Evaluation of machine learning algorithms for noninvasive intracranial pressure estimation using near infrared spectroscopy as a covariate
Intracranial pressure (ICP) is a vital parameter that is continuously monitored in patients with severe brain injury and imminent intracranial hypertension. To estimate intracranial pressure without intracranial probes based on transcutaneous near infrared spectroscopy (NIRS). We developed machine l...
Saved in:
Published in | Technology and health care Vol. 32; no. 2; p. 937 |
---|---|
Main Authors | , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Netherlands
01.01.2024
|
Subjects | |
Online Access | Get more information |
Cover
Loading…
Abstract | Intracranial pressure (ICP) is a vital parameter that is continuously monitored in patients with severe brain injury and imminent intracranial hypertension.
To estimate intracranial pressure without intracranial probes based on transcutaneous near infrared spectroscopy (NIRS).
We developed machine learning based approaches for noninvasive intracranial pressure (ICP) estimation using signals from transcutaneous near infrared spectroscopy (NIRS) as well as other cardiovascular and artificial ventilation parameters.
In a patient cohort of 25 patients, with 22 used for model development and 3 for model testing, the best performing models were Fourier transform based Transformer ICP waveform estimation which produced a mean absolute error of 4.68 mm Hg (SD = 5.4) in estimation.
We did not find a significant improvement in ICP estimation accuracy by including signals measured by transcutaneous NIRS. We expect that with higher quality and greater volume of data, noninvasive estimation of ICP will improve. |
---|---|
AbstractList | Intracranial pressure (ICP) is a vital parameter that is continuously monitored in patients with severe brain injury and imminent intracranial hypertension.
To estimate intracranial pressure without intracranial probes based on transcutaneous near infrared spectroscopy (NIRS).
We developed machine learning based approaches for noninvasive intracranial pressure (ICP) estimation using signals from transcutaneous near infrared spectroscopy (NIRS) as well as other cardiovascular and artificial ventilation parameters.
In a patient cohort of 25 patients, with 22 used for model development and 3 for model testing, the best performing models were Fourier transform based Transformer ICP waveform estimation which produced a mean absolute error of 4.68 mm Hg (SD = 5.4) in estimation.
We did not find a significant improvement in ICP estimation accuracy by including signals measured by transcutaneous NIRS. We expect that with higher quality and greater volume of data, noninvasive estimation of ICP will improve. |
Author | Baumann, Daniel Seric, Marko Narula, Gagan Keller, Emanuela Fröhlich, Jürg Boss, Jens Baumann, Dirk Salles, Joan P Willms, Jan |
Author_xml | – sequence: 1 givenname: Gagan surname: Narula fullname: Narula, Gagan organization: Neurocritical Care Unit, Department of Neurosurgery and Institute of Intensive Care Medicine, Clinical Neuroscience Center, University Hospital Zurich, Zurich, Switzerland – sequence: 2 givenname: Jens surname: Boss fullname: Boss, Jens organization: Neurocritical Care Unit, Department of Neurosurgery and Institute of Intensive Care Medicine, Clinical Neuroscience Center, University Hospital Zurich, Zurich, Switzerland – sequence: 3 givenname: Marko surname: Seric fullname: Seric, Marko organization: Neurocritical Care Unit, Department of Neurosurgery and Institute of Intensive Care Medicine, Clinical Neuroscience Center, University Hospital Zurich, Zurich, Switzerland – sequence: 4 givenname: Daniel surname: Baumann fullname: Baumann, Daniel organization: Neurocritical Care Unit, Department of Neurosurgery and Institute of Intensive Care Medicine, Clinical Neuroscience Center, University Hospital Zurich, Zurich, Switzerland – sequence: 5 givenname: Joan P surname: Salles fullname: Salles, Joan P organization: Luciole Medical AG, Zurich, Switzerland – sequence: 6 givenname: Jürg surname: Fröhlich fullname: Fröhlich, Jürg organization: Luciole Medical AG, Zurich, Switzerland – sequence: 7 givenname: Dirk surname: Baumann fullname: Baumann, Dirk organization: Luciole Medical AG, Zurich, Switzerland – sequence: 8 givenname: Emanuela surname: Keller fullname: Keller, Emanuela organization: Neurocritical Care Unit, Department of Neurosurgery and Institute of Intensive Care Medicine, Clinical Neuroscience Center, University Hospital Zurich, Zurich, Switzerland – sequence: 9 givenname: Jan surname: Willms fullname: Willms, Jan organization: Neurocritical Care Unit, Department of Neurosurgery and Institute of Intensive Care Medicine, Clinical Neuroscience Center, University Hospital Zurich, Zurich, Switzerland |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37483038$$D View this record in MEDLINE/PubMed |
BookMark | eNo1kElOwzAYhS0EogNsOADyBQIe0theoqoMUiU2ZV39OL9bo8SO7CRSr8CpCSqs3ubpe8OCXIYYkJA7zh6kkPJx97ouhGRSmAsy51rpQpWMz8gi5y_GmKyEuSYzqUo9mfScfG9GaAbofQw0OtqCPfqAtEFIwYcDheYQk--PbaYuJjql-TBC9iNSH_oENkHw0NAuYc5DQoq59-2ZN-RfQphQk9clSFjT3KHtU8w2dicKmQK1cYTkoccbcuWgyXj7p0vy8bzZrV-L7fvL2_ppW1ihyr6o9cpUFQcBDqVQaJ2wSilrhTBOl5VYTSOVVU5zNHXJDDcryziXJde14kIsyf2Z2w2fLdb7Lk2F02n_f4r4AZgxZiI |
ContentType | Journal Article |
DBID | CGR CUY CVF ECM EIF NPM |
DOI | 10.3233/THC-230329 |
DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed |
DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) |
DatabaseTitleList | MEDLINE |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
DeliveryMethod | no_fulltext_linktorsrc |
Discipline | Medicine Engineering |
EISSN | 1878-7401 |
ExternalDocumentID | 37483038 |
Genre | Journal Article |
GroupedDBID | --- --K 0R~ 1B1 29Q 36B 4.4 53G 6PF AAFNC AAOTM AAWTL ABDBF ABJNI ABUBZ ACGFS ACIWK ACPQW ACPRK ADZMO AENEX AFRAH AFRHK ALMA_UNASSIGNED_HOLDINGS CAG CGR COF CUY CVF DU5 EAD EAP EAS EBD EBS ECM EHE EHN EIF EJD EMB EMK EMOBN EPL EST ESX F5P HZ~ I-F IHE IL9 IOS M41 MET MIO MV1 NGNOM NPM NQ- O9- RIG ROL RPZ SV3 TUS |
ID | FETCH-LOGICAL-c274t-d859661a2afe327ecf2c777cc229f846253627c7f81e9d409195c0113418d7122 |
IngestDate | Thu May 23 23:30:37 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 2 |
Keywords | spectrum analysis intracranial pressure machine learning Brain injuries |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c274t-d859661a2afe327ecf2c777cc229f846253627c7f81e9d409195c0113418d7122 |
PMID | 37483038 |
ParticipantIDs | pubmed_primary_37483038 |
PublicationCentury | 2000 |
PublicationDate | 2024-01-01 |
PublicationDateYYYYMMDD | 2024-01-01 |
PublicationDate_xml | – month: 01 year: 2024 text: 2024-01-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Netherlands |
PublicationPlace_xml | – name: Netherlands |
PublicationTitle | Technology and health care |
PublicationTitleAlternate | Technol Health Care |
PublicationYear | 2024 |
SSID | ssj0003629 |
Score | 2.3672628 |
Snippet | Intracranial pressure (ICP) is a vital parameter that is continuously monitored in patients with severe brain injury and imminent intracranial hypertension.
To... |
SourceID | pubmed |
SourceType | Index Database |
StartPage | 937 |
SubjectTerms | Algorithms Cerebrovascular Circulation Humans Intracranial Hypertension - diagnosis Intracranial Pressure Spectroscopy, Near-Infrared |
Title | Evaluation of machine learning algorithms for noninvasive intracranial pressure estimation using near infrared spectroscopy as a covariate |
URI | https://www.ncbi.nlm.nih.gov/pubmed/37483038 |
Volume | 32 |
hasFullText | |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Na9wwEBWbFEJ6KG36nbbMobfFrS17I_uYhKRLIDltILcgj6VtIbGXdDeQ_IT-j_7Pzki25S4t_biYxcKL0DxGM08zT0K8z2RcURxfRWVcISUoaRyVstJRXmKCezHKKuZ-59Ozvel5dnIxuRiNvg-qllbL8gPe_7Kv5H-sSu_Irtwl-w-W7f-UXtBvsi89ycL0_CsbH_VS3e6Y3NVFmu4iiPlYX80byv0_e82Fcc3M66129epfmNNF2qeYMHe1sHyQwIobvpVxvHIcQs0yPzTTG1em7royWf2yWdzx_TR6jM0t5dp6-VM9UWDr3cmE77R0Etg986xvVlcuav2k5wGeB-0N7iem7iN9Zu-waypqAu_KZw916JEfkhcyG5AXxjvcXLGeafuu9ciB8ewTY-9eCy8Qs-72U8m09PFsehhRRpV6CmVg_8W1AwAr7dBw_ufRNQnubmhDbKic3egZU0Ltdk8RQOF1b3kaH8MktsVW9-FazuJil9lj8ahNOmDfI-iJGJl6RzwcSFHuiK3TtsjiqfgWYAWNhRZW0MEKAqyAYAUDWMEQVtDBCgKswMEKGFbQwQqGsAL9FTT0sHomzo-PZofTqL2yI0KpsmVU5RPKnxMttTWpVAatRKUUopSFpVBXTmi5FCqbJ6aoMgpWiwnSFkOxVF6pRMrnYpOmbV4KyBJbmDSziTUqQ4slhdIZRaeGdg0jMX8lXvg1vVx4XZbLbrVf_3ZkV2wHFL4RDyw5AvOWospl-c5Z9QcQv3_0 |
link.rule.ids | 786 |
linkProvider | National Library of Medicine |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Evaluation+of+machine+learning+algorithms+for+noninvasive+intracranial+pressure+estimation+using+near+infrared+spectroscopy+as+a+covariate&rft.jtitle=Technology+and+health+care&rft.au=Narula%2C+Gagan&rft.au=Boss%2C+Jens&rft.au=Seric%2C+Marko&rft.au=Baumann%2C+Daniel&rft.date=2024-01-01&rft.eissn=1878-7401&rft.volume=32&rft.issue=2&rft.spage=937&rft_id=info:doi/10.3233%2FTHC-230329&rft_id=info%3Apmid%2F37483038&rft_id=info%3Apmid%2F37483038&rft.externalDocID=37483038 |