occur when a certain prescription is processed through an unreported channel. Demographic data about the geographic area where a physician practices while very helpful when available may be incomplete for certain regions. Therefore, it is important to include data from multiple sources such as internal sales data, prescriptions of competitors’ products, diagnostic codes, etc. With multiple data sources, problems with any one source are less likely to have a major impact.

Use the Right Tools and Integrate Them
Approaches that integrate analytical skills, clinical knowledge, and business acumen yield the best results. It is helpful to use the latest analytical tools such as Gradient Boosting, Random Forests, and Support Vector Machines as well as more traditional tools such as linear regression. Additionally, clinical knowledge is crucial for understanding the disease state the medicine treats. How long does typical treatment last? Is the therapy used to treat multiple different diseases? How is it administered? Clinical knowledge affords the necessary background for data selection and creation of features for predictive statistical analysis. Finally, business knowledge of outside factors that drive demand and purchasing decisions also should also be incorporated into data selection and feature creation.
Using an integrated approach to predicting product uptake and demand not only increases prediction accuracy, it also yields better insights into your data. Trends that might have just been lost in the shuffle of statistical analysis might jump out at a team member with clinical knowledge of the disease state or business knowledge of the market. When pharmaceutical companies face the challenges of predicting product uptake and demand, integrating analytical, clinical, and business skills into the team is the key to addressing those challenges.

Please feel free to reach out to Snowfish to learn more about our integrated approach to predicting demand. Companies are already benefiting from our insights.
David Fishman is President of Snowfish, LLC a strategic consulting firm which works exclusively in the life sciences industry. For more information, please check out

Posted by Dave Fishman  |  Comments Off on Predicting Product Demand: Leveraging an Integrated Approach  |  in Management Consulting

Personalized Medicine, What’s the Future?

Personalized medicine is currently one of the hottest areas in life sciences, imparting significant levels of excitement among venture capitalists, life science companies, clinicians and patients. It even has its own journal that “translates recent genomic, genetic and proteomic advances into the clinical context.” As Snowfish has had the privilege of working with genomics companies, we have heard firsthand the potential impact these new technologies will have on the way patients are treated and how the industry does business.

In brief, personalized medicine refers to the customizing of medical treatment to the individual characteristics of each patient. Contrary to a common perception, it does not refer to the creation of drugs or medical devices that are unique to a patient but rather, the ability to classify individuals into subpopulations that differ in their susceptibility to a particular disease or their response to a specific treatment. This information ensures that interventions are targeted only to those who will benefit, thus sparing expense and side effects for those who will not.

Most medical professionals will concur with the fact that patient response to both disease and therapeutic intervention are highly variable. It is not uncommon for one patient to respond beautifully and tolerate a drug without incident and another to experience side effects while obtaining no benefit. Depending on the source it has been documented that 30% to 70% of patients fail to respond to a drug treatment. There is a variety of potential reasons including adherence, and even misdiagnosis. Still, it seems highly probable that patient-specific factors such as variability in drug metabolism rates, the metabolic or genetic nature of the underlying disease, and other characteristics such as age are also contributing factors. Enter personalized medicine.

Oncology is where personalized medicine appears to making the greatest amount of headway. This makes sense as treatment response rates in cancer are amongst the lowest for any major disease. The well-established genomic basis of cancer has put cancer research at the forefront of personalized medicine in the quest for more targeted and tolerable therapies. Early examples of success are Herceptin in breast cancer and Gleevec in chronic myeloid leukemia (CML).

Various technologies are being employed in the effort to more effectively guide the treatment strategy based on the likelihood that the cancer will recur or metastasize. For example, the clear molecular differences seen in breast cancer are highly applicable to genomic profiling, and through transcriptional profiling approaches, several prognostic and predictive assays have been developed. Prominent amongst these is Genetic Health’s Oncotype Dx, a 21 gene polymerase chain reaction (PCR) panel that predicts tumor recurrence at ten years in estrogen-receptor (ER)-positive, node-negative breast cancer patients receiving tamoxifen therapy. [1] Using a statistically defined algorithm, the gene expression profile is used to define a recurrence score that can be used to identify patients who are likely to benefit from additional adjuvant therapy. Patients with low recurrence scores and, therefore, good prognosis are spared the stress and risk of unnecessary therapy, and the healthcare system saves the costs of delivering additional treatment. The assay has been endorsed by both the Association of Clinical Oncologists (ASCO) and the National Comprehensive Cancer Network.

Although it is one of the first, and certainly the one of the most successful to date, it is already clear that Oncotype Dx is merely the tip of the iceberg. In breast cancer alone, we have seen the emergence of multi-analyte tests based on techniques as broad as PCR, microarray, immunohistochemistry and fluorescent in situ hybridization, amongst others. Genomic Health is also expanding the use of their assay in breast cancer as well as developing similar prognostic test for colon cancer, prostate cancer, non-small cell lung cancer, melanoma, and renal cancer.

One of the main obstacles to the growth of personalized medicine has been cost. Until very recently the devices used for genome sequencing cost $500,000 to $750,000. Additionally, the individual tests run $5,000 to $10,000 and take days to produce results. Things are changing though. Just this past year, Life Technologies introduced an Ion Proton™ Sequencer that is designed to sequence the entire human genome in a day for $1,000 and the machine costs $149,000. Clearly, the barriers to affordability are breaking down. It is not hard to imagine that the cost of a complete genomic testing will be a few hundred dollars within a few years. [2]

In order to realize the full potential of personalized medicine, engagement of multiple stakeholders is critical. Payers will need to be convinced of the clear benefits of specific genetic tests. As companion diagnostics are critical to development and utilization of therapies, the Federal Drug Administration (FDA) will need to promulgate clear and straightforward paths for diagnostic approvals. Clinicians will need to modify existing treatment regimens and include genetic testing as a core component and feel confident to withhold standard therapies when genetic testing indicates that these treatments are ineffective or no more effective than watchful waiting. Treatment guidelines will require modification in order to account for the genetic makeup of patient populations. Life science companies will have to develop a new mindset; where the goal is not the single multi-billion dollar blockbuster but rather a portfolio of more products which treat smaller populations. That said there could even be the potential to review the “shelves” of failed products to determine if there could be success with a more appropriate genotype or phenotype.

Personalized medicine is upon us and it will completely revolutionize how treatment is determined. Today, clinicians choose therapies based on research done on thousands of people that have a diverse genetic profile and have only a limited ability to adjust therapy based on individual differences. In the case of cancer, treatment is currently based upon the tumor location.

In the future, the tumor itself will be tested and it will be based less on the location than on its genetic and molecular composition. Genomic testing will be able to identify which oncogenes are turned on and which oncogenes are turned off. Most importantly, clinicians will be better able to identify the drugs and treatments that will yield the greatest benefit to the patient.

We will eventually see this type of therapy for all human illness and will likely have access to tests that will portend the future and enable patients to avoid developing conditions such as diabetes, heart disease, and various types of cancer.
1. Paik, S. et al. A multigene assay to predict recurrence of tamoxifen-treated, node-negative breast cancer. N Engl J Med 2004.351; 2817-2826.

Dave Fishman is President of Snowfish, LLC a strategic consulting firm which specializes in helping life sciences companies by using data to address the most challenging issues. More information on Snowfish may be found at or by emailing us at

Posted by Dave Fishman  |  1 Comment  |  in Management Consulting