PMID- 38139230
OWN - NLM
STAT- MEDLINE
DCOM- 20231225
LR  - 20240210
IS  - 1422-0067 (Electronic)
IS  - 1422-0067 (Linking)
VI  - 24
IP  - 24
DP  - 2023 Dec 12
TI  - Prioritization of Fluorescence In Situ Hybridization (FISH) Probes for 
      Differentiating Primary Sites of Neuroendocrine Tumors with Machine Learning.
LID - 10.3390/ijms242417401 [doi]
LID - 17401
AB  - Determining neuroendocrine tumor (NET) primary sites is pivotal for patient care 
      as pancreatic NETs (pNETs) and small bowel NETs (sbNETs) have distinct treatment 
      approaches. The diagnostic power and prioritization of fluorescence in situ 
      hybridization (FISH) assay biomarkers for establishing primary sites has not been 
      thoroughly investigated using machine learning (ML) techniques. We trained ML 
      models on FISH assay metrics from 85 sbNET and 59 pNET samples for primary site 
      prediction. Exploring multiple methods for imputing missing data, the 
      impute-by-median dataset coupled with a support vector machine model achieved the 
      highest classification accuracy of 93.1% on a held-out test set, with the top 
      importance variables originating from the ERBB2 FISH probe. Due to the greater 
      interpretability of decision tree (DT) models, we fit DT models to ten dataset 
      splits, achieving optimal performance with k-nearest neighbor (KNN) imputed data 
      and a transformation to single categorical biomarker probe variables, with a mean 
      accuracy of 81.4%, on held-out test sets. ERBB2 and MET variables ranked as 
      top-performing features in 9 of 10 DT models and the full dataset model. These 
      findings offer probabilistic guidance for FISH testing, emphasizing the 
      prioritization of the ERBB2, SMAD4, and CDKN2A FISH probes in diagnosing NET 
      primary sites.
FAU - Pietan, Lucas
AU  - Pietan L
AD  - Interdisciplinary Graduate Program in Genetics, University of Iowa, Iowa City, IA 
      52242, USA.
AD  - Department of Biomedical Engineering, University of Iowa, Iowa City, IA 52242, 
      USA.
FAU - Vaughn, Hayley
AU  - Vaughn H
AD  - Interdisciplinary Graduate Program in Genetics, University of Iowa, Iowa City, IA 
      52242, USA.
AD  - Stead Family Department of Pediatrics, University of Iowa, Iowa City, IA 52242, 
      USA.
FAU - Howe, James R
AU  - Howe JR
AUID- ORCID: 0000-0001-5312-5972
AD  - Healthcare Department of Surgery, University of Iowa, Iowa City, IA 52242, USA.
FAU - Bellizzi, Andrew M
AU  - Bellizzi AM
AD  - Department of Pathology, University of Iowa, Iowa City, IA 52242, USA.
FAU - Smith, Brian J
AU  - Smith BJ
AD  - Department of Biostatistics, University of Iowa, Iowa City, IA 52242, USA.
FAU - Darbro, Benjamin
AU  - Darbro B
AD  - Interdisciplinary Graduate Program in Genetics, University of Iowa, Iowa City, IA 
      52242, USA.
AD  - Stead Family Department of Pediatrics, University of Iowa, Iowa City, IA 52242, 
      USA.
FAU - Braun, Terry
AU  - Braun T
AD  - Interdisciplinary Graduate Program in Genetics, University of Iowa, Iowa City, IA 
      52242, USA.
AD  - Department of Biomedical Engineering, University of Iowa, Iowa City, IA 52242, 
      USA.
AD  - Center for Bioinformatics and Computational Biology, University of Iowa, Iowa 
      City, IA 52242, USA.
FAU - Casavant, Thomas
AU  - Casavant T
AD  - Interdisciplinary Graduate Program in Genetics, University of Iowa, Iowa City, IA 
      52242, USA.
AD  - Department of Biomedical Engineering, University of Iowa, Iowa City, IA 52242, 
      USA.
AD  - Center for Bioinformatics and Computational Biology, University of Iowa, Iowa 
      City, IA 52242, USA.
AD  - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, 
      IA 52242, USA.
LA  - eng
GR  - P50 CA174521/CA/NCI NIH HHS/United States
GR  - T32 GM008629/GM/NIGMS NIH HHS/United States
GR  - T32 GM 008629/NH/NIH HHS/United States
PT  - Journal Article
DEP - 20231212
PL  - Switzerland
TA  - Int J Mol Sci
JT  - International journal of molecular sciences
JID - 101092791
SB  - IM
MH  - Humans
MH  - *Neuroendocrine Tumors/diagnosis/genetics/pathology
MH  - In Situ Hybridization, Fluorescence
MH  - *Intestinal Neoplasms/pathology
MH  - *Pancreatic Neoplasms/pathology
MH  - Machine Learning
PMC - PMC10743810
OTO - NOTNLM
OT  - biomarker
OT  - fluorescence in situ hybridization
OT  - imputation
OT  - machine learning
OT  - model
OT  - neuroendocrine tumor
COIS- The authors declare no conflict of interest.
EDAT- 2023/12/23 12:43
MHDA- 2023/12/25 06:42
PMCR- 2023/12/12
CRDT- 2023/12/23 01:21
PHST- 2023/10/31 00:00 [received]
PHST- 2023/11/29 00:00 [revised]
PHST- 2023/12/06 00:00 [accepted]
PHST- 2023/12/25 06:42 [medline]
PHST- 2023/12/23 12:43 [pubmed]
PHST- 2023/12/23 01:21 [entrez]
PHST- 2023/12/12 00:00 [pmc-release]
AID - ijms242417401 [pii]
AID - ijms-24-17401 [pii]
AID - 10.3390/ijms242417401 [doi]
PST - epublish
SO  - Int J Mol Sci. 2023 Dec 12;24(24):17401. doi: 10.3390/ijms242417401.