eprintid: 10179358 rev_number: 6 eprint_status: archive userid: 699 dir: disk0/10/17/93/58 datestamp: 2023-10-23 08:29:06 lastmod: 2023-10-23 08:29:06 status_changed: 2023-10-23 08:29:06 type: proceedings_section metadata_visibility: show sword_depositor: 699 creators_name: Bili, Danai creators_name: Lange, Frédéric creators_name: Jones, Kelly H creators_name: Parfentyeva, Veronika creators_name: Durduran, Turgut creators_name: Robertson, Nikki creators_name: Mitra, Subhabrata creators_name: Tachtsidis, Ilias title: Classification of brain injury severity using a hybrid broadband NIRS and DCS instrument with a machine learning approach ispublished: pub divisions: UCL divisions: B02 divisions: B04 divisions: C05 divisions: D11 divisions: F42 divisions: G14 note: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. abstract: Optical biomarkers of neonatal hypoxic ischemic (HI) brain injury can offer the advantage of continuous, cot-side assessment of the degree of injury; research thus far has focused on examining different optical measured brain physiological signals and feature combinations to achieve this. To maximize the breadth of physiological characteristics being taken into consideration, a multimodal optical platform has been developed, allowing unique physiological insights into brain injury. In this paper we present an assessment of severity of injury using a state-of-the-art hybrid broadband Near Infrared Spectrometer (bNIRS) and Diffusion Correlation Spectrometer (DCS) instrument called FLORENCE with a machine learning pipeline. We demonstrate in the preclinical neonatal model (the newborn piglet) that our approach can identify different HI insult severity (controls, mild, severe). We show that a machine learning pipeline based on k-means clustering can be used to differentiate between the controls and the HI piglets with an accuracy of 78%, the mild severity insult piglets from the severe insult piglets with an accuracy of 90% and can also differentiate the 3 piglet groups with an accuracy of 80%. So, this analytics pipeline demonstrates how optical data from multiple instruments can be processed towards markers of brain health. date: 2023-08-09 date_type: published publisher: SPIE official_url: https://doi.org/10.1117/12.2670657 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2095433 doi: 10.1117/12.2670657 isbn_13: 9781510664654 lyricists_name: Tachtsidis, Ilias lyricists_name: Robertson, Nicola lyricists_name: Mitra, Subhabrata lyricists_name: Lange, Frederic lyricists_id: ITACH19 lyricists_id: NROBE79 lyricists_id: MITRA07 lyricists_id: FLANG91 actors_name: Flynn, Bernadette actors_id: BFFLY94 actors_role: owner full_text_status: public pres_type: paper series: European Conferences on Biomedical Optics publication: Proceedings of SPIE - The International Society for Optical Engineering volume: 12628 place_of_pub: Munich, Germany pagerange: 126280D event_title: European Conferences on Biomedical Optics 2023 issn: 0277-786X book_title: Proceedings Volume 12628, Diffuse Optical Spectroscopy and Imaging IX editors_name: Contini, Davide editors_name: Hoshi, Yoko editors_name: O'Sullivan, Thomas D citation: Bili, Danai; Lange, Frédéric; Jones, Kelly H; Parfentyeva, Veronika; Durduran, Turgut; Robertson, Nikki; Mitra, Subhabrata; Bili, Danai; Lange, Frédéric; Jones, Kelly H; Parfentyeva, Veronika; Durduran, Turgut; Robertson, Nikki; Mitra, Subhabrata; Tachtsidis, Ilias; - view fewer <#> (2023) Classification of brain injury severity using a hybrid broadband NIRS and DCS instrument with a machine learning approach. In: Contini, Davide and Hoshi, Yoko and O'Sullivan, Thomas D, (eds.) Proceedings Volume 12628, Diffuse Optical Spectroscopy and Imaging IX. (pp. 126280D). SPIE: Munich, Germany. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10179358/1/126280D.pdf