Skip to main content

A multimodal AI-Ready Dataset. Updated Regularly. More details from TrialBench: Multi-Modal AI-Ready Datasets for Clinical Trial Prediction.

Project description

TrialBench: Multi-modal AI-ready Clinical Trial Datasets

PyPI version

License

1. Installation :rocket:

`bash pip install trialbench`

2. Tasks & Phases :clipboard:

Supported Tasks | Task Type | Task Name | Phase Name | ------------------------------------------- | Mortality Prediction | [mortality_rate]{.title-ref}/[mortality_rate_yn]{.title-ref} | 1-4 | | Adverse Event Prediction | [serious_adverse_rate]{.title-ref}/[serious_adverse_rate_yn]{.title-ref} | 1-4 | | Patient Retention Prediction | [patient_dropout_rate]{.title-ref}/[patient_dropout_rate_yn]{.title-ref} | 1-4 | | Trial Duration Prediction | [duration]{.title-ref} | 1-4 | | Trial Outcome Prediction | [outcome]{.title-ref} | 1-4 | | Trial Failure Analysis | [failure_reason]{.title-ref} | 1-4 | | Dosage Prediction | [dose]{.title-ref}/[dose_cls]{.title-ref} | all |

Clinical Trial Phases ` Phase 1: Safety Evaluation Phase 2: Efficacy Assessment Phase 3: Large-scale Testing Phase 4: Post-marketing Surveillance`

3. Quick Start :zap:

`python import trialbench # Load dataset task = 'dose' phase = 'all' # Load data train_loader, valid_loader, test_loader, num_classes, tabular_input_dim = trialbench.load_data(task, phase)`

4. Data Loading :card_file_box:

[load_data]{.title-ref} Parameters | Parameter | Type | Description | ------ | [task]{.title-ref} | str | Target prediction task (e.g., 'mortality_rate_yn') | | [phase]{.title-ref} | int | Clinical trial phase (1-4) |

Returns | Object | Type | Description | --------------- | [train_loader]{.title-ref} | DataLoader | Training set loader | | [valid_loader]{.title-ref} | DataLoader | Validation set loader | | [test_loader]{.title-ref} | DataLoader | Test set loader | | [num_classes]{.title-ref} | int | Number of output classes | | [tabular_input_dim]{.title-ref} | int | Dimension of tabular features |

5. Citation :handshake:

If you use TrialBench in your research, please cite: `bibtex @article{chen2024trialbench, title={Trialbench: Multi-modal artificial intelligence-ready clinical trial datasets}, author={Chen, Jintai and Hu, Yaojun and Wang, Yue and Lu, Yingzhou and Cao, Xu and Lin, Miao and Xu, Hongxia and Wu, Jian and Xiao, Cao and Sun, Jimeng and others}, journal={arXiv preprint arXiv:2407.00631}, year={2024} }`

---

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

trialbench-0.1.0.dev1.tar.gz (19.7 kB view details)

Uploaded Source

File details

Details for the file trialbench-0.1.0.dev1.tar.gz.

File metadata

  • Download URL: trialbench-0.1.0.dev1.tar.gz
  • Upload date:
  • Size: 19.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.16

File hashes

Hashes for trialbench-0.1.0.dev1.tar.gz
Algorithm Hash digest
SHA256 a9a18a14b09597fad21ae71d533086d05d3c244935251a5d77f64b6bcb0d215a
MD5 288d70dacb7ceefa23c0f557a562bd84
BLAKE2b-256 71ae6374d6b2294699cabfca83a941cdd39ab1886f80a5a0994b8c0b865846d8

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page