Chris George, Co-Founder & CEO, QubeHealth shares his views on digital healthcare
The pandemic has been a powerful catalyst in driving innovations in healthcare. From telehealth, to remote healthcare management through smart devices and more. Health IT adoption skyrocketed post-pandemic as patients, hospitals, and healthcare systems increasingly relied on digital health technologies for healthcare access and delivery, setting the stage for exponential growth and innovation in 2021 and beyond.
The post-pandemic reality
A McKinsey report states that telehealth usage rose 38X during this time. For instance, an Italian hospital deployed robot-nurses to remotely monitor patients’ oxygen saturation levels and blood pressure during the overwhelming hours of the Covid-19 outbreak.
Israel’s Sheba Medical Centre joined hands with TytoCare to treat Covid-19 patients remotely by equipping them with custom-built stethoscopes capable of transmitting relevant data to a care team ready to intervene when required.
Another vertical disrupted by the pandemic is the pharmaceutical industry, where their representatives were fully or partly moved off the field and turned to virtual interaction representatives. In China, over 70% of medical tech companies plan to adopt a hybrid, online-offline sales mechanism.
Capturing value from health data
Health data has long been ripe for innovation through predictive analytics. Due to continuous monitoring with smart wearables, clinical trials, claims, patient-reported medical data, availability of new-age technologies for DNA sequencing, patient-reported social media data, and more, by 2020, the amount of healthcare data has grown to 25,000 petabytes. The global healthcare big data analytics market will witness a steep rise at a CAGR of 12.5% by 2026.
“COVID-19 has increased the need for health leaders to be able to make decisions in real-time and predict what resources they will require for upcoming demand,” says Rob O’Neill, head of analytics at the University Hospitals of Morecambe Bay, NHS Foundation Trust (UHMBT). Deriving actionable data in healthcare is helping organizations and providers with a roadmap for optimising operations, improving patient outcomes, and adopting new healthcare models.
Predicting patterns in healthcare
Predictive analytics enable doctors to accurately predict patient outcomes through medical imaging, prognosis, population health management, and palliative care plans, transforming the care administered. Lauren Neal, head of the Health Artificial Intelligence (AI) business at Booz-Allen says, “(predictive analytics can help) identify pain points throughout the stages of intake and care to improve both healthcare delivery and patient experience.”
Some common use cases of how hospitals might use predictive analytics include:
- Creating risk scores to identify which patients may benefit from enhanced, personalized services, wellness activities, etc.
- Determining which individuals are at the highest risk for readmission and predicting sepsis rates, especially during triage situations, pandemics, and more.
- Identifying and tracking patients with the gravest co-morbidities that require specialised care.
- Monitoring and anticipating personal protective equipment supply and demand throughout the year
Startups making strides in churning health data
The Irish startup GlowDx built a diagnostics platform for tackling infectious ailments like Chikungunya, Dengue Fever, and Zika virus in emerging economies. It utilises machine learning for modeling and predicting potential outbreaks of mosquito-borne infections.
Qube Health (the author is the CEO), a fin-tech for health-tech company based in India, pools together a large volume of healthcare consumption data – healthcare payments, insurance claims, and health records to provide contextual suggestions that help individual’s plan their family’s future healthcare needs.
Israeli startup InnVentis uses advanced algorithms on high-quality health data to design solutions for patient monitoring, diagnostics, and therapeutic decisions on chronic inflammatory diseases.
Challenges in drawing upon health data
Healthcare systems rely on labs, patient-reported data, regulated and unregulated Electronic Health Records (EHRs), medical notes, independent imaging devices, research reports, medical service alerts, and drug prescriptions. This makes it challenging to extract and structure data so that an algorithm can derive meaningful output.
While AI and ML algorithms have helped; creating a significant difference in identifying at-risk patients, improving their diagnoses, delivering better care, there remains a sizeable gap to bridge.
Interoperability, remains another challenge. By its very nature, healthcare systems worldwide don’t collect uniform data and don’t have a uniform infrastructure to process large volumes of disparate health data as yet. Integration of multiple healthcare data sources and interoperability between healthcare systems leave massive scope for improvement.
In countries like India, where there’s no regulatory framework on EHR (Electronic Health Records), most healthcare organizations are weary and relatively less proactive in making the data entries, including the claims, EHR, operations details, ambulatory data, etc., more uniform.
What’s next for data in healthcare?
In the US, 4 out of 5 people approve of RPM (Remote Patient Monitoring), and a staggering number will allow physicians to monitor their health and track patient data remotely. With increased usage of IoT-powered biomedical sensors, 2,314 exabytes of healthcare data are available today worldwide.
Soon enough, predictive analytics can empower doctors and caregivers to identify diseases early, deliver personalised preventative treatment plans, and highlight anomalies in at-home treatment compliance and routine medications.
Ultimately, we will have improved patient outcomes across population cohorts by selecting targeted treatment plans, considering patient’s existing conditions, medications, and personal history. This is an exciting future to look forward to in patient care.