People often find comfort in complacency, but growth stagnates when complacency takes over. For many years, Americans had much of the same experience with healthcare in the United States. A patient would visit a doctor and depending on their diagnosis, the doctor would prescribe medicine or some other type of treatment based on their symptoms. Days or a week later, they would go back to the doctor for a follow up visit. If better, the doctor would send them on their way, but if they still felt unwell, the doctor would order some tests and try another treatment until something worked. But with the recent introduction of precision medicine the healthcare landscape is changing. The future will be a new and better approach to healthcare based on each person’s unique genetic makeup, and their specific diseases taken in combination with myriad other factors such as secondary conditions, gender, and age.
So, what exactly is precision medicine?
Understanding Precision Medicine – The Next Generation of Healthcare
Precision medicine was implemented by former President Barack Obama as an approach for disease diagnosis, treatment and prevention. The model considers individual variability in genes, physiology, environmental exposures and lifestyle to create a model that proposes customization of healthcare, with medical decisions, practices or products being tailored specifically for an individual patient.
However, precision medicine hasn’t exactly evolved as expected. Instead, health networks are drawing on massive amounts of data from all of their patients and correlating that data to patients in a similar circumstance. To illustrate this admittedly complex undertaking with an extremely simplified scenario, consider the following. If a 55-year-old male weighing 180 pounds is diagnosed with colon cancer, his doctors could look at data about other 55-year-old men with the same diagnoses, and similar weight, to see which treatments worked best for those patients. The doctors could then create an individualized treatment plan based on what worked best for other patients with the same conditions.
Precision medicine has enormous potential to save lives, but if health systems are using incorrect data, it can have negative effects on the outcome. Clean and standardized data is critical to accurately implement precision medicine and a necessary first step in preparing the healthcare data for insights and analysis.
The Importance of Data Quality
Complicating things further is the consolidation of healthcare entities across the US. Health systems have vast networks that include physicians, hospitals, and other healthcare providers. This enables great care for patients because specialists are often readily accessible, but it complicates the data gathering process, as well as maintaining proper data quality. On a daily basis, these large health systems are treating hundreds of patients, generating valuable medical data at a rapid pace. All the data from these visits needs to be entered in to a system by a doctor, nurse, assistant, etc. With so much information, human errors are bound to occur. In addition, a provider can easily enter duplicate data, misspell words, use inconsistent data formats or include wrong data. Any incorrect information can significantly skew the results, potentially leading to a misdiagnosis or incomplete treatment plan. As providers across these systems enter this data into their patients’ electronic health records and claim files, immense volumes of data are being accrued and aggregated into a data lake or other big data environment. It is within these consolidated data environments where these quality issues may lurk undetected.
Keeping this in mind, let’s go back to our example of the 55-year-old male with colon cancer. His doctor is trying to correlate results to similar patients, but another 55-year-old male with colon cancer had his records entered six times. He was cured, but nobody caught this error. The healthcare provider is now basing his treatment plan on one individual, rather than six as originally thought, significantly driving down positive statistics. Those duplicates can cause a doctor to go with a completely different treatment plan than if the information was correct, the data was clean and there was only one record.
For better evaluation, health systems need a solution to ensure data quality and data cleaning of the information they’re using and to improve the diagnosis they’re recommending. So, what exactly should the health system be using when it comes to precision medicine?
To achieve enterprise-wide data quality across a healthcare network, a self-service data integrity suite designed to handle not one, but rather multiple steps from data acquisition and preparation, to data analysis and operationalization will help with more accurate information. The suite should enable users to source data from multiple data platforms and applications, including vendor products, external databases and big data environments such as data lakes.
The suite should sit on top of the healthcare networks’ data lake and continually monitor the data to ensure the bad data is immediately flagged and stopped before it could potentially have a negative impact on patient care. With a data integrity suite, you can implement business rules to ensure that when duplicate files are sent, an exception report will flag the discrepancy and the process will prevent the incorrect file from processing.
In addition, the suite should enable users to apply statistical and process controls, and artificial intelligence machine-learning algorithms for segmentation, classification, recommendation, regression and forecasting. This will allow healthcare providers to create individualized treatment plans for their patients that should work for them specifically.
To learn more about ensuring data quality for healthcare networks, download the eBook below.
For a deeper dive into this topic, visit our resource center. Here you will find a broad selection of content that represents the compiled wisdom, experience, and advice of our seasoned data experts and thought leaders.