Fatime Oumar, a PhD candidate at the University of Twente, is tackling this challenge by developing dynamic, AI driven predictive models that detect complications, such as infections, respiratory decline, or other physiological issues, before they manifest clinically. These adverse events may arise days, weeks, or even months after treatment, often without obvious warning signs, and sometimes too late to manage effectively.
Fatime specialises in biomedical engineering and works on AI based models that detect early signs of complications after cancer or obesity treatment. Part of her research involves collecting and analysing continuous vital signs, including heart rate and respiration, using wearable sensors and personalised prediction algorithms. “We try to pick up the early signs, subtle, silent changes in the body, that might signal something is about to go wrong,” she explains.
Making the invisible visible
Fatime is part of the Biomedical Signals and Systems (BSS) group at UT and contributes to RECENTRE, a nationwide research programme funded by the 4TU.Federation. Her work focuses on developing predictive models that can identify complications following various types of cancer therapy and bariatric procedures. In collaboration with clinical partners such as Medisch Spectrum Twente (MST), Ziekenhuisgroep Twente (ZGT), the Princess Máxima Centre for Paediatric Oncology, and the Helen Dowling Institute, Fatime is bridging the gap between engineering and healthcare.
In a pilot study at MST, patients undergoing major abdominal cancer surgery were monitored at home for 14 days using a small, lightweight wearable patch. This device discreetly recorded vital physiological signals, including heart rate, breathing rate, and physical activity, on a continuous basis. “These sensors collect high frequency data that reflect the patient’s real time condition,” Fatime says. “We use this data to train AI models that learn what is normal for each patient, creating a personalised baseline.”
When the system detects a deviation, such as a subtle but consistent rise or drop in heart rate, it flags it as a potential warning sign. “Often, these deviations occur well before traditional clinical scores would detect a problem,” she adds. “With some patients, we’re seeing signs six hours earlier than current hospital methods. That difference can be meaningful in a clinical setting.”
From hospital to home
Fatime’s work supports a broader shift: from hospital-based observation to home-based continuous monitoring. As she puts it, “Hospitals are often full. If we can monitor safely from a distance, it is better for everyone.” While data collection remains a technical challenge, she is optimistic. Her goal is to develop self-updating, dynamic models that adapt as new patient data comes in. “That’s the future: personalised, evolving risk prediction based on longitudinal data.”
Beyond recovery: predicting long-term risks
Another aspect of her research looks at long term survivorship, particularly in childhood cancer populations. In collaboration with the Princess Máxima Centre, she studies how long term health data, including lifestyle, comorbidities, and treatment history, can be integrated to predict risks such as cardiac dysfunction that may appear years after treatment. “We aim to develop adaptive risk prediction models that account for changes in a patient’s health over time,” she explains. “Risk is not static. It evolves in response to lifestyle changes, new diagnoses, and treatment history. By anticipating these changes, we can better support timely and tailored follow up care.”
Personal fascination
Fatime’s interest in medical data analysis began during her studies in Türkiye, where she earned both her bachelor’s and master’s degrees in biomedical engineering. Her bachelor’s thesis focused on detecting diabetic retinopathy using retinal imaging and machine learning. During her master’s, she developed an evolutionary algorithm to select relevant spectral features from urine based FTIR spectroscopy data, which were then used in machine learning models to classify endometrial and ovarian cancer. “I was fascinated by the idea that computational models could extract meaningful patterns from complex biological data,” she says. “The PhD position at the University of Twente immediately caught my attention, as it brought together my interests in biomedical data analysis, artificial intelligence, and clinical relevance.”
Looking ahead
In addition to her research, Fatime is passionate about teaching and mentoring students. Soon, she plans to guide students in biomedical engineering and artificial intelligence courses. “If others can learn from my work, and then go even further, that is success to me.”
With over two years remaining in her PhD, her vision is clear: to make healthcare smarter, earlier, and more proactive. “We cannot eliminate all complications,” she concludes, “but we can make sure they don’t take us by surprise.”
