Search

Simple Summary: Breast cancer is a heterogeneous disease characterized by different risks of relapse, which makes it challenging to predict progression and select the most appropriate follow-up strategies. With the ever-growing adoption of Electronic Health Records, there are great opportunities to leverage the amount of data collected routinely in electronic format for secondary purposes. Machine Learning algorithms offer the ability to analyze large amounts of data and reveal insights that might otherwise go undetected. In this study, we have applied several algorithms to predict 5-year breast cancer recurrence from health data. We compared whether taking advantage of both structured and unstructured data from health records yields better prediction results than using any of the sources separately. These algorithms are valuable tools to help clinicians effectively integrate large amounts of data into their decision-making and are key to improving risk stratification and providing personalized assistance to patients. Recurrence is a critical aspect of breast cancer (BC) that is inexorably tied to mortality. Reuse of healthcare data through Machine Learning (ML) algorithms offers great opportunities to improve the stratification of patients at risk of cancer recurrence. We hypothesized that combining features from structured and unstructured sources would provide better prediction results for 5-year cancer recurrence than either source alone. We collected and preprocessed clinical data from a cohort of BC patients, resulting in 823 valid subjects for analysis. We derived three sets of features: structured information, features from free text, and a combination of both. We evaluated the performance of five ML algorithms to predict 5-year cancer recurrence and selected the best-performing to test our hypothesis. The XGB (eXtreme Gradient Boosting) model yielded the best performance among the five evaluated algorithms, with precision = 0.900, recall = 0.907, F1-score = 0.897, and area under the receiver operating characteristic AUROC = 0.807. The best prediction results were achieved with the structured dataset, followed by the unstructured dataset, while the combined dataset achieved the poorest performance. ML algorithms for BC recurrence prediction are valuable tools to improve patient risk stratification, help with post-cancer monitoring, and plan more effective follow-up. Structured data provides the best results when fed to ML algorithms. However, an approach based on natural language processing offers comparable results while potentially requiring less mapping effort. [ABSTRACT FROM AUTHOR]

Introduction: Cancer survival has increased dramatically in recent years, with more than half of European cancer patients surviving at least 5 years after their first diagnosis. However, cancer survivors have complex needs that are generally not appropriatelly addressed in the guidelines' recommendations used in follow-up after treatment, especially when it comes to improving the Quality of Life (QoL). Moreover, information collected in the Electronic Health Records (EHR) shows a biased view of the patients, since their voice is not routinely recorded. Tools that provide a holistic view of the cancer survivor are needed to improve the delivery of survivorship care. Objectives: The PERSIST H2020 project aims to improve the health outcomes and QoL of breast and colorectal cancer survivors by developing innovative tools based on Big Data and advanced data analytics to support the decision-making of physicians. It will provide evidence base and tools that take into account the whole person--all of one's health and lifestyle conditions-- that contribute to optimal follow-up and development of personalized survivorship care plans. Results: PERSIST is an open and flexible ecosystem composed by a central Big Data platform and several digital tools to support both patients and health providers. Interoperability is guaranteed by the CASIDE data model [1], which is based on the FHIR healthcare standard, and allows the structured collection, integration and aggregation of complex and fragmented data from EHR, patient sensed data, and PROMs (Patient Reported Outcome Measures). These data are analyzed through advanced data analysis and artificial intelligence algorithms that provide actionable recommendations for better decision-making. Patient trajectories learned from patient data enable practitioners a better appreciation of the risks at patient-specific level and help to prevent or timely identify side effects and the development of secondary conditions. A multicenter clinical study is being held in 4 EU countries (Belgium, Latvia, Slovenia, and Spain) involving 160 survivors, 80 of breast cancer and 80 of colorectal cancer. Conclusions: PERSIST provides a scalable and interoperable ecosystem powered by Big Data and AI to analyse data coming from different sources, facilitating an integrated view of survivors health. It will support decision-making and contribute to optimal treatment decisions with positive consequences for the QoL and the health status of survivors. Implications For Transferability And Limitations: The system's modular design and interoperability based on the FHIR healthcare standard makes the components highly reusable. The AI algorithms are specific for breast and colon cancer, and are trained with data from the hospitals participating in the project, which may not be representative and generalizable to other settings. [ABSTRACT FROM AUTHOR]