[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120375-en":3,"doc-seo-120375-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120375,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Towards Quantifying Biomarkers for Respiratory Distress in Preterm Infants - Machine Learning on Mid Infrared Spectroscopy of Lipid Mixtures","Neonatal respiratory distress syndrome (nRDS) presents diagnostic challenges that can delay timely treatment for preterm infants. Mid-infrared (mid-IR) spectroscopy enables measurement of two nRDS biomarkers—lecithin (L) and sphingomyelin (S)—with potential for point-of-care (POC) diagnosis and monitoring. The study models lung surfactant as five lipids and systematically varies other lipid species to evaluate machine-learning prediction of lipid concentrations and the L/S ratio. Uncertainty is quantified using jackknife+-after-bootstrap and variant bootstrap methods, yielding an L/S uncertainty of about ±0.3 moles/mole, alongside identification of key wavenumbers for model interpretation via SHAP.","Graphical Abstract  \nTowards Quantifying Biomarkers for Respiratory Distress in Preterm Infants: Machine Learning on Mid Infrared Spectroscopy of Lipid Mixtures  \nWaseem Ahmed, Aneesh Vincent Veluthandath, Jens Madsen, Howard W. Clark, Ahilanandan Dushianthan, Anthony D. Postle, James S. Wilkinson, Ganapathy Senthil Murugan  \nHighlights  \nTowards Quantifying Biomarkers for Respiratory Distress in Preterm Infants: Machine Learning on Mid Infrared Spectroscopy of Lipid Mixtures  \nWaseem Ahmed, Aneesh Vincent Veluthandath, Jens Madsen, Howard W. Clark, Ahilanandan Dushianthan, Anthony D. Postle, James S. Wilkinson, Ganapathy Senthil Murugan  \n• Comprehensive calibration of PLSR models using physiological concentrations of lung surfactant lipids  \n• Prediction intervals for quantified uncertainty in PLSR models  \n• Use of SHAP values to explain strength of AI model features with a view to optimising a spectroscopic point of care platform.  \nTowards Quantifying Biomarkers for Respiratory Distress in Preterm Infants: Machine Learning on Mid Infrared Spectroscopy of Lipid Mixtures  \nWaseem Ahmeda , Aneesh Vincent Veluthandatha , Jens Madsenb , Howard W. Clarkb , Ahilanandan Dushianthanc , Anthony D. Postled , James S.  \nWilkinsona , Ganapathy Senthil Murugana  \na Optoelectronics Research Centre, University of Southampton, Southampton, SO17  \n1BJ, Hampshire, UK  \nb Neonatology, Faculty of Population Health Sciences, EGA Institute for Women’s  \nHealth, University College London, London, WC1E 6AU, London, UK c Perioperative and Critical Care Theme, NIHR Biomedical Research Centre, University  \nHospital Southampton NHS Foundation Trust, Southampton, SO16 6YD, Hampshire, UK  \nd Academic Unit of Clinical & Experimental Sciences, Faculty of Medicine, Southampton  \nGeneral Hospital, Southampton, SO16 6YD, Hampshire, UK  \nAbstract  \nNeonatal respiratory distress syndrome (nRDS) is a challenging condition to diagnose which can lead to delays in receiving appropriate treatment. Mid infrared (IR) spectroscopy is capable of measuring the concentrations of two diagnostic nRDS biomarkers, lecithin (L) and sphingomyelin (S) with the potential for point of care (POC) diagnosis and monitoring. The effects of varying other lipid species present in lung surfactant on the mid IR spectra used to train machine learning models are explored. This study presents a lung lipid model of five lipids present in lung surfactant and varies each ina systematic approach to evaluate the ability of machine learning models to predict the lipid concentrations, the L/S ratio and to quantify the uncertainty in the predictions using the jackknife+-after-bootstrap and variant bootstrap methods. We establish the L/S ratio can be determined with an uncertainty of approximately ±0.3 moles/mole and we further identify the 5 most prominent wavenumbers associated with each machine learning model.  \nEmail address: [waseem.ahmed@soton.ac.uk](waseem.ahmed@soton.ac.uk) (Waseem Ahmed)  \nPreprint submitted to Talanta March 20, 2024  \nKeywords: ATR-FTIR, Machine, Learning, PLSR, Lipid, SHAP values, nRDS  \n1. Introduction  \nMid-infrared (mid-IR) spectroscopy has been posited as a platform for rapid, point of care diagnostic tool which can interrogate samples in the functional group and fingerprint spectral regions[1, 2] . This allows for both qualitative and quantitative determination of biomarkers to provide a clinician with useful information to consider during diagnosis and prognostication. Attenuated total reflectance Fourier Transform infrared spectroscopy (ATR-FTIR) is one method by which such information may be obtained. Spectroscopic analysis of biological samples followed by machine learning of collected spectra provides an opportunity to apply a more robust multivariate analysis, using all relevant information from multiple spectral peaks, to give quantitative estimates of biomarker concentrations without the need for an expert end-user.  \nNeonatal respiratory distress syndrome (","cbCaihbZo0ZdPF84","https://ap.wps.com/l/cbCaihbZo0ZdPF84","pdf",2013171,1,28,"English","en",105,"# Highlights\n# Abstract\n# Keywords\n# 1. Introduction\n## Background: nRDS and diagnostic delay\n## Mid-IR spectroscopy and ATR-FTIR\n## Lung surfactant composition and L/S biomarker relevance\n## Motivation for uncertainty quantification and interpretable ML","[{\"question\":\"What biomarkers are targeted for quantifying respiratory distress in preterm infants?\",\"answer\":\"The study targets lecithin (L) and sphingomyelin (S), including the L/S ratio used to reflect nRDS-associated changes in lung surfactant.\"},{\"question\":\"How does the study use machine learning with mid-infrared spectroscopy?\",\"answer\":\"It trains models on mid-IR spectra from a lung lipid model of five surfactants, varying lipid components to assess prediction of lipid concentrations and the L/S ratio.\"},{\"question\":\"How is prediction uncertainty quantified in the PLSR models?\",\"answer\":\"Uncertainty in the quantified predictions is estimated using jackknife+-after-bootstrap and variant bootstrap methods, leading to an L/S uncertainty of approximately ±0.3 moles/mole.\"}]","Towards Quantifying Biomarkers for Respiratory Distress in Preterm Infants - Machine Learning on Mid Infrared Spectroscopy of Lipid Mixtures | PDF",1785729725,71,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"towards-quantifying-biomarkers-for-respiratory-distress-in-preterm-infants-machine-learning-on-mid-infrared-spectroscopy-of-lipid-mixtures","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/towards-quantifying-biomarkers-for-respiratory-distress-in-preterm-infants-machine-learning-on-mid-infrared-spectroscopy-of-lipid-mixtures/120375/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What biomarkers are targeted for quantifying respiratory distress in preterm infants?","Question",{"text":75,"@type":76},"The study targets lecithin (L) and sphingomyelin (S), including the L/S ratio used to reflect nRDS-associated changes in lung surfactant.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the study use machine learning with mid-infrared spectroscopy?",{"text":80,"@type":76},"It trains models on mid-IR spectra from a lung lipid model of five surfactants, varying lipid components to assess prediction of lipid concentrations and the L/S ratio.",{"name":82,"@type":73,"acceptedAnswer":83},"How is prediction uncertainty quantified in the PLSR models?",{"text":84,"@type":76},"Uncertainty in the quantified predictions is estimated using jackknife+-after-bootstrap and variant bootstrap methods, leading to an L/S uncertainty of approximately ±0.3 moles/mole.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]