OSCR

Survival Outcomes and Machine Learning-Based Prediction of 12-Month Mortality in Glioblastoma Before and During the COVID-19 Pandemic: A SEER Population-Based Study.

Code ↔ Paper

5 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 5 matches · 2 of them tie a paragraph to a whole file, not to given lines: weak matches, whose lines are not tinted
  1. [1] § 3. Results › 3.6. Machine Learning-Based Prediction of 12-Month All-Cause Mortality ↔ seersingle.py, the whole file · a weak match · score 0.73 · Logistic Regression, Gradient Boosting, Random Forest, F1 score, ROC Area, recall
  2. [2] § 3. Results › 3.6. Machine Learning-Based Prediction of 12-Month All-Cause Mortality ↔ seersingle.py, the whole file · a weak match · score 0.70 · Logistic Regression, Gradient Boosting, Random Forest, ROC Area, accuracy, Matthews
  3. [3] § 3. Results › 3.6. Machine Learning-Based Prediction of 12-Month All-Cause Mortality ↔ comparativeroccurves.py, lines 75–108 · score 0.70 · ROC curves, Logistic Regression, Gradient Boosting, Random Forest, AUC, predictive
  4. [4] § 3. Results › 3.6. Machine Learning-Based Prediction of 12-Month All-Cause Mortality ↔ comparativeroccurves.py, lines 75–108 · score 0.68 · ROC curves, Logistic Regression, Gradient Boosting, Random Forest, SVM, AUC
  5. [5] § 2. Materials and Methods › 2.5. Machine Learning Analysis ↔ comparativeroccurves.py, lines 46–73 · score 0.60 · F1 Score, Precision, Recall, Accuracy, weighted, Matthews

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 108 lines · 3.8 KB · no license · 3 matches

  1. # -*- coding: utf-8 -*-
  2. """ComparativeROCcurves.ipynb
  4. Automatically generated by Colab.
  6. Original file is located at
  7. https://colab.research.google.com/drive/1NSO-gesZpx4b5TQWlXh-ko1zO-FoW9s4
  8. """
  10. import pandas as pd
  11. import numpy as np
  12. import matplotlib.pyplot as plt
  13. import seaborn as sns
  14. import shap
  15. from sklearn.model_selection import train_test_split
  16. from sklearn.linear_model import LogisticRegression
  17. from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
  18. from sklearn.svm import SVC
  19. from sklearn.preprocessing import LabelEncoder, StandardScaler
  20. from sklearn.metrics import roc_curve, auc, classification_report, accuracy_score, matthews_corrcoef, roc_auc_score
  22. from google.colab import files
  24. print("Please upload the 'PreCOVID.xlsx' file.")
  25. uploaded = files.upload()
  27. file_path = '/content/PreCOVID.xlsx.csv'
  28. df = pd.read_excel('/content/PreCOVID.xlsx')
  30. # Target: 1 = Alive (Hayatta), 0 = Dead (Vefat)
  31. df['Target'] = 1 - df['mortality_12m_allcause']
  33. features = ['age_group', 'sex', 'race', 'surgery_binary', 'radiation_binary', 'chemotherapy_binary']
  34. X = df[features].copy()
  36. le = LabelEncoder()
  37. for col in X.columns:
  38. X[col] = le.fit_transform(X[col].astype(str))
  40. X_train, X_test, y_train, y_test = train_test_split(X, df['Target'], test_size=0.20, random_state=42)
  42. scaler = StandardScaler()
  43. X_train_sc = scaler.fit_transform(X_train)
  44. X_test_sc = scaler.transform(X_test)
  46. def print_complete_table(y_true, y_pred, y_prob, model_name):
  47. report = classification_report(y_true, y_pred, output_dict=True)
  48. acc_overall = accuracy_score(y_true, y_pred)
  49. mcc_overall = matthews_corrcoef(y_true, y_pred)
  51. rec_dead = report['0']['recall']
  52. rec_alive = report['1']['recall']
  54. roc_dead = roc_auc_score(1-y_true, y_prob[:, 0])
  55. roc_alive = roc_auc_score(y_true, y_prob[:, 1])
  57. sens_overall = report['weighted avg']['recall']
  58. spec_overall = report['weighted avg']['recall']
  60. print(f"\n{'='*25} {model_name} {'='*25}")
  61. print(f"{'Metrik':<15} | {'Dead':<10} | {'Alive':<10} | {'Overall':<10}")
  62. print("-" * 65)
  64. for label, key in [('Precision', 'precision'), ('Recall', 'recall'), ('F-measure', 'f1-score')]:
  65. print(f"{label:<15} | {report['0'][key]:<10.4f} | {report['1'][key]:<10.4f} | {report['weighted avg'][key]:.4f}")
  67. print(f"{'Accuracy':<15} | {rec_dead:<10.4f} | {rec_alive:<10.4f} | {acc_overall:.4f}")
  68. print(f"{'MCC':<15} | {mcc_overall:<10.4f} | {mcc_overall:<10.4f} | {mcc_overall:.4f}")
  70. print(f"{'Sensitivity':<15} | {rec_dead:<10.4f} | {rec_alive:<10.4f} | {sens_overall:.4f}")
  71. print(f"{'Specificity':<15} | {rec_dead:<10.4f} | {rec_alive:<10.4f} | {spec_overall:.4f}")
  73. print(f"{'ROC Area':<15} | {roc_dead:<10.4f} | {roc_alive:<10.4f} | {roc_alive:.4f}")
  75. models = {
  76. "LOGISTIC REGRESSION": LogisticRegression(random_state=42),
  77. "RANDOM FOREST": RandomForestClassifier(n_estimators=100, random_state=42),
  78. "GRADIENT BOOSTING": GradientBoostingClassifier(random_state=42),
  79. "SVM": SVC(probability=True, random_state=42)
  80. }
  82. for name, model in models.items():
  83. model.fit(X_train_sc, y_train)
  84. y_pred = model.predict(X_test_sc)
  85. y_prob = model.predict_proba(X_test_sc)
  86. print_complete_table(y_test, y_pred, y_prob, name)
  88. plt.figure(figsize=(10, 7))
  90. for name, model in models.items():
  91. model.fit(X_train_sc, y_train)
  93. y_prob = model.predict_proba(X_test_sc)[:, 1]
  95. fpr, tpr, _ = roc_curve(y_test, y_prob)
  96. roc_auc = auc(fpr, tpr)
  98. plt.plot(fpr, tpr, lw=2, label=f'{name} (AUC = {roc_auc:.2f})')
  100. plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
  101. plt.xlim([0.0, 1.0])
  102. plt.ylim([0.0, 1.05])
  103. plt.xlabel('False Positive Rate (1 - Specificity)')
  104. plt.ylabel('True Positive Rate (Sensitivity)')
  105. plt.title('Figure 5: ROC Curves for ML Models')
  106. plt.legend(loc="lower right")
  107. plt.grid(alpha=0.3)
  108. plt.show()

comparativeroccurves.py at commit 82a84e7, no license · at the source

Overview

Authors: Yasemin Adalı1,2, Ömer Emin Çınar3,4, Ümit Akın Dere5
ORCID iDs: Yasemin Adalı, Ömer Emin Çınar, Ümit Akın Dere
  1. Centre for Public Health, School of Medicine, Dentistry and Biomedical Sciences, Queen’s University Belfast, Belfast BT7 1NN, UK
  2. Department of Epidemiology, Centre for Public Health, Pamukkale University Faculty of Medicine, Denizli 20070, Türkiye
  3. School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast BT7 1NN, UK
  4. Department of Computer Engineering, Faculty of Engineering and Architecture, Recep Tayyip Erdogan University, Rize 53100, Türkiye
  5. Department of Neurosurgery, Pamukkale University Faculty of Medicine, Denizli 20070, Türkiye
Institutions: Queen's University Belfast (United Kingdom); Pamukkale University (Türkiye); Recep Tayyip Erdoğan University (Türkiye)
Journal: Medicina (Kaunas, Lithuania), volume 62, issue 6, article 1169
Dates: received 11 May 2026; accepted 14 June 2026; published online 16 June 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/medicina62061169 · PMID 42356181 · PMCID PMC13304340 · OpenAlex W7164937537
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: human (organism), other condition (population), clinical / translational (subfield)
Methods: Connectivity, Machine learning, Statistics
Keywords: glioblastoma, COVID-19, cancer epidemiology, SEER, survival analysis, machine learning
MeSH: Brain Neoplasms*, COVID-19*, Glioblastoma*, Machine Learning*, Adult, Aged, Female, Humans, Male, Middle Aged, Predictive Learning Models, SARS-CoV-2, SEER Program, Survival Analysis, United States (* major topic)
Topic: COVID-19 and healthcare impacts (Oncology, Medicine), according to OpenAlex
Funding: Queen's University Belfast; Queen's University; National Cancer Institute
Citations: not cited yet (Europe PMC); 26 references in the paper

Abstract

Background and Objectives: The COVID-19 pandemic disrupted cancer diagnosis and treatment pathways worldwide. Glioblastoma is an aggressive primary brain malignancy requiring timely multimodal care. This study evaluated survival outcomes among glioblastoma patients diagnosed before and during the COVID-19 pandemic and prepared a dataset for machine learning-based prediction of 12-month mortality. Materials and Methods: Patients aged ≥20 years diagnosed with glioblastoma between 2018 and 2021 were identified from the SEER database using ICD-O-3 histology codes 9440/3, 9441/3, and 9442/3. Patients were categorized as pre-COVID period (2018–2019) or COVID period (2020–2021). OS and CSS were evaluated using Kaplan–Meier curves, log-rank tests, and Cox regression models. Machine learning models predicted 12-month all-cause mortality using registry variables. Results: The final cohort included 9914 patients; 4819 were diagnosed pre-COVID and 5095 during COVID. Median OS was 11 months pre-COVID and 10 months during COVID; 12-month OS was 44.3% and 41.2%, respectively. Median CSS was 11 months in both periods; 12-month CSS was 46.9% and 44.1%, respectively. COVID-period diagnosis was modestly associated with poorer OS (adjusted HR 1.050, 95% CI 1.006–1.095, p = 0.025) and CSS (adjusted HR 1.048, 95% CI 1.003–1.095, p = 0.035). Machine learning models showed moderate discrimination for 12-month mortality prediction. Conclusions: Glioblastoma patients diagnosed during the COVID period had modestly poorer OS and CSS in conventional survival analyses; however, competing-risk analysis did not show a significant association with cancer-specific death. Registry-based machine learning models provided moderate 12-month mortality prediction, supporting their potential utility for population-level prognostic assessment.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repository

Its files are read in the Code ↔ Paper reader above, with 5 matches between paragraphs and lines of code.

omerecinar/MDPI-Medicina-Manuscript-Colab-Codes

License: none: the authors keep all their rights
State: the link answers, verified on 27 September 2026
Evidence: files inventoried
Commit: 82a84e7c5ae5c46f864a94cb9d12dc06bb24bceb, 11 May 2026
Languages: Python (4)
Size: 4 files, 4 scripts
Software Heritage: not archived
Found in: “Supplementary Materials”
Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation
Tools: NumPy (4 files), pandas (4 files), Matplotlib (3 files), scikit-learn (3 files), SHAP (3 files), XGBoost (2 files), seaborn (1 file)
Availability: 1 check, the latest on 27 September 2026: the link answers
  • 27 September 2026: the link answers
4 files
At the source: github.com/omerecinar/MDPI-Medicina-Manuscript-Colab-Codes.git

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 4 scripts, each with its path and the digest of its content;
  • 5 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data Availability Statement

The data used in this study are publicly available from the Surveillance, Epidemiology, and End Results (SEER) Program of the National Cancer Institute upon completion of the SEER Research Data Agreement. Data were extracted using SEER*Stat software version 9.0.42.2 from the “Incidence-SEER Research Data, 17 Registries, November 2024 Submission, released April 2025” database. Data access was granted under SEER Research Data Agreement number SAR0115042. No new data were created in this study.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 2, 28 September 2026

  • Funding: added Queen's University Belfast; Queen's University; National Cancer Institute

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 3 authors, 6 keywords, 15 MeSH terms, 26 references.

Cite

This paper

Adalı, Y., Çınar, Ö. E., & Dere, Ü. A. (2026). Survival Outcomes and Machine Learning-Based Prediction of 12-Month Mortality in Glioblastoma Before and During the COVID-19 Pandemic: A SEER Population-Based Study. Medicina (Kaunas, Lithuania), 62(6), 1169. https://doi.org/10.3390/medicina62061169

BibTeX

@article{adal2026survival,
author = {Adalı, Yasemin and Çınar, Ömer Emin and Dere, Ümit Akın},
title = {{Survival Outcomes and Machine Learning-Based Prediction of 12-Month Mortality in Glioblastoma Before and During the COVID-19 Pandemic: A SEER Population-Based Study}},
journal = {Medicina (Kaunas, Lithuania)},
year = {2026},
month = jun,
volume = {62},
number = {6},
pages = {1169},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {1010-660X},
doi = {10.3390/medicina62061169},
url = {https://doi.org/10.3390/medicina62061169},
pmid = {42356181},
pmcid = {PMC13304340}
}

RIS

TY - JOUR
AU - Adalı, Yasemin
AU - Çınar, Ömer Emin
AU - Dere, Ümit Akın
TI - Survival Outcomes and Machine Learning-Based Prediction of 12-Month Mortality in Glioblastoma Before and During the COVID-19 Pandemic: A SEER Population-Based Study
T2 - Medicina (Kaunas, Lithuania)
J2 - Medicina (Kaunas)
PY - 2026
DA - 2026/06/16
VL - 62
IS - 6
SP - 1169
SN - 1010-660X
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/medicina62061169
UR - https://doi.org/10.3390/medicina62061169
LA - en
ER -

CSL-JSON

{
"id": "10.3390/medicina62061169",
"type": "article-journal",
"title": "Survival Outcomes and Machine Learning-Based Prediction of 12-Month Mortality in Glioblastoma Before and During the COVID-19 Pandemic: A SEER Population-Based Study",
"container-title": "Medicina (Kaunas, Lithuania)",
"author": [
{
"family": "Adalı",
"given": "Yasemin"
},
{
"family": "Çınar",
"given": "Ömer Emin"
},
{
"family": "Dere",
"given": "Ümit Akın"
}
],
"container-title-short": "Medicina (Kaunas)",
"volume": "62",
"issue": "6",
"page": "1169",
"DOI": "10.3390/medicina62061169",
"PMID": "42356181",
"PMCID": "PMC13304340",
"ISSN": "1010-660X",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/medicina62061169",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
16
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1016/j.isci.2026.115329 [code]
Brain metastases converge on shared geometric architecture and transcriptomic landscape yet remain distinct from gliomas.
Journal: iScience
In common: SHAP, XGBoost, seaborn, 4 other tools, clinical / translational, other condition
[2] doi:10.1073/pnas.2516601123 [code]
Unveiling the glymphatic system's role in brain aging: A comprehensive biomarker and modifiable intervention target.
Journal: Proceedings of the National Academy of Sciences of the United States of America
In common: SHAP, XGBoost, seaborn, 4 other tools, clinical / translational
[3] doi:10.1038/s41467-026-71555-0 [code]
A deep representation learning model to predict response to vagus nerve stimulation.
Journal: Nature communications
In common: SHAP, XGBoost, seaborn, 4 other tools, clinical / translational
[4] doi:10.1038/s41467-026-76837-1 [code]
Drug screen and machine learning predict neuroprotective agents in a preclinical human model of childhood dementia.
Journal: Nature communications
In common: SHAP, XGBoost, seaborn, 4 other tools, other condition
[5] doi:10.1016/j.nicl.2026.104012 [code]
Structural-functional multilayer brain network properties and outcome of combined repetitive transcranial magnetic stimulation and psychotherapy for obsessive-compulsive disorder.
Journal: NeuroImage. Clinical
In common: SHAP, XGBoost, seaborn, 4 other tools, other condition
[6] doi:10.1093/braincomms/fcag079 [code]
Machine learning-based combination of the central vein sign, cortical lesions and paramagnetic rim lesions: a web-based tool for the diagnosis of multiple sclerosis.
Journal: Brain communications
In common: SHAP, XGBoost, seaborn, 4 other tools, clinical / translational
[7] doi:10.3389/fnins.2026.1803154 [code]
Multimodal machine learning reveals neurobiological signatures of binge-type eating disorders.
Journal: Frontiers in neuroscience
In common: SHAP, XGBoost, seaborn, 4 other tools, other condition
[8] doi:10.1038/s42003-026-10957-8 [code]
Brain defence by the extracellular matrix protein Cochlin.
Journal: Communications biology
In common: SHAP, XGBoost, seaborn, 4 other tools
[9] doi:10.3390/s26175327 [code]
Subject Identity Confounds qEEG Emotion Recognition on DEAP and DREAMER.
Journal: Sensors (Basel, Switzerland)
In common: SHAP, XGBoost, seaborn, 4 other tools
[10] doi:10.1371/journal.pcbi.1014615 [code]
Toward reliable machine learning models for neural circuit inference: A diagnostic study of CNNs on spike trains.
Journal: PLoS computational biology
In common: SHAP, XGBoost, seaborn, 4 other tools

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.