Turning Records into Foresight: Machine Learning to Anticipate Need in Cancer Survivorship Care
Key Takeaways:
- Sylvester researchers used machine learning on records and patient-reported data from over 25,000 people who have survived cancer to predict who is most at risk.
- Adding patients’ own reports nearly doubled the models’ accuracy, with the top 10 per cent of risk capturing about half of later events.
- The work signals a shift towards proactive, personalised survivorship care, though it is not yet meant to change practice.
A new phase of care
For a growing number of people who have survived cancer, ringing the bell at the end of primary treatment marks the start of a complex new phase of care – one that is often less structured and far harder to predict. Even once therapy has concluded, people may continue to experience lingering physical symptoms, emotional distress or other unexpected medical needs. These can lead to visits to the emergency department or urgent care, to hospital admissions, and to a worsening burden of symptoms over time.
A new study from Sylvester Comprehensive Cancer Center, part of the University of Miami Miller School of Medicine, suggests that the key to anticipating these outcomes may lie in examining electronic health records and patient-reported data systematically, using novel artificial intelligence (AI) technologies.
Published in JCO – Clinical Cancer Informatics, the study demonstrates how machine learning models, when applied to clinical data and patient-reported outcomes (PROs), can help identify survivors at increased risk of unplanned healthcare use and of an elevated symptom burden during survivorship. By transforming medical records and patient-reported data into predictive signals, the research offers a potential route towards more proactive, personalised survivorship care.
Cancer survivorship care is a dynamic, ongoing process rather than a single phase of care, explained Frank J. Penedo, Ph.D., Sylvester associate director for population sciences, director of Sylvester’s Survivorship and Supportive Care Institute and the study’s senior author.
“For many patients, new or evolving challenges arise after treatment ends, just as routine clinical contact often tapers off, raising a critical question. How can we identify those at higher risk earlier, before these concerns intensify and become harder to address?” Dr Penedo said.
Listening to people’s own experiences
Patient-reported outcomes capture experiences that traditional clinical data often miss or assess only infrequently. These include emotional well-being, fatigue, functional limitations and other practical needs that may interfere with adequate survivorship care. Over the past decade, PROs have become an increasingly important component of cancer care. Yet translating large volumes of patient-reported data, and integrating them with vast amounts of medical record data to produce actionable insights – particularly across whole populations of survivors – has remained a persistent challenge.
Led by Akina Natori, M.D., M.S.P.H., a Sylvester oncologist and assistant professor in the Division of Medical Oncology at the Miller School, the study reframed PROs. Rather than treating them as retrospective descriptions of what a person has already experienced, the team used them as prospective indicators of future need.
“PROs tell us how patients are actually feeling and functioning,” said Dr Natori, first author of the study. “We wanted to know whether those self-reported experiences, in combination with clinical data such as cancer and treatment type, could help us identify which survivors might be at higher risk for significant symptom burden or unplanned health care use down the line.”
Unplanned healthcare use can include emergency department visits or hospital admissions that arise outside scheduled follow-up. Such events often signal unmet needs or gaps in survivorship and supportive care. Being able to forecast that risk could allow care teams to step in earlier, with targeted symptom management, psychosocial support or closer monitoring.
Applying machine learning to survivorship data
To explore that possibility, the research team analysed data from more than 25,000 people who have survived cancer, followed over three years, using machine learning to detect patterns that traditional statistical methods can miss. The advantage of these approaches is their ability to weigh many factors at once – clinical history, treatments, symptoms, emotional well-being and patterns of healthcare use – and to find the subtle interactions that signal which people are heading towards trouble.
The answers turned out to depend on what was being predicted. For acute events such as emergency room visits and hospital admissions, recent clinical activity was the strongest signal: what was happening with a person over the last few months mattered more than where they had started. For symptom burden, longer-term trends told a clearer story. Crucially, adding patient-reported outcomes nearly doubled how well the models performed compared with clinical data alone. When the researchers flagged the highest-risk 10 per cent of people, that group accounted for roughly half of all subsequent healthcare events and elevated symptom episodes.
Building models that clinicians can trust
“This type of risk stratification problem is well-suited for machine learning,” said Jerry R. Bonnell, Ph.D., a postdoctoral associate at the University of Miami’s Frost Institute for Data Science and Computing. “The challenge is developing models that are not only accurate, but also interpretable and meaningful for clinicians making real-world decisions.”
That emphasis on interpretability shaped the study’s design. Rather than treating the models as opaque, “black box” systems, the team built them to show their reasoning. This surfaced which factors were driving a given person’s risk score, and how those factors shifted over time. The goal is a tool that gives clinicians not just a number, but a starting point for conversation: about who needs closer follow-up, what they may need, and when to step in before a problem escalates.
An interdisciplinary approach
The project drew together expertise from clinical oncology, psychosocial oncology, population sciences and data science, reflecting the multifaceted nature of survivorship care. Contributors included Vasileios Stathias, Ph.D., assistant director for data science at Sylvester, alongside collaborators across the University of Miami.
“Survivorship sits at the intersection of biology, behavior and health systems,” Dr Stathias said. “By combining patient-reported and clinical data with advanced analytics, we can begin to see patterns that might otherwise remain invisible and that can inform more proactive care strategies.”
Additional authors included:
- Sara Fleszar Pavlovic, Ph.D., a Miller School research assistant professor of medical oncology
- Mitsunori Ogihara, Ph.D., programme director of UM’s Big Data Analytics and Data Mining program
- Andrew Wang, A.B.
- Ravi Vadapalli, Ph.D., director of advanced computing for the Frost Institute for Data Science and Computing
- Blanca Silvia Noriega Esquives, M.D., Ph.D., a Sylvester postdoctoral associate
- Tracy Crane, Ph.D., RDN, co-leader of the Cancer Control Program and director of lifestyle medicine, prevention and digital health at Sylvester
Implications for cancer survivorship care
While the authors emphasised that the findings are not intended to change clinical practice immediately, they highlighted the broader implications of the work. As populations of people living beyond cancer continue to grow, health systems face mounting pressure to deliver long-term care that is precise, proactive and sustainable.
“This is about shifting from reactive to proactive survivorship care,” Dr Penedo said. “If we can identify patients who are more likely to struggle, we can begin to align supportive resources earlier and more effectively.”
The team also noted the potential impact of predictive models that combine clinical and PRO-based data on healthcare access. Because PROs reflect patient voices directly, they may help surface unmet needs that are less likely to be captured through routine clinical encounters alone.
Looking ahead
Future research will focus on continuing to refine and validate these models across broader populations of survivors, and on exploring how risk stratification driven by electronic health record and PRO data could be integrated into survivorship standards of care.
“The expertise of our multidisciplinary team provides a unique opportunity to create a data ecosystem that facilitates the implementation of AI-powered analytics to guide proactive and precision care to reduce the burden of cancer on patients and health systems. This study is among several initiatives that are working towards this goal,” said Dr Penedo.
“Our long-term goal is to ensure that survivorship care keeps pace with advances in treatment,” said Dr Natori. “That means using data not only to describe outcomes, but to anticipate them, so we can more proactively support patients in the years after cancer.”
Source: University of Miami Miller School of Medicine
Read More