Features - Oncology Data to Lancet

# GLOBOCAN Data Integration

from oncology.data import globocan

# Fetch lung cancer data for 185 countries

data = globocan.fetch(

  cancer_type="lung",

  year=2022,

  metrics=["incidence", "mortality"]

)

# Auto-harmonize country codes

data = globocan.harmonize(data)

GLOBOCAN Data Integration

Direct API access to IARC's Global Cancer Observatory. Fetch incidence, mortality, and prevalence data for 36 cancer types across 185 countries. Automatic data harmonization ensures consistency across different coding systems.

Real-time data synchronization with GLOBOCAN 2022
Automatic ISO country code harmonization
Age-standardized rate (ASR) calculation
Temporal trend analysis across multiple editions
Downloadable raw data with metadata

# Advanced Statistical Analysis

from oncology.stats import AnalysisEngine

engine = AnalysisEngine(data)

# Joinpoint regression for trend detection

trends = engine.joinpoint(

  variable="asr",

  segment_type="log-linear"

)

# APC modeling with age-period-cohort

apc = engine.apc_model(

  drift=True,

  confidence=0.95

)

AI Statistical Engine

Our AI-powered statistical engine automatically selects the most appropriate analytical methods for your data. From basic descriptive statistics to advanced epidemiological models, every analysis follows best practices recommended by top journals.

Joinpoint regression for trend change detection
Age-Period-Cohort (APC) modeling
Negative binomial regression for overdispersed counts
Bayesian spatial analysis for geographic patterns
Competing risk survival analysis
Automatic assumption checking and diagnostics

# Publication-Ready Visualization

from oncology.viz import ChartGenerator

viz = ChartGenerator(style="lancet")

# Generate forest plot

fig = viz.forest_plot(

  data=results,

  effect="HR",

  ci=0.95,

  dpi=300

)

# Export for submission

fig.save("figure1.tiff")

Publication-Ready Visualizations

Generate publication-quality figures that meet The Lancet's strict formatting requirements. Every chart is automatically styled with proper fonts, dimensions, and resolution for journal submission.

Forest plots with heterogeneity metrics
Kaplan-Meier survival curves with risk tables
Choropleth maps for geographic distribution
Trend plots with confidence intervals
Stacked bar charts for cancer type breakdown
Export at 300+ DPI in TIFF, EPS, or PNG

# Auto-Generate Lancet Manuscript

from oncology.paper import ManuscriptGenerator

gen = ManuscriptGenerator(

  journal="lancet",

  format="original_article"

)

# Generate complete manuscript

manuscript = gen.generate(

  analysis=results,

  figures=figs,

  tables=tables

)

# Export as DOCX

manuscript.export("manuscript.docx")

Lancet Manuscript Generator

Transform your analysis results into a complete Lancet-format manuscript. Our AI generates structured sections following the journal's guidelines, including proper formatting for abstracts, methods, results, and discussion.

Structured abstract with objectives, methods, findings, interpretation
STROBE-compliant methods section
Auto-formatted results with confidence intervals
Context-aware discussion with recent references
Table legends and figure captions
Export as DOCX, LaTeX, or Markdown

# Peer Review Simulation

from oncology.review import PeerReviewer

reviewer = PeerReviewer(

  journal="lancet",

  rigor="high"

)

# Run pre-submission review

report = reviewer.review(

  manuscript=ms,

  check_strobe=True,

  check_stats=True

)

# Get improvement suggestions

report.print_issues()

Peer Review Assistant

Before submitting to The Lancet, run your manuscript through our AI-powered peer review simulation. We check for common methodological issues, statistical reporting errors, and STROBE compliance to maximize your chances of acceptance.

STROBE checklist automated verification
Statistical method appropriateness checking
Sample size and power analysis validation
Reference completeness and recency check
Writing quality and clarity assessment
Actionable improvement suggestions

# SEER Data Analysis

from oncology.data import SEERClient

seer = SEERClient(api_key="your_key")

# Fetch survival data

survival = seer.fetch_survival(

  cancer="breast",

  stage="all",

  years=range(2000, 2023)

)

# 5-year relative survival

rates = seer.survival_rate(

  data=survival,

  period=5

)

SEER Program Integration

Access NCI's Surveillance, Epidemiology, and End Results program data directly. Analyze cancer survival trends, incidence patterns, and demographic breakdowns for the US population with our streamlined SEER API integration.

Direct access to SEER*Stat database
Relative survival analysis by stage and demographics
Trend analysis with annual percent change (APC)
Age-adjusted rate calculations
Conditional survival estimates
Stage-shift analysis over time

Technology Stack

Built with Modern Research Tools

Our platform leverages the latest advances in data science, epidemiology, and AI.

🐍 Python 3.11+

Core analytics engine built on Python with pandas, NumPy, and scipy for robust data processing.

📊 R Integration

Seamless R integration for specialized epidemiological packages like Epi, NCC, and APC.

🤖 LLM-Powered

Large language models for manuscript generation, peer review simulation, and methodology suggestions.

⚡ FastAPI Backend

High-performance async API for real-time data processing and analysis submission.

📈 Plotly & Matplotlib

Publication-quality static and interactive visualizations with customizable themes.

🔒 Secure & Compliant

GDPR-compliant data handling, encrypted storage, and audit logging for sensitive research data.

Platform Features