# sowmiya-gowda/ml-and-dl-tb-detection architecture

> Architecture diagram of the GitHub repository sowmiya-gowda/ml-and-dl-tb-detection, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sowmiya-gowda/ml-and-dl-tb-detection
- Repository: https://github.com/sowmiya-gowda/ml-and-dl-tb-detection

## Overview

This repository presents an early-stage TB prediction model in a single notebook. The documented workflow selects relevant clinical predictors, combines classifiers, and targets diagnostic screening with improved accuracy, recall/F1, and ROC-AUC. The notebook itself was not excerpted, so the graph reflects only the README’s stated workflow; implementation details and additional data or evaluation stages are not verified.

Main entry points: [`TB.ipynb`](https://github.com/sowmiya-gowda/ml-and-dl-tb-detection/blob/main/TB.ipynb) (Ensemble classifiers)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_prediction["TB prediction"]
  node_selection["Feature selection<br/>[TB.ipynb]"]
  node_ensemble["Ensemble classifiers<br/>[TB.ipynb]"]
  node_screening["TB screening prediction<br/>[TB.ipynb]"]
  node_performance["Diagnostic performance<br/>[TB.ipynb]"]
end

node_clinical["Clinical predictors"]

node_clinical -->|"selects features"| node_selection
node_selection -->|"supplies predictors"| node_ensemble
node_ensemble -->|"predicts TB"| node_screening
node_ensemble -->|"improves metrics"| node_performance

click node_selection "https://github.com/sowmiya-gowda/ml-and-dl-tb-detection/blob/main/TB.ipynb"
click node_ensemble "https://github.com/sowmiya-gowda/ml-and-dl-tb-detection/blob/main/TB.ipynb"
click node_screening "https://github.com/sowmiya-gowda/ml-and-dl-tb-detection/blob/main/TB.ipynb"
click node_performance "https://github.com/sowmiya-gowda/ml-and-dl-tb-detection/blob/main/TB.ipynb"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_selection,node_ensemble,node_screening,node_performance toneBlue
class node_clinical toneIndigo
```

## Components

### TB prediction

- [Feature selection](https://github.com/sowmiya-gowda/ml-and-dl-tb-detection/blob/main/TB.ipynb): `TB.ipynb`
- [Ensemble classifiers](https://github.com/sowmiya-gowda/ml-and-dl-tb-detection/blob/main/TB.ipynb): `TB.ipynb`
- [TB screening prediction](https://github.com/sowmiya-gowda/ml-and-dl-tb-detection/blob/main/TB.ipynb): `TB.ipynb`
- [Diagnostic performance](https://github.com/sowmiya-gowda/ml-and-dl-tb-detection/blob/main/TB.ipynb): `TB.ipynb`

### Other components

- **Clinical predictors**

## Connections

- Clinical predictors → Feature selection: selects features (evidence: `README.md`)
- Feature selection → Ensemble classifiers: supplies predictors (evidence: `README.md`)
- Ensemble classifiers → TB screening prediction: predicts TB (evidence: `README.md`)
- Ensemble classifiers → Diagnostic performance: improves metrics (evidence: `README.md`)
