PMID- 35532797
OWN - NLM
STAT- MEDLINE
DCOM- 20221107
LR  - 20221210
IS  - 1432-0711 (Electronic)
IS  - 0932-0067 (Print)
IS  - 0932-0067 (Linking)
VI  - 306
IP  - 6
DP  - 2022 Dec
TI  - A machine learning approach applied to gynecological ultrasound to predict 
      progression-free survival in ovarian cancer patients.
PG  - 2143-2154
LID - 10.1007/s00404-022-06578-1 [doi]
AB  - In a growing number of social and clinical scenarios, machine learning (ML) is 
      emerging as a promising tool for implementing complex multi-parametric 
      decision-making algorithms. Regarding ovarian cancer (OC), despite the 
      standardization of features that can support the discrimination of ovarian masses 
      into benign and malignant, there is a lack of accurate predictive modeling based 
      on ultrasound (US) examination for progression-free survival (PFS). This 
      retrospective observational study analyzed patients with epithelial ovarian 
      cancer (EOC) who were followed in a tertiary center from 2018 to 2019. 
      Demographic features, clinical characteristics, information about the surgery and 
      post-surgery histopathology were collected. Additionally, we recorded data about 
      US examinations according to the International Ovarian Tumor Analysis (IOTA) 
      classification. Our study aimed to realize a tool to predict 12 month PFS in 
      patients with OC based on a ML algorithm applied to gynecological ultrasound 
      assessment. Proper feature selection was used to determine an attribute core set. 
      Three different machine learning algorithms, namely Logistic Regression (LR), 
      Random Forest (RFF), and K-nearest neighbors (KNN), were then trained and 
      validated with five-fold cross-validation to predict 12 month PFS. Our analysis 
      included n. 64 patients and 12 month PFS was achieved by 46/64 patients (71.9%). 
      The attribute core set used to train machine learning algorithms included age, 
      menopause, CA-125 value, histotype, FIGO stage and US characteristics, such as 
      major lesion diameter, side, echogenicity, color score, major solid component 
      diameter, presence of carcinosis. RFF showed the best performance (accuracy 
      93.7%, precision 90%, recall 90%, area under receiver operating characteristic 
      curve (AUROC) 0.92). We developed an accurate ML model to predict 12 month PFS.
CI  - (c) 2022. The Author(s).
FAU - Arezzo, Francesca
AU  - Arezzo F
AUID- ORCID: 0000-0002-8914-9594
AD  - Department of Biomedical Sciences and Human Oncology, Obstetrics and Gynecology 
      Unit, University of Bari "Aldo Moro", Piazza Giulio Cesare 11, 70124, Bari, 
      Italy. francesca.arezzo@uniba.it.
FAU - Cormio, Gennaro
AU  - Cormio G
AD  - Department of Biomedical Sciences and Human Oncology, Obstetrics and Gynecology 
      Unit, University of Bari "Aldo Moro", Piazza Giulio Cesare 11, 70124, Bari, 
      Italy.
FAU - La Forgia, Daniele
AU  - La Forgia D
AD  - Department of Breast Radiology, Giovanni Paolo II I.R.C.C.S. Cancer Institute, 
      via Orazio Flacco 65, 70124, Bari, Italy.
FAU - Santarsiero, Carla Mariaflavia
AU  - Santarsiero CM
AD  - Department of Biomedical Sciences and Human Oncology, Obstetrics and Gynecology 
      Unit, University of Bari "Aldo Moro", Piazza Giulio Cesare 11, 70124, Bari, 
      Italy.
FAU - Mongelli, Michele
AU  - Mongelli M
AD  - Department of Biomedical Sciences and Human Oncology, Obstetrics and Gynecology 
      Unit, University of Bari "Aldo Moro", Piazza Giulio Cesare 11, 70124, Bari, 
      Italy.
FAU - Lombardi, Claudio
AU  - Lombardi C
AD  - Department of Biomedical Sciences and Human Oncology, Obstetrics and Gynecology 
      Unit, University of Bari "Aldo Moro", Piazza Giulio Cesare 11, 70124, Bari, 
      Italy.
FAU - Cazzato, Gerardo
AU  - Cazzato G
AD  - Department of Emergency and Organ Transplantation, Pathology Section, University 
      of Bari "Aldo Moro", Piazza Giulio Cesare 11, 70124, Bari, Italy.
FAU - Cicinelli, Ettore
AU  - Cicinelli E
AD  - Department of Biomedical Sciences and Human Oncology, Obstetrics and Gynecology 
      Unit, University of Bari "Aldo Moro", Piazza Giulio Cesare 11, 70124, Bari, 
      Italy.
FAU - Loizzi, Vera
AU  - Loizzi V
AD  - Interdisciplinar Department of Medicine, Obstetrics and Gynecology Unit, 
      University of Bari "Aldo Moro", Piazza Giulio Cesare 11, 70124, Bari, Italy.
LA  - eng
PT  - Journal Article
PT  - Observational Study
PT  - Research Support, Non-U.S. Gov't
DEP - 20220509
PL  - Germany
TA  - Arch Gynecol Obstet
JT  - Archives of gynecology and obstetrics
JID - 8710213
SB  - IM
MH  - Humans
MH  - Female
MH  - Carcinoma, Ovarian Epithelial/diagnostic imaging
MH  - Progression-Free Survival
MH  - *Machine Learning
MH  - *Ovarian Neoplasms/diagnostic imaging/surgery/pathology
MH  - Ultrasonography
PMC - PMC9633520
OTO - NOTNLM
OT  - Gynecological ultrasound
OT  - Machine learning
OT  - Ovarian cancer
OT  - Progression-free survival
COIS- The authors have no relevant financial or non-financial interests to disclose.
EDAT- 2022/05/10 06:00
MHDA- 2022/11/08 06:00
PMCR- 2022/05/09
CRDT- 2022/05/09 11:14
PHST- 2022/02/21 00:00 [received]
PHST- 2022/04/12 00:00 [accepted]
PHST- 2022/05/10 06:00 [pubmed]
PHST- 2022/11/08 06:00 [medline]
PHST- 2022/05/09 11:14 [entrez]
PHST- 2022/05/09 00:00 [pmc-release]
AID - 10.1007/s00404-022-06578-1 [pii]
AID - 6578 [pii]
AID - 10.1007/s00404-022-06578-1 [doi]
PST - ppublish
SO  - Arch Gynecol Obstet. 2022 Dec;306(6):2143-2154. doi: 10.1007/s00404-022-06578-1. 
      Epub 2022 May 9.