Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy

Abstract

BackgroundSecondary and retrospective use of hospital-hosted clinical data provides a time- and cost-efficient alternative to prospective clinical trials for biomarker development. This study aims to create a retrospective clinical dataset of Magnetic Resonance Images (MRI) and clinical records of neonatal hypoxic ischemic encephalopathy (HIE), from which clinically-relevant analytic algorithms can be developed for MRI-based HIE lesion detection and outcome prediction.MethodsThis retrospective study will use clinical registries and big data informatics tools to build a multi-site dataset that contains structural and diffusion MRI, clinical information including hospital course, short-term outcomes (during infancy), and long-term outcomes (~ 2 years of age) for at least 300 patients from multiple hospitals.DiscussionWithin machine learning frameworks, we will test whether the quantified deviation from our recently-developed normative brain atlases can detect abnormal regions and predict outcomes for individual patients as accurately as, or even more accurately, than human experts.Trial Registration Not applicable. This study protocol mines existing clinical data thus does not meet the ICMJE definition of a clinical trial that requires registration

Study protocol: retrospectively mining multisite clinical data to presymptomatically predict seizure onset for individual patients with Sturge-Weber

“…The Computational Health Research Integration System (ChRIS) platform offers this function, 32 similar to other retrospective paediatric brain MRI projects at BCH. 27 33 KKI also hosts the i2b2 34 platform for this function.…”

“…Existing MRI studies for SWS mostly used expert reviews. We will leverage MRI analytics and machine learning algorithms, which have had success in characterising subtle yet complex injury patterns 22 23 and in predicting outcomes for stroke, 24 tumour, 25 autism 26 and other neurologic diseases, 27…”

Künstliche Intelligenz bei Bildauswertung und Diagnosefindung

“…In einem Multizenterprojekt wurden klinische Daten und Ergebnisse der Bildgebung bei Kindern mit neonataler hypoxisch-ischämischer Enzephalopathie gesammelt. Eine KI mit ML soll an diesem Datenpool Algorithmen entwickeln, die Aussagen zur Prognose gestatten [29]. Ergebnisse der Bildgebung werden in AI-Anwendungen integriert, die Biomarker für bestimmte neurokognitive Erkrankungen identifizieren, um diese möglichst frühzeitig zu diagnostizieren und eine entsprechende (Früh-)Förderung bzw.…”

Artificial intelligence in paediatric radiology: Future opportunities

“…[42][43][44] At present, several pipelines and registries are being created for similar work in children. For example, Weiss et al 45 have created a multicentre clinical and imaging dataset to develop machine-learning frameworks for the detection and outcome prediction in neonatal hypoxic ischaemic encephalopathy. Similarly in paediatric oncology, the recently established multi-centre 'PRIMAGE' project aims to phenotype, provide appropriate treatment decisions and prognosticate disease outcomes for two types of paediatric cancers -neuroblastoma and diffuse intrinsic pontine glioma (DIPG).…”