Catherine Zhu, a recent addition to the IMO Health team, boasts a diverse background in software engineering, data analytics, business intelligence, and product management. While distinct, each of these roles reinforced to Zhu the importance of superior data quality, leading her to IMO Health, a clinical data intelligence company laser-focused on transforming healthcare by transforming data.
In the following Q&A, Zhu dishes about – you guessed it – data, and how clinical AI can serve as a critical link in improving data quality in healthcare across payers, providers, and health tech.
IMO Health: You recently joined the IMO Health team and we’re so excited to have you. Can you tell us a little bit about your career background and what made you interested in data quality?
Catherine Zhu: I’m so excited to be part of the IMO Health team! I started out as a software engineer at IBM, but throughout my career have worked in the healthcare, insurance, higher education, and technology industries. I’ve worked as a software engineer, data analyst, business intelligence developer, and product manager – roles which taken collectively have given me a strong understanding of the importance of data in driving insights and improving decision-making.
I became interested in data quality after seeing firsthand, while working for a healthcare provider, how critical accurate data is for healthcare outcomes, and how high-quality data analysis can significantly contribute to patient care and operational efficiencies. I’m excited to apply my passion for leveraging data to solve complex challenges to IMO Health’s mission of improving healthcare data quality and precision.
IMO Health: How would you describe what clinical AI is, and why it’s important, to someone who is unfamiliar?
CZ: Clinical AI, at its best, combines advanced technology, clinical terminology, and human expertise to boost healthcare data quality. Any effective clinical AI project requires three elements: a clear objective or problem to solve, an appropriate algorithm to address the issue, and data to fuel the process.
IMO Clinical AI brings together the best of all these elements: award-winning technology, a detailed and expansive database of clinical terminology, and expert human oversight. It utilizes a robust AI development platform, natural language processing (NLP) pipelines, and large language models (LLMs) in a platform specifically designed to provide accurate, actionable insights for healthcare. By using high-quality ingredients in its technological “recipe,” IMO Clinical AI empowers organizations to make data-driven decisions and improve patient care.
INSIGHT BRIEF
Harnessing the potential of ambient AI: Optimizing workflows, reducing burnout, and improving patient interactions
IMO Health: How do you see clinical AI serving as a bridge between payers, providers, and health tech companies, ensuring smoother collaboration and data sharing across the healthcare ecosystem?
CZ: By standardizing and analyzing data from multiple sources, such as electronic health records (EHRs) and claims data, IMO Clinical AI helps create a unified view of a patient’s health. For payers, this means more accurate risk assessments that can create additional confidence in the diagnosis and prescription stages of a health visit. Providers can leverage AI-powered insights to heighten the personalization of care and improve patient outcomes. Plus, a better and more streamlined reimbursement process benefits both sides.
Health tech companies can also use the insights our Clinical AI draws from a massive reservoir of experiential data to develop innovative solutions that integrate seamlessly into providers’ existing workflows. Ultimately, Clinical AI fosters better communication among different stakeholders, reduces redundancies, and helps all parties work together to provide effective and patient-personalized care.
IMO Health: Can you expand further on how clinical AI can help align the goals of payers and providers, particularly in areas like reimbursement?
CZ: Clinical AI creates more transparent mechanisms for calculating reimbursement, care coordination, and outcomes-based care. By analyzing clinical and claims data, AI can help identify gaps in documentation, ensuring that providers capture the full scope of care provided, which leads to more accurate reimbursements for payers.
In care coordination, AI-driven insights can help providers identify high-risk patients earlier, enabling timely interventions that improve outcomes and reduce costs. For payers, this means fewer hospital readmissions and more effective management of chronic conditions in alignment with value-based care goals.
IMO Health: What qualities should organizations look for when considering a clinical AI vendor? Is there anything they should avoid?
CZ: I would say that qualities like proven expertise in healthcare and a track record of success in clinical settings are very important. The vendor should have a deep knowledge of clinical workflows, regulatory compliance, and the ability to integrate seamlessly with existing systems like EHRs. Conversely, things to watch out for would be not having real-world validation or having a rigid, one-size-fits-all approach with no flexibility to tailor the AI solution to the needs of an individual organization.
I would advise providers to look for solutions that prioritize transparency and offer explainable AI models so healthcare teams can also understand how decisions are made within the “black box” of the algorithm. Vendors with overly complex or non-intuitive user interfaces can lead to poor adoption rates which undermine the success of AI implementation. Inadequate data privacy measures or failure to comply with healthcare regulations are also major concerns.
IMO Health: What role does accurate and comprehensive clinical terminology play in the effectiveness of clinical AI solutions, particularly for data quality management?
CZ: Data quality is everything in clinical AI. Inconsistent or inaccurate terminology can lead to data fragmentation, misinterpretation, and incomplete analysis, impacting patient outcomes and the level of care provided.
In contrast, standardized terminology – such as IMO Health’s terminology database – which has been widely used and contributed to by medical providers for decades – ensures that clinical data is consistently captured, aggregated, and analyzed across different systems and care settings. The AI is thus equipped with the collective knowledge of all the terminology used in provider-patient interactions to generate its subsequently more accurate predictions and recommendations.