With the major part of the US healthcare spending going towards a small share of the US population, healthcare providers have a serious issue on their hands. In 2019, 5% of Americans accounted for half of the overall healthcare expenditures, Peterson-KFF reports. The main reason for this disproportion is the lack of focus on patients with chronic conditions, which results in ill-timed interventions and increased readmission rates.

While there is no shortage of data or solutions that can be applied to solving this challenge, the hardest part is making this data actionable. However, a recent economic study by Medtronic has proven that predictive analytics and modeling could help a median-sized US hospital save over $500K annually by delivering actionable insights automatically. This is why more and more medical providers are turning to predictive analytics consulting and predictive modeling to promote disease prevention and consequently reduce healthcare expenses.

What is predictive modeling in healthcare?

Predictive modeling uses data mining, machine learning, and statistics to identify patterns in data and recognize the chance of particular outcomes occurring. To build an accurate predictive model, developers first define the problem and collect data. For most analytical goals, a combination of clinical data and claims is used.

Each model is created with a range of predictor variables that affect future results. The model can use a simple linear equation or a complex neural network to perform advanced tasks. Data analysts run and assess different models to solve the defined problem. After the assessment, the model with the highest score is validated, tested, and run against a real-world dataset.

Here is an example of how predictive modeling assists physicians: a patient of certain race, age, medical history and genetics presents herself at a hospital with a newly diagnosed condition. The predictive model considers the new condition and all the patient-specific data mentioned above, while looking at the population cohort with similar characteristics to develop a treatment plan tailored to this particular patient. This plan is then presented to the attending physician for approval, exemplifying the use of big data in precision medicine.

Predictive modeling applications in healthcare

Employing predictive modeling helps doctors, support staff, and financial departments receive alerts about potential outcomes and risks, so that they are better prepared for the future. Below are some predictive modeling examples in healthcare.

1. Avoiding readmission

According to Medicare’s Hospital Readmission Reduction program, healthcare organizations are subject to penalties in case of patient readmission within 30 days after receiving care. Therefore, avoiding readmission will not only improve patient satisfaction but also save providers money.

Predictive analytics can identify patients with a high risk of readmission after a particular treatment. Predictive analytical tools can explain what exactly puts patients into this high-risk group and advise doctors on the time of a follow-up visit and optimal discharge instructions to avoid readmission.

Additionally, predictive analytics can incorporate social factors determining a patient’s health. When the social factors are considered, it becomes easier to understand when patients might not adhere to their prescribed care plans.

Having [social] challenges makes it much harder for people to be able to properly focus on their health. The science of predictive analytics is beginning to develop algorithms to track who these individuals may be and respond with carefully customized ways of reaching them to help them on their health journeys.

Rich Temple

Vice President, Chief Information Officer at Deborah Heart and Lung Center

UnityPoint Health, a network of healthcare organizations based in Iowa, has reduced readmissions by 40% within 1.5 years of using predictive analytics. In one example, their home health team used predictive analytics to understand which patients became most vulnerable when the city was hit by a blizzard. This helped them focus their attention on particular individuals and reduce hospital visits.

2. Preventing suicide and self-harm

Identifying patients who are likely to harm themselves gives the opportunity to offer mental health care, which can hopefully prevent events of self-harm and suicide.

Kaiser Permanente together with the Mental Health Research Network used predictive modeling along with the EHR and a standard questionnaire on depression to identify patients who were at high risk of attempting suicide. They have discovered that suicide attempts were 200 times more likely among the 1% of patients flagged as high-risk by the algorithm. It should be noted that applying predictive modeling requires larger computational capacity, so the company should have performed EHR migration before implementing the technology.

3. Developing precision medicine and estimating a patient’s reaction

Medical researchers are turning to predictive modeling and analytics to supplement the traditional clinical processes. One interesting usage is adoption of predictive modeling for “in silico” testing. It involves importing an extensive number of patient-specific geometrics to a computer and using those for modeling the impact of therapies on patients. This is a promising way to evaluate new therapies without the need to recruit patients.

This method is now used in clinial trial management software for trial simulations related to degenerative conditions such as Alzheimer and Parkinson’s disease.

FDA’s Center for Drug Evaluation and Research (CDER) is currently using modeling and simulation to predict clinical outcomes, inform clinical trial designs, support evidence of effectiveness, optimize dosing, predict product safety, and evaluate potential adverse event mechanisms.

Scott Gottlieb

MD, Former Food and Drug Administration (FDA) Commissioner

4. Enhancing clinical decision support

Another common use case for predictive modeling in healthcare is clinical decision support, where predictive models are applied to help clinicians make better decisions about patient care. 

Predictive models help identify patients who are at risk of developing certain conditions and then recommend treatment plans and predict their outcomes. These tools can also help doctors identify patients who may have a risk of adverse drug reactions. 

As chronic diseases are the key reasons for exorbitant healthcare spending, providers strive to prevent the unplanned deterioration of patients with chronic conditions. Applying predictive modeling, doctors from Intermountain Healthcare, Salt Lake City, Utah, managed to assign risk scores to their patients with chronic obstructive pulmonary disease (COPD). The risk scores called LIVE took into account blood tests and an array of parameters that could signal other conditions in COPD patients. Such a detailed patient profile allowed clinicians to make timely and grounded decisions regarding patient treatment, hospitalizations, transferring to palliative care, and allocating wards and resources, thus improving the quality of care.

5. Streamlining inventory management

Due to the size and complexity of modern hospitals and their services, hospital inventory management has grown more complex. But with predictive analytics tools in place, clinicians can discover certain trends in resource allocations and foresee the facility’s upcoming needs. This can enable healthcare administrators to buy the required medical goods or relocate them right on time to prevent stockouts.

Besides, hospitals can employ predictive analytics for determining what resources are prone to be out-of-stock faster than others relying on trends among the population or seasonal needs. With the help of predictive modeling tools in healthcare, healthcare organizations can better understand their intricate supply requirements and find ways to save money and reduce waste.

6. Improving patient engagement

Predictive analytics offers healthcare providers a better view of patients and their needs. Community Health Network from Indianapolis, Indiana, provides one of the best examples of predictive modeling in healthcare with the clinic managing to reduce the level of no-shows using a smart predictive algorithm. To have no-show risk patients confirm their appointment, the team employed a three-step notification process:

1. A text message to confirm the visit
2. A personalized outreach
3. A call from administrators

A technology of this kind can predict patients’ behavior in terms of following their treatments. It can also pinpoint which interventions or healthcare messages would resonate with certain patients or patient populations. With the help of this information, providers can design patient engagement strategies, upscale the efficiency of their work with patients, and improve their health outcomes.

Looking to upscale decision-making in your clinic?

Add healthcare analytics solutions to your digital mix

Contact us

Predictive analytics: step-by-step adoption guide

The HIMSS Analytics Adoption Model for Analytics Maturity (AMAM) and the Healthcare Analytics Adoption Model by HealthCatalyst are two similar models that introduce a step-by-step roadmap for adopting analytics at healthcare organizations.

Healthcare analytics adoption model

Level 8	Personalized medicine & prescriptive analytics	Tailoring patient care based on population outcomes and genetic data. Fee-for-quality rewards for health maintenance
Level 7	Clinical risk intervention & predictive analytics	Organizational intervention processes are supported with predictive risk models. Fee-for-quality includes fixed per capita payment
Level 6	Population health management & suggestive analytics	Tailoring patient care based on population metrics. Fee-for-quality includes bundled per case payment
Level 5	Waste & care variability reduction	Reducing variability in care processes. Focusing on internal optimization and waste reduction
Level 4	Automated external reporting	Efficient, consistent production of reports and adaptability to changing requirements
Level 3	Automated internal reporting	Efficient, consistent production of reports and widespread availability in the organization
Level 2	Standartized vocabulary & patient registries	Relating and organizing the core data content
Level 1	Enterprise data warehouse	Collecting and integrating the core data content
Level 0	Fragmented point solutions	Inefficient, inconsistent versions of the truth. Cumbersome internal and external reporting

But how exactly can providers adopt predictive modeling tools in healthcare and fit them into the standard practice? We offer an easy-to-follow guide.

Step #1: Assess your data

The quality of predictions analytics tools provide highly depends on the quality of data users “feed” the solution. However, data in the clinical setting commonly has several flaws, which may hamper quality of analytics:

• The data comes from various sources, and these records are not always interoperable. So, it is important to understand the limitations and possibilities of heterogeneous data in predictive modeling.
• Clinical data may be unstructured because some providers write examination notes on paper and then transfer them into EHRs as plain text, while others might just skip some fields. This data variability may significantly hinder further analysis.
• If the data was gathered outside the hospital, it’s likely to be fragmented because healthcare organizations either use patient-submitted surveys at specific time intervals or gather health status information during follow-up appointments. To solve this problem, providers can turn to the internet of medical things and patient-generated data (PGHD) managed via mobile health solutions.

So, before starting a predictive modeling project, the healthcare provider’s team needs to perform data cleaning, which they can accomplish by seeking data management services.

Step #2: Ask the right questions

At this stage, data analytics experts and stakeholders discuss the existing challenges predictive modeling may help resolve. It is critical that the two parties approve a challenge to deal with, making it a top priority.

Then the teams can discuss other important aspects:

• Data to be used
• Resource availability
• Business or clinical value

Step #3: Set off

At this point, data analytics specialists determine valid use cases for AI-driven modeling and examine the selected data quality, its quantity, and its suitability for solving the appointed issue.

Step #4: Develop the model

Next, developers proceed with creating the model. Throughout the predictive model development, data analytics experts can require additional data, and in this case, the team needs to go back to square one and go over relevant questions.

At times, it’s not new data that is needed but a different perspective. This different focus can actually change the way the algorithm predicts potential outcomes. For instance, a team can review the data on diagnosis and treatment in separate groups instead of examining it individually.

Step #5: Launch the predictive model

The second-to-last step of the offered framework involves launching the model in the hospital environment. The teams need to refocus on the results the model produces and assess its accuracy and potential applications.

Step #6: Ensure continuity

The work doesn’t stop at predictive model implementation. As the landscape changes, healthcare predictive modeling tools can gradually stop producing actionable insights.

This is why healthcare providers need to regularly seek out IT specialists’ help for mapping workflows, detecting improvement opportunities, and updating the existing algorithm.

Launch predictive modeling with Itransition

Healthcare data analytics

Our engineers are ready to develop tailored healthcare data analytics solutions to help you gain valuable insights from your medical big data.

Predictive analytics: adoption challenges

When deciding on whether to adopt predictive modeling, healthcare organizations should consider these potential challenges:

1. Technology

Technology presents a pool of numerous issues when it comes to setting up clinical systems, workflows, and environments. Providers need to enable seamless integration between all their systems, including EHR, CRM, LIS, RIS, and more, to ensure uninterrupted and correct data aggregation. The integration is also a critical step for enabling healthcare digital transformation across all provider’s facilities.

Both structured and unstructured data need to be leveraged, which implies further challenges associated with NLP in healthcare and possible data errors. To make results immediately comprehensible for all stakeholders, data should be properly visualized, with summaries and automatically generated insights for each prediction.

2. Security

Data privacy remains a concern, especially when it comes to collaboration between organizations or data exchange within one health system. Besides, population health management studies require data anonymization to be safely used by any organization.

To retain the utility of collected data for predictive modeling while complying with the HIPAA regulations, providers need to invest in information security assurance.

With expert assistance from vendors, providers can let go of many issues related to technology and security, but it will take a certain commitment from the organization itself to engage decision-makers and health specialists in predicting outcomes and acting on them.

3. People

Predictive modeling can’t be of practical use in a vacuum. Health specialists are indispensable from this equation, because it is them who take part in the workflows, input data, and offer clinical experience to interpret predictions more accurately.

For the long-term success of predictive modeling at a healthcare organization, all these issues should be addressed by providers and technology enablers.

Despite challenges, predictive modeling is worth the effort

The value-based approach to healthcare encourages organizations to start using predictive analytics for developing personalized treatment plans, reducing readmissions, and generally improving health outcomes. There are additional benefits on the way, including more data-driven clinical workflows, optimized facility administration, more transparent supply chains, and cost-effective decisions.

However, predictive modeling adoption comes with its challenges. In addition to technology- and data-related challenges presented above, there is a moral challenge in identifying a reasonable point of human intervention. More precisely, predictive analytics predicts which treatment is most suited for a particular patient, as accurately as the algorithm can. But it is up to the human doctor to review those predictions and decide whether to act upon them or make an adjustment. Doctors should not just shift the responsibility to algorithms. They need to know when to interfere.

Despite all the challenges, though, the value delivered by predictive analytics is immense. This technology is worth your investment if you possess the data required for its operation, and if you are aware of the challenges and prepared to tackle them proactively.