The Healthcare System of Tomorrow: How Advanced Analytics is Evolving Patient Care and Cybersecurity

At healthcare organizations, data sets are growing fast, both in volume and complexity, as the types and sources of data continue to multiply. Thirty percent of the world’s data is already estimated to be healthcare data1, and in the U.S. many hospitals gather over 100 data points per patient per day2.

However, simply creating vast data pools doesn’t automatically translate into better care. That’s where advanced analytics comes in—and its application in healthcare is growing at a rapid rate.

Advanced analytics enables healthcare organizations to manage, process, and use their data in new ways for unparalleled insights. Offering capabilities such as predictive models and automated decision support, it enables clinicians to achieve everything from more efficient patient care through real-time monitoring and personalized results, to more effective mitigation of cybersecurity risks.

At Intel, we work with a number of healthcare organizations who are using advanced analytics to transform their patient care and protect their patients’ personal information. Here are three best-practice case studies of advanced analytics success.

 

Delivering Care Sooner with the Semantic Data Lake

One New York-based healthcare system has deployed an advanced analytics solution, Semantic Data Lake, to automate and accelerate its ability to identify high-risk patients in need of critical, time-sensitive intervention.

Semantic Data Lake leverages multiple data formats and sources–including clinician data, behavioral insights, wellness research findings, population demographics, and even medical images—to create realistic, holistic profiles of patients. Advanced analytics algorithms then generate insights on these profiles, and the insights are optimized over time through machine learning capabilities.

The solution is built on the Intel® Xeon® processor E5-2690 v3 with Cloudera’s Hadoop* distribution and Franz’s AllegroGraph*, a high-performance semantic graph database. Through its ability to stream and mine data in near real-time and at scale, the healthcare system can identify patients at risk for respiratory failure 24 to 48 hours in advance, with high levels of sensitivity and specificity3. Physicians are consequently able to better prevent fatal episodes or respiratory failure.

 

Driving Real-time Clinical Interventions with Predictive Analytics

By loading its electronic medical record data into a Cloudera* cluster powered by the Intel® Xeon® processor E5 v4 family, one specialized rapid response team at a different healthcare provider has been able to develop a predictive model that can identify patients at risk for requiring clinical intervention within a defined period of time.

The solution analyzes a range of data including blood pressure, temperature, and pulse rate, and uses machine learning to train the algorithm over time.

When the proof-of-concept model was tested against historical data, it was found to be 80 percent accurate in predicting the likelihood of a rapid response team event within the next hour.4  The model has therefore enabled the team to optimize real-time clinical interventions, improving its resource utilization and bettering its patient care outcomes.

 

Helping to Protect Connected Devices from Cyber-attacks with Artificial Intelligence

Faced with sophisticated unknown malware and zero-day attacks threatening its operations, a large multisite healthcare system wanted to use advanced analytics to improve its cybersecurity capabilities.

It chose to deploy the Cybraics nLighten* platform, which combines artificial intelligence (AI) and advanced security analytics to scan for threats, vulnerabilities, infections, and targeted attacks. The platform runs on the Cloudera Enterprise Data Hub* and is powered by the Intel® Xeon® processor E5-2650 v4 and Intel® Solid State Drive Data Center S3500 Series with Non-Volatile Memory Express* support.

The nLighten analytics solution has enabled the healthcare system’s IT department to detect and resolve dangerous medical device and ransomware infections. This solution has also helped to detect vulnerable systems and employees, enabling proactive remediation. These in turn have helped mitigate risk of disruptive and costly breaches, helping to safeguard patient safety, privacy, and the organization’s reputation.

Find out more about how advanced analytics is transforming healthcare and other industries by reading Intel’s new cross-sector eBook on the Business Impact of Advanced Analytics.

1 Tech's Next Big Wave: Big Data Meets Biology, Fortune 2018 http://fortune.com/2018/03/19/big-data-digital-health-tech/

2 Montefiore Creates Data Analytics Platform to Advance Patient Care, Intel 2017, p.1 https://www.intel.com/content/www/us/en/healthcare-it/solutions/documents/montefiore-advance-patient-care-solution-brief.html

3 Intel and Partners Come Together to Solve Healthcare, Intel 2018 https://newsroom.intel.com/editorials/intel-partners-come-together-solve-healthcare/

4 80-percent accuracy indicates the level of accuracy observed when scoring a set of unlabeled test data that was not used in the development of the model. Using Machine Learning and EMR Data to Predict Patient Decline, Intel 2017, p.1 https://www.intel.com/content/www/us/en/healthcare-it/solutions/documents/using-machine-learning-and-emr-data-to-predict-patient-decline-case-study.html

Intel® technologies' features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration. No computer system can be absolutely secure. Check with your system manufacturer or retailer or learn more at https://www.intel.com.

Software and workloads used in performance tests may have been optimized for performance only on Intel® microprocessors. Performance tests, such as SYSmark* and MobileMark*, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more information go to http://www.intel.com/benchmarks.

Estimated results were obtained prior to implementation of recent software patches and firmware updates intended to address exploits referred to as "Spectre" and "Meltdown". Implementation of these updates may make these results inapplicable to your device or system.

All information provided here is subject to change without notice. Contact your Intel representative to obtain the latest Intel product specifications and roadmaps.