Machine learning in neonatal intensive care

Olli-Pekka Rinta-Koski

Machine learning in neonatal intensive care

Julkaisun otsikon käännös: Koneoppiminen vastasyntyneiden tehohoidossa

Olli-Pekka Rinta-Koski

Tutkimustuotos: Doctoral Thesis › Collection of Articles

Abstrakti

Tämä väitöskirja käsittelee koneoppimismenetelmien soveltamista vastasyntyneiden tehohoidossa. Pääasiallinen tavoite on potilaan tilan ennustaminen monikanavaisen aikasarjadatan perusteella. Ennustusmenetelmien tutkimisen päämäärä on datalähtöisten työkalujen kehittäminen hoitohenkilökunnan päätöksenteon avuksi. Ennen 37. raskausviikkoa syntyneillä keskoslapsilla on monia kehitykseen ja terveyteen liittyviä ongelmia. Näistä lapsista kaikkein ongelmallisimpia ovat syntymäpainoltaan alle 1500 g painoiset pikkukeskoset, jotka tarvitsevat tehohoitoa vastasyntyneiden teho-osastolla ennen kotiutumistaan. Vastasyntyneiden teho-osasto on paljon dataa tuottava ympäristö, jossa potilaista kerätään monikanavaista fysiologista dataa erilaisten sensorien avulla. Sensoridataa käyttämällä voidaan muodostaa kokonaisvaltainen kuva potilaan tilasta ja elintoiminnoista. Vastasyntyneiden tehohoidossa joudutaan tekemään monista lähteistä kerätyn tiedon perusteella reaaliaikaisia päätöksiä, joilla voi olla potilaan kannalta vakavia ja pitkäkestoisia vaikutuksia. Hoitohenkilökunta voi päivittäisessä työssään käyttää hyväkseen teho-osaston näytöiltä saatavaa reaaliaikaista dataa. Pitkäaikaisten trendien ja suurien, jopa tuhansia potilaita sisältävien datamäärien analyysi edellyttää koneoppimismenetelmien käyttöä. Tässä väitöskirjassa sovelletaan koneoppimismenetelmiä, erityisesti luokittelua gaussisten prosessien avulla, sairaalakuolleisuuden ja tiettyjen sairauksien ennustamiseen. Tutkimusaineisto oli fysiologisia signaaleja sisältävää aikasarjadataa, jota on kerätty HUS:in vastasyntyneiden teho-osastolla vuosina 1999-2013 hoidetuista pikkukeskosista. Tuloksemme osoittavat, että aikasarjadatan pohjalta luodun koneoppimismallin ennustusvoima on verrannollinen lääketieteellisten tunnuslukujen kanssa, ja että näiden yhdistelmällä saadaan parempia tuloksia kuin kummallakaan yksin. Tutkimme myös elintoimintomittausten muuttumista havainnoitsijan painotuksen mukaan. Lisäksi väitöskirjaan sisältyy retrospektiivinen kohorttitutkimus muutoksista alle 1000 g syntymäpainoisten pikkukeskosten kasvussa tehohoidon aikana.

Julkaisun otsikon käännös	Koneoppiminen vastasyntyneiden tehohoidossa
Alkuperäiskieli	Englanti
Pätevyys	Tohtorintutkinto
Myöntävä instituutio	Aalto-yliopisto
Valvoja/neuvonantaja	Särkkä, Simo, Vastuuprofessori Hollmen, Jaakko, Ohjaaja
Kustantaja	Aalto University
Painoksen ISBN	978-952-60-8209-7
Sähköinen ISBN	978-952-60-8210-3
Tila	Julkaistu - 2018
OKM-julkaisutyyppi	G5 Artikkeliväitöskirja

Tutkimusalat

koneoppiminen
neonatologia

Pääsy asiakirjaan

http://urn.fi/URN:ISBN:978-952-60-8210-3Lisenssi: Määrittelemätön

OpenUrl-saatavuus

Koko teksti

Siteeraa tätä

@phdthesis{384b0b18f2eb4055b5267d5ad3bd3a6c,

title = "Machine learning in neonatal intensive care",

abstract = "This thesis deals with the applications of machine learning in the context of neonatal intensive care. The main focus is on prediction using multichannel time series data. The purpose of developing prediction methods is to create data-driven tools for helping care personnel to make more informed decisions. Preterm infants, born before 37 weeks of gestation, are subject to many developmental issues and health problems. Very Low Birth Weight infants, with a birth weight under 1500 g, are the most afflicted in this group. These infants require treatment in the neonatal intensive care unit before they are mature enough for hospital discharge. The neonatal intensive care unit is a data-intensive environment, where multi-channel physiological data is gathered from patients using a number of sensors to construct a comprehensive picture of the patients' vital signs. Neonatal intensive care requires combining information from multiple sources, often with severe and far-reaching consequences for the patient. Real-time data is available on multiple monitor screens in the ward, and is used by care personnel to help them make informed decisions. Analysis of trends and vast data sets, possibly spanning thousands of patients, requires the use of machine learning methods. In the research done for this thesis we have applied machine learning methods, in particular Gaussian process classification, to predict neonatal in-hospital mortality and morbidities. We have used time series data collected from Very Low Birth Weight infants treated in the neonatal intensive care unit of Helsinki University Hospital between 1999 and 2013. Our results show that machine learning models based on time series data alone have predictive power comparable with standard medical scores, and combining the two results in improved predictive ability. We have also studied the effect of observer bias on recording vital sign measurements in the neonatal intensive care unit, as well as conducted a retrospective cohort study on trends in the growth of Extremely Low Birth Weight (birth weight under 1000 g) infants during intensive care.",

keywords = "machine learning, neonatology, koneoppiminen, neonatologia, machine learning, neonatology",

author = "Olli-Pekka Rinta-Koski",

year = "2018",

language = "English",

isbn = "978-952-60-8209-7",

series = "Aalto University publication series DOCTORAL DISSERTATIONS",

publisher = "Aalto University",

number = "189",

address = "Finland",

school = "Aalto University",

}

TY - BOOK

T1 - Machine learning in neonatal intensive care

AU - Rinta-Koski, Olli-Pekka

PY - 2018

Y1 - 2018

N2 - This thesis deals with the applications of machine learning in the context of neonatal intensive care. The main focus is on prediction using multichannel time series data. The purpose of developing prediction methods is to create data-driven tools for helping care personnel to make more informed decisions. Preterm infants, born before 37 weeks of gestation, are subject to many developmental issues and health problems. Very Low Birth Weight infants, with a birth weight under 1500 g, are the most afflicted in this group. These infants require treatment in the neonatal intensive care unit before they are mature enough for hospital discharge. The neonatal intensive care unit is a data-intensive environment, where multi-channel physiological data is gathered from patients using a number of sensors to construct a comprehensive picture of the patients' vital signs. Neonatal intensive care requires combining information from multiple sources, often with severe and far-reaching consequences for the patient. Real-time data is available on multiple monitor screens in the ward, and is used by care personnel to help them make informed decisions. Analysis of trends and vast data sets, possibly spanning thousands of patients, requires the use of machine learning methods. In the research done for this thesis we have applied machine learning methods, in particular Gaussian process classification, to predict neonatal in-hospital mortality and morbidities. We have used time series data collected from Very Low Birth Weight infants treated in the neonatal intensive care unit of Helsinki University Hospital between 1999 and 2013. Our results show that machine learning models based on time series data alone have predictive power comparable with standard medical scores, and combining the two results in improved predictive ability. We have also studied the effect of observer bias on recording vital sign measurements in the neonatal intensive care unit, as well as conducted a retrospective cohort study on trends in the growth of Extremely Low Birth Weight (birth weight under 1000 g) infants during intensive care.

AB - This thesis deals with the applications of machine learning in the context of neonatal intensive care. The main focus is on prediction using multichannel time series data. The purpose of developing prediction methods is to create data-driven tools for helping care personnel to make more informed decisions. Preterm infants, born before 37 weeks of gestation, are subject to many developmental issues and health problems. Very Low Birth Weight infants, with a birth weight under 1500 g, are the most afflicted in this group. These infants require treatment in the neonatal intensive care unit before they are mature enough for hospital discharge. The neonatal intensive care unit is a data-intensive environment, where multi-channel physiological data is gathered from patients using a number of sensors to construct a comprehensive picture of the patients' vital signs. Neonatal intensive care requires combining information from multiple sources, often with severe and far-reaching consequences for the patient. Real-time data is available on multiple monitor screens in the ward, and is used by care personnel to help them make informed decisions. Analysis of trends and vast data sets, possibly spanning thousands of patients, requires the use of machine learning methods. In the research done for this thesis we have applied machine learning methods, in particular Gaussian process classification, to predict neonatal in-hospital mortality and morbidities. We have used time series data collected from Very Low Birth Weight infants treated in the neonatal intensive care unit of Helsinki University Hospital between 1999 and 2013. Our results show that machine learning models based on time series data alone have predictive power comparable with standard medical scores, and combining the two results in improved predictive ability. We have also studied the effect of observer bias on recording vital sign measurements in the neonatal intensive care unit, as well as conducted a retrospective cohort study on trends in the growth of Extremely Low Birth Weight (birth weight under 1000 g) infants during intensive care.

KW - machine learning

KW - neonatology

KW - koneoppiminen

KW - neonatologia

KW - machine learning

KW - neonatology

M3 - Doctoral Thesis

SN - 978-952-60-8209-7

T3 - Aalto University publication series DOCTORAL DISSERTATIONS

PB - Aalto University

ER -

Machine learning in neonatal intensive care

Abstrakti

Tutkimusalat

Pääsy asiakirjaan

OpenUrl-saatavuus

Sormenjälki

Siteeraa tätä