Predictive Health Analytics

Go Deep with Predictive Health Analytics Using SQL, Python, and R

Between the digitization and storage of health records in the cloud and the rise of consumer health technology, the amount of healthcare data has skyrocketed in recent years. Analysts predict that the amount of health data will continue to increase as organizations move to join care provider information, prescription details, lab results, patient activity tracking and more on the same platform.

All of this data is certainly worth collecting, but only if there’s a cohesive strategy in place to connect those disparate data into a unified view of a patient’s health information, transforming that knowledge into insights and ultimately into healthier patients.

As one of the most data-heavy industries, healthcare is in a unique position to generate value from a wide and deep pool of data available for analysis. 

By allowing customers to utilize SQL, R, and Python together in their analyses, platforms for health analytics provide a way to go deep on data. Support for advanced languages allows health companies the ability to focus on the future and look for answers to questions that were previously considered too complicated to address.

These platforms have opened the doors for data scientists to explore deeper questions and it’s exciting to see how health technology customers will use these platforms to generate insights and make decisions. 

Thrown in some predictive analysis capabilities and you have a wide range of benefits for any and most health technology customers. Better yet, some Sisense customers are already taking advantage of these capabilities in inspiring new ways to operate more efficiently and create a better experience for their customers. Here’s a look at some of the ways predictive analytics can help companies in the healthcare industry:

Diving into Predictive Analysis for Healthcare 

With the advanced capabilities of R and Python, Sisense for Cloud Data Teams allows teams to build and test predictive machine learning models from their historical data. Once the models are tested, data teams can plug in today’s data to get a better idea of how the same KPI will change in the future. 

Internally, health companies can use this type of modeling to forecast demand for medical supplies, staffing needs and more. Strategy can be adjusted based on the predictions and the results can be measured to refine the model even more. These changes can help a health company operate more efficiently while ensuring that patients are still fully supported in their times of need. 

Externally, the same techniques can be applied to help minimize readmission, monitor patient traffic and improve customer communication. These predictive models can use large databases of patient information to find patterns among similar patients and recommend preventative care. As companies hone these predictive models, they’ll use their knowledge of customer needs to operate more efficiently. More importantly, they can shift their patient focus to preventative care, which will result in better overall health and lower costs.

Predicting Complex User Behaviors 

The health insurance market is complicated, connecting patients to multiple different medical facilities, treatment providers, labs, care providers and more. New York’s Oscar Health is building a single system to track all of that and uses our analytics platform to unify all of their data in one place. This allows the team to eliminate traditional silos and create data-based insights that are valuable for the entire company. 

By unifying their data, Oscar Health has been able to satisfy their reporting needs across the company and move on to more complex questions about their members. Specifically, Oscar Health’s data team has focused on using the scripting powers of Python to develop a deeper understanding of their customers through data. The goal is to identify trends within specific user cohorts that can accurately identify complex behavior patterns and predict future usage of their product. This allows Oscar to provide better care for their customers and manage internal processes much more efficiently. 

These complex predictive dashboards have been made available to members across the organization, instilling a culture of data-based decisions. As the company scales, more teams are interested in and dive into data to find insights to drive their decisions. The flexibility of the platform means any team at Oscar Health can create dashboards quickly and investigate data for any question.

Saving Lives with Predictive Modeling 

One of the most effective trailblazers in the field of predictive analytics is Crisis Text Line, a free, anonymous 24/7 text-based crisis intervention system that aims to mitigate crises by connecting people to counselors who are trained to cool down hot moments. Crisis Text Line uses Sisense for Cloud Data Teams to analyze text conversations in real-time. They use natural language processing and machine learning to pull insights from their rich data set and identify keywords in texts to help steer a counselor toward safe resolution. 

This innovative approach to predictive modeling allows the Crisis Text Line to detect keywords that identify trends in real-time. This augments counselors’ conversational abilities and gives them the peace of mind that they aren’t alone. While advanced analytics are valued for their assistance, it is important to the organization that they don’t replace human volunteers with automated responses.

The Crisis Text Line data team uses Sisense for Cloud Data Teams to conduct this complex analysis and quickly visualize the results. In the near future, the team plans to set up a self-service data environment that will empower counselors to access information without help from the data team. This setup would give counselors quicker access to data and ultimately lead to better-informed conversations with texters. Often, the end-user save difficulty predicting the needs of texters ahead of time, so a data tool that relies on upfront modeling is ineffective. An agile data environment allows the team of counselors to find answers on their own. 

Sisense for Cloud Data Teams has helped the Crisis Text Line team scale significantly in the past year and there are plans to more than double the number of volunteers and conversations again over the next two years. By empowering more end-user so access advanced analytics dashboards, the service can rely on counselors to find more answers on their own and give texters a better experience as the team grows.


Predictive analytics is still young and there will be huge improvements in the field in the coming years. At Sisense, we want our customers on the front lines of those innovations, using advanced analytics to improve operational efficiency and the customer experience in ways that were previously not possible. We’re inspired by the stories of some of our current customers and look forward to empowering the next generation of forward-looking health technology providers to proactively care for their patients. 

If you want to see how predictive analytics can move your company forward, set up a free trial, watch a demo, or talk to one of our experts about how your data team can implement predictive models in your company:

Watch a Demo Start a Trial