Machine Learning Model to Help Predict Survival Among Patients With OSCC: This cohort study describes a model using machine learning to help predict 5-year overall survival among patients with oral squamous cell carcinoma (OSCC) and compares this model with a prediction model created from the TNM (Tumor, Node, Metastasis) clinical and pathologic stage.
Omar A. Karadaghy, MD1; Matthew Shew, MD1; Jacob New, PhD2; et alAndrés M. Bur, MD1
Author Affiliations
1Department of Otolaryngology–Head and Neck Surgery, University of Kansas Medical Center, Kansas City
2University of Kansas Medical Center, School of Medicine, Kansas City
JAMA Otolaryngol Head Neck Surg. 2019;145(12):1115-1120. doi:10.1001/jamaoto.2019.0981
Full
Text
Key Points
Question How can machine learning be used to further our ability to create prediction models for survival of oral cancer?
Findings In this cohort study of more than 30 000 patients, a prediction model using a variety of patients, tumors, treatment facilities, and treatment types predicted 5-year overall survival with an accuracy of 71%, precision of 71%, and recall of 68%.
Meaning Novel machine learning forms of analysis may help in the creation of prediction models using large data registries, and the inclusion of several aspects of the health status of a patient with cancer can more accurately predict survival.
Abstract
Importance Predicting survival of oral squamous cell carcinoma through the use of prediction modeling has been underused, and the development of prediction models would augment clinicians’ ability to provide absolute risk estimates for individual patients.
Objectives To develop a prediction model using machine learning for 5-year overall survival among patients with oral squamous cell carcinoma and compare this model with a prediction model created from the TNM (Tumor, Node, Metastasis) clinical and pathologic stage.
Design, Setting, and Participants A retrospective cohort study was conducted of 33 065 patients with oral squamous cell carcinoma from the National Cancer Data Base between January 1, 2004, and December 31, 2011. Patients were excluded if the treatment was considered palliative, staging demonstrated T0 or Tis, or survival or staging data were missing. Patient, tumor, treatment, and outcome information were obtained from the National Cancer Data Base. The data were split into a distribution of 80% for training and 20% for testing. The model was created using 2-class decision forest architecture. Permutation feature importance scores were used to determine the variables that were used in the model’s prediction and their order of significance. Statistical analysis was conducted from August 1, 2018, to January 10, 2019.
Main Outcomes and Measures Ability to predict 5-year overall survival assessed through area under the curve, accuracy, precision, and recall.
Results Among the 33 065 patients in the study, the mean (SD) age was 64.6 (14.0) years, 19 791 were men (59.9%), 13 274 were women (40.1%), and 29 783 (90.1%) were white. At 60 months, there were 16 745 deaths (50.6%). The median time of follow-up was 56.8 months (range, 0-155.6 months). Age, pathologic T stage, positive margins at the time of surgery, lymph node size, and institutional identification were identified among the most significant variables. The calculated area under the curve for this machine learning model was 0.80 (95% CI, 0.79-0.81), accuracy was 71%, precision was 71%, and recall was 68%. In comparison, the calculated area under the curve of the TNM staging system was 0.68 (95% CI, 0.67-0.70), accuracy was 65%, precision was 69%, and recall was 52%.
Conclusions and Relevance Using machine learning algorithms, a prediction model was created based on patient social, demographic, clinical, and pathologic features. The developed prediction model proved to be better than a prediction model that exclusively used TNM pathologic and clinical stage according to all performance metrics. This study highlights the role that machine learning may play in individual patient risk estimation in the era of big data.
Medicine by Alexandros G. Sfakianakis,Anapafseos 5 Agios Nikolaos 72100 Crete Greece,00302841026182,00306932607174,alsfakia@gmail.com,
Πληροφορίες
Ετικέτες
Πέμπτη 19 Δεκεμβρίου 2019
Machine Learning Model to Help Predict Survival Among Patients With OSCC
Αναρτήθηκε από
Medicine by Alexandros G. Sfakianakis,Anapafseos 5 Agios Nikolaos 72100 Crete Greece,00302841026182,00306932607174,alsfakia@gmail.com,
στις
11:33 μ.μ.
Ετικέτες
00302841026182,
00306932607174,
alsfakia@gmail.com,
Anapafseos 5 Agios Nikolaos 72100 Crete Greece,
Medicine by Alexandros G. Sfakianakis,
Telephone consultation 11855 int 1193
Εγγραφή σε:
Σχόλια ανάρτησης (Atom)
Αρχειοθήκη ιστολογίου
-
►
2023
(276)
- ► Φεβρουαρίου (133)
- ► Ιανουαρίου (143)
-
►
2022
(1976)
- ► Δεκεμβρίου (116)
- ► Σεπτεμβρίου (158)
- ► Φεβρουαρίου (165)
- ► Ιανουαρίου (161)
-
►
2021
(3661)
- ► Δεκεμβρίου (161)
- ► Σεπτεμβρίου (274)
- ► Φεβρουαρίου (64)
- ► Ιανουαρίου (368)
-
►
2020
(4554)
- ► Δεκεμβρίου (400)
- ► Σεπτεμβρίου (381)
- ► Φεβρουαρίου (638)
- ► Ιανουαρίου (691)
-
▼
2019
(4999)
-
▼
Δεκεμβρίου
(924)
- Happy New Year ! God is our strength. Let Him be t...
- Inability to close mouth and dysphagia caused by p...
- Piperacillin-tazobactam induced bicytopenia in low...
- Acute cerebellar ataxia due to Epstein-Barr virus ...
- Pericardial knock
- Paternal uniparental disomy for chromosome 14: pre...
- Chronic mesenteric ischaemia masked by candida eso...
- History, treatment and analysis of a rare form of ...
- History, treatment and analysis of a rare form of ...
- Extracellular Vesicles from Mesenchymal Stem Cells...
- Signaling Network of Forkhead Family of Transcript...
- Csf1 Deficiency Dysregulates Glial Responses to De...
- Spontaneous Ultraslow Na+ Fluctuations in the Neon...
- Journal of Voice
- Thorough performance evaluation of 213 nm ultravio...
- The Xylella fastidiosa-Resistant Olive Cultivar “L...
- GEO series published today
- Comparative Pharmacokinetic Study of Taxifolin aft...
- Investigating Prime-Pull Vaccination through a Com...
- New GEO Series
- Transcription profiling of dendritic cells differe...
- Chemotherapeutic remodeling of the gut microbiome ...
- DNA methylation and hydroxymethylation mediated ge...
- The histone methyltransferase SETDB1 contributes t...
- HIF1α/HIF2α-miR210-3p network promotes glioblastom...
- H3K27Ac ChIP-seq on Patient Dirived Xenograft (PDX...
- CRISPR/Cas9-mediated gene correction in newborn ra...
- Genome-wide localisation of histone H3S57ph in pro...
- Pathway level gating of auxin signalling provides ...
- Single cell transcriptome sequencing of gastric ca...
- Whole kidneys at embryonic day 16.5: wildtype (WT)...
- Antifungal Activity of Beauveria bassiana Endophyt...
- Immune Responses after Vascular Photodynamic Thera...
- One Anastomosis Gastric Bypass Reconstitutes the A...
- Immune Checkpoint Inhibitor Rechallenge in Patient...
- Ontogenetic Pattern Changes of Nucleobindin-2/Nesf...
- Latent Tuberculosis Infection Treatment Completion...
- The Chromatin Remodelling Contributions of Snf2l i...
- CD271/p75NTR is a novel diagnostic marker, prognos...
- Chemogenomic profiling of breast cancer patient-de...
- Sequencing of canine and genetically-engineered mo...
- Telomeres suppress the activity of retrotransposon...
- Bu Shen Zhu Yun Decoction Improves Endometrial Rec...
- Multicentre, non-interventional study of the effic...
- Finding/identifying primaries with neck disease (F...
- Intermittent theta burst stimulation applied durin...
- Multidimensional impact of severe mental illness o...
- Clinical evaluation of percutaneous transforaminal...
- Digital phenotyping for assessment and prediction ...
- Research priorities in children requiring elective...
- Complications after surgery for benign prostatic e...
- Identifying patient concerns during consultations ...
- Better before-better after: efficacy of prehabilit...
- Elderly migrants : Effect of social integration on...
- Pattern and probability of dispensing of prescript...
- Improving mental health and physiological stress r...
- B!RTH: a mixed-methods survey of audience members ...
- Vitamin D in the prevention of exacerbations of as...
- Advanced practice nurses, registered nurses and me...
- Complement activation in individuals with previous...
- Thyroid Hormone Receptor β Inhibits Self-Renewal C...
- Macrofollicular Variant of Follicular Thyroid Carc...
- Trained immunity confers broad-spectrum protection...
- IGFBP7 acts as a negative regulator of RANKL‐induc...
- Subgingival Instrumentation for Treatment of Perio...
- The Spine Functional Index
- Sarcomatoid Dedifferentiation in Renal Cell Carcin...
- Negative Impact of Wound Complications on Oncologi...
- Nanoformulated Zoledronic Acid Boosts the Vδ2 T Ce...
- Autophagy in the Immunosuppressive Perivascular Mi...
- Molecular Profiling of Atypical Tenosynovial Giant...
- Biomarkers of meat and seafood intake: an extensiv...
- Non ‐alcoholic steatohepatitis mimicking solitary ...
- Diffusion-Weighted MR Imaging of Primary and Secon...
- Clear cell carcinoma of the anterior abdominal wal...
- Sister Mary Joseph nodule: an often overlooked or ...
- Superb microvascular imaging technique in depictin...
- Protean Manifestations and Diagnostic Challenges I...
- Thyroid Dose Estimates for a Cohort of Belarusian ...
- Dose to Medical Personnel
- Factors Determining Work Arduousness Levels among ...
- Treatment of Miller Class I Gingival Recession wit...
- Vitamin K and Bone Health: A Review on the Effects...
- Laparoscopic Partial Nephrectomy for cT1 Tumors
- A Non-Interventional Pilot Study to Explore the Ro...
- Anlotinib Combined With TACE in Hepatocellular Car...
- Testing the Addition of the Immunotherapy Drug, Pe...
- Management of Cognitive Difficulties After Cancer ...
- Nab-paclitaxel Versus Topotecan As Second-Line Tre...
- Sintilimab Combined With Bevacizumab for Brain Met...
- SHR-1210 Combined With Albumin-bound Paclitaxel an...
- Heated Intra-peritoneal Chemotherapy With Doxorubi...
- Ribociclib and Spartalizumab in R/M HNSCC
- Biomolecules, Vol. 10, Pages 66: The Emerging Role...
- Evaluating the effectiveness of adjuvant radiother...
- Examining seasonal variation in epistaxis in a mar...
- Is the survival rate for acral melanoma actually w...
- The Improved Effects of a Multidisciplinary Team o...
- Treatment of an Adult Skeletal Class III Patient w...
- Significant influencing factors and practical solu...
- ► Σεπτεμβρίου (845)
-
▼
Δεκεμβρίου
(924)
Δεν υπάρχουν σχόλια:
Δημοσίευση σχολίου