Data quality issues plague the U.S. healthcare system

Oleg Bess, MD, explains why data quality is essential to improving the United States healthcare system.

Data quality is critical to improving the United States health care system. But what is data quality? Fundamentally, it’s about extracting value for patients, clinicians, and payers. High-quality data is both usable and actionable, while low-quality data, such as duplicate records, missing patient names, or out-of-date information, creates barriers to healthcare delivery and problems with healthcare. billing / payment. These inefficiencies result in monetary losses throughout the health care system.

Unfortunately, healthcare has lagged behind virtually every other industry in harnessing data for strategic and operational advantage. It’s not for lack of data: more patient health data is captured by medical equipment, digital devices and apps today than ever before. If data is gold, the healthcare industry sits on top of a gold mine.

In general, the industry has done a poor job of extracting and refining this data gold ore to the point of being useful. This is a lost opportunity as quality data would add value to all healthcare stakeholders including hospitals, payers, healthcare information exchanges, laboratories and patients .

Effect on research, patient outcomes

Poor data quality has negative ramifications across health care. The way we market new drugs is a case in point. The first phase is to identify and develop the drug, a process that represents less than 20% of the cost of developing the drug. Next come clinical trials, which account for most of the drug development costs.

Clinical trials are long and arduous. Worse, from a data quality perspective, the data is still collected on paper, transferred to computer, and usually not combined with other datasets for similar patient types or even other patients in this trial. clinical. If all of this information were readily available and automated, clinical trials would cost less than 10% of what they currently do.

In clinical practice, there is a significant lack of aggregate patient data, leaving clinicians with only part of a patient’s story. Additionally, when a physician sees a patient in hospital, they need the patient’s outpatient records to make informed, evidence-based decisions about appropriate treatment. In far too many cases, however, the data that would inform point-of-care clinicians is trapped in silos scattered across the healthcare landscape.

Healthcare has not taken advantage of advanced digital technologies like artificial intelligence (AI) and machine learning, which are being used to transform many other industries. In large part, this is because these tools are not accessible or the quality of health data is so poor that smart machines would have a hard time processing and analyzing it to gain actionable insights into patient care. .

In contrast, access to quality healthcare data would create scenarios in which AI and machine learning can quickly provide clinicians with point-of-care information to inform patients about their health. specific condition, provide referrals to appropriate specialists, suggest new drugs, and improve outcomes. With the right data and the right ideas, clinicians may be able to involve the patient in a clinical trial that could save the patient’s life.

Poor quality data is also a problem for payers as they need the data to make decisions, regardless of the condition. Data collection begins when a patient is diagnosed, but the payer may not be notified for weeks. So, for example, a patient diagnosed with cancer may suddenly have to find a specialist and determine if the practice is taking out insurance.

However, if a payer immediately finds out that this patient has cancer, they can help guide the patient to the right provider, alleviating some of the burden of financial problems associated with medical treatment.

Improve data quality

There are 3 main steps to get high quality data. The first is to ensure access to the data the clinician needs. There are still many legacy systems in healthcare, which host most medical records on an organization’s servers and not on a cloud platform, where they could be more easily accessed and aggregated by authorized users. . While interoperability and data sharing has improved in the healthcare environment in recent years, integrations are being built one at a time. Bringing the data together in a central database, where that information can be turned into gold, remains a challenge.

The next step concerns identity management. Much of the value of health data comes from the ability to document longitudinal changes in individual patients. Clinicians, for example, may want to see how drugs affect lab results for a particular patient. Even though they could connect disparate data sources and have the data funnel in a single database, they cannot relate the data to a specific patient. With effective identity management, it is possible to create a longitudinal patient record which can provide enormous clinical benefits and efficiency.

The third phase of improving data quality is to make the data usable or actionable. Once the longitudinal record of precise patient data is created, it should be organized and easy for clinicians to locate and read. This requires a process called data normalization. Health data can come from multiple sources (i.e. electronic health records, laboratories, pharmacy systems, etc.), all of which may use different coding for a medical procedure, different terms for a certain test or even different language to categorize the sexes. Data standardization creates a common terminology that enables the semantic interoperability necessary to make data actionable.

There are no quick fixes to improving the quality of healthcare data. This will require a joint effort and the innovation inherent in the free market. There will be companies that help us collect and connect to data, and there will be companies and entities that help us connect with data. There will be technologies that identify data and others that standardize data, and there will be companies that provide quality databases that healthcare stakeholders can use to perform advanced analytics. The end result will be a health system that offers better care at lower cost.

Oleg Bess, MD, is CEO and co-founder of 4medica, which provides clinical data management and healthcare interoperability software and services.

Source link

Previous Fashionable copiers and hackers will be the bane of supply chain security in 2022
Next Photos of birds, insects and the bush: how you can help map New Zealand's biodiversity on your phone