Datasets:
id stringlengths 11 11 | prompt listlengths 1 1 | completion listlengths 1 1 | Label stringclasses 2
values |
|---|---|---|---|
NCT01187615 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT01046487 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT01381887 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT02015676 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT01813955 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT01213160 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT00722293 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00451880 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00096304 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT00129896 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00315861 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT01064622 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT01925300 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT01111188 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00560352 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT01292798 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT01273558 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00730392 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT01101594 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT00379080 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT00735878 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT00494221 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT02012166 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00543114 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT01575405 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00068757 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00096707 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT01192165 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00473486 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT01028248 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00612794 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00361244 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT01154062 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT01130818 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00482014 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00201838 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT01235039 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00179608 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00411762 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT01273948 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT01176903 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00477386 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT01054300 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00732784 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00642655 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00567879 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Failure\n"
}
] | Failure |
NCT00694980 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
NCT00607308 | [
{
"role": "user",
"content": "You are an expert medical assistant specialized in predicting clinical trial outcomes. Your task is to predict the outcome in binary format (Success or Failure), based on the provided information on the clinical trial.\n\nYou will be provided with the following:\n- **Diseases:*... | [
{
"role": "assistant",
"content": "**Answer:** Success\n"
}
] | Success |
araag2/HINT(複製)
データの内容
臨床試験の結果の予測を扱う HINT の論文(arXiv:2102.04252)に関するデータセット。カードは、分子の情報、対象疾患、試験計画、知識を組み合わせて予測する枠組みを説明している。ライセンスは CC BY-SA 4.0 である。データの項目の説明は未記入(TO:DO)のままで、列の意味はカードからは分からない。
データの概要
| 項目 | 値 |
|---|---|
| 行数 | 37,431(3 構成・9 分割の合計) |
| 列数 | 4〜10(構成による) |
| 容量 | 54.41 MB(ファイル 11 本) |
| ファイルの形式 | parquet 9 |
| 言語 | en |
| 公開 | public |
構成と分割
| 構成(config) | 分割(split)ごとの行数 | 列数 |
|---|---|---|
conversational |
train 8,143、dev 907、test 3,427 |
4 |
processed |
train 8,143、dev 907、test 3,427 |
10 |
source |
train 8,143、dev 907、test 3,427 |
10 |
列(構成 conversational・分割 train。構成ごとに列が違う)
| 列 | 型 | 先頭の行の値 |
|---|---|---|
id |
string |
NCT01187615 |
prompt |
list<struct{role: string, content: string}> |
[1 件] |
completion |
list<struct{role: string, content: string}> |
[1 件] |
Label |
string |
Failure |
行数と列は HF のデータセットビューアの集計(元のデータセットの現在の版で数えたもの)。全データセットの一覧は HYUKI5/dataset-catalog にある。
複製について
araag2/HINT をリビジョン 64c393761a38934fc19351ba761dee7557429bf4 の時点でそのまま複製したもの。中身は変えていない。判断モデル Laya(convaiinnovations/laya)の微調整に使う候補として、調査メモ(Laya 学習用データセット調査)に載せたデータを集めている。
出典
- 元のデータセット: https://huggingface.co/datasets/araag2/HINT
- 複製したリビジョン:
64c393761a38934fc19351ba761dee7557429bf4(2025-11-04 15:52:47+00:00) - 元のライセンス表記:
cc-by-sa-4.0
論文
アノテーションの方法
元のカードにアノテーションの節が無かった。下の「調査メモの記述」と「元のカード」を参照。
微調整に使うときの注意
- 調査メモの台帳での区分: B(継承条件・gated・モデル由来の条件・上流の規約などが付く)。区分は記載の文言で機械的に付けたもので、法的な判定ではない。学習に入れる前に元のカードとライセンスの原文で確かめる。
- Laya の入力は 2,048 token まで(ModernBERT-large / mmBERT)。長い本文は先頭から黙って切られるので、切れる行は事前に除くか、要約・切り出しをしてから入れる。
- 分割は記事・文書単位で行い、同じ本文から作った別の問いを学習側と較正側に分けない。温度と閾値は学習に使っていない分割で別々に当てる。
調査メモの記述
| メモ | 節 | ライセンス(記載) | 確認 | 注記 |
|---|---|---|---|---|
sector_specific.md |
Q1. 治験の成否・結果の方向(株価のカタリストになる判断)に使える公開データは何があるか (L21) | cc-by-sa-4.0(HF)。原典リポジトリのライセンスは確認できなかった(検索結果では MIT と不明で割れる) | 検索結果 | 複数/混在 / 原文注記: status が terminated・withdrawn の行を Failure にしているなら、why_stop を入力に含めると答えが漏れる(推論。ラベル生成規則はカードで未確認)。SA。件数が原典と食い違う理由は |
元のカード(日本語訳)
以下は元のデータセットのカードの本文を日本語に訳したもの(機械翻訳)。訳に疑問があるときは、末尾の原文を確かめる。
HINT: 臨床試験結果予測のための階層的相互作用ネットワーク
データセットの説明
| リンク | |
|---|---|
| ホームページ: | Github.io |
| リポジトリ: | Github |
| 論文: | arXiv |
| 連絡先(原著者): | Tianfan Fu (futianfan@gmail.com) |
| 連絡先(キュレーター): | Artur Guimarães (artur.guimas@gmail.com) |
データセットの概要
Clinical trials are crucial for drug development but are time consuming, expensive, and often burdensome on patients. More importantly, clinical trials face uncertain outcomes due to issues with efficacy, safety, or problems with patient recruitment. If we were better at predicting the results of clinical trials, we could avoid having to run trials that will inevitably fail more resources could be devoted to trials that are likely to succeed. In this paper, we propose Hierarchical INteraction Network (HINT) for more general, clinical trial outcome predictions for all diseases based on a comprehensive and diverse set of web data including molecule information of the drugs, target disease information, trial protocol and biomedical knowledge. HINT first encode these multi-modal data into latent embeddings, where an imputation module is designed to handle missing data. Next, these embeddings will be fed into the knowledge embedding module to generate knowledge embeddings that are pretrained using external knowledge on pharmaco-kinetic properties and trial risk from the web. Then the interaction graph module will connect all the embedding via domain knowledge to fully capture various trial components and their complex relations as well as their influences on trial outcomes. Finally, HINT learns a dynamic attentive graph neural network to predict trial outcome. Comprehensive experimental results show that HINT achieves strong predictive performance, obtaining 0.772, 0.607, 0.623, 0.703 on PR-AUC for Phase I, II, III, and indication outcome prediction, respectively. It also consistently outperforms the best baseline method by up to 12.4\% on PR-AUC.
データの例
{
'TO:DO': ...,
...
}
データのフィールド
TO:DO
追加情報
データセットのキュレーター
原論文
- Tianfan Fu - ジョージア工科大学
- Kexin Huang - ハーバード大学
- Cao Xiao - IQVIA の Analytics Center of Excellence
- Lucas M. - テンプル大学
- Jimeng Sun - イリノイ大学アーバナー・シャンペーン校
Huggingface のキュレーター
- Artur Guimarães (artur.guimas@gmail.com) - INESC-ID / リスボン大学 / 高等工科大学(Instituto Superior Técnico)
ライセンス情報
引用情報
@article{fu2021hint,
title={HINT: Hierarchical Interaction Network for Trial Outcome Prediction Leveraging Web Data},
author={Fu, Tianfan and Huang, Kexin and Xiao, Cao and Glass, Lucas M and Sun, Jimeng},
journal={arXiv preprint arXiv:2102.04252},
year={2021}
}
貢献
このデータセットを追加してくれた araag2 に感謝する。
原文(英語)
HINT: Hierarchical interaction network for clinical-trial-outcome predictions
Dataset Description
| Links | |
|---|---|
| Homepage: | Github.io |
| Repository: | Github |
| Paper: | arXiv |
| Contact (Original Authors): | Tianfan Fu (futianfan@gmail.com) |
| Contact (Curator): | Artur Guimarães (artur.guimas@gmail.com) |
Dataset Summary
Clinical trials are crucial for drug development but are time consuming, expensive, and often burdensome on patients. More importantly, clinical trials face uncertain outcomes due to issues with efficacy, safety, or problems with patient recruitment. If we were better at predicting the results of clinical trials, we could avoid having to run trials that will inevitably fail more resources could be devoted to trials that are likely to succeed. In this paper, we propose Hierarchical INteraction Network (HINT) for more general, clinical trial outcome predictions for all diseases based on a comprehensive and diverse set of web data including molecule information of the drugs, target disease information, trial protocol and biomedical knowledge. HINT first encode these multi-modal data into latent embeddings, where an imputation module is designed to handle missing data. Next, these embeddings will be fed into the knowledge embedding module to generate knowledge embeddings that are pretrained using external knowledge on pharmaco-kinetic properties and trial risk from the web. Then the interaction graph module will connect all the embedding via domain knowledge to fully capture various trial components and their complex relations as well as their influences on trial outcomes. Finally, HINT learns a dynamic attentive graph neural network to predict trial outcome. Comprehensive experimental results show that HINT achieves strong predictive performance, obtaining 0.772, 0.607, 0.623, 0.703 on PR-AUC for Phase I, II, III, and indication outcome prediction, respectively. It also consistently outperforms the best baseline method by up to 12.4\% on PR-AUC.
Data Instances
{
'TO:DO': ...,
...
}
Data Fields
TO:DO
Additional Information
Dataset Curators
Original Paper
- Tianfan Fu - Georgia Institute of Technology
- Kexin Huang - Harvard University
- Cao Xiao - Analytics Center of Excellence, IQVIA
- Lucas M. - Temple University
- Jimeng Sun - University of Illinois at Urbana-Champaign
Huggingface Curator
- Artur Guimarães (artur.guimas@gmail.com) - INESC-ID / University of Lisbon - Instituto Superior Técnico
Licensing Information
Citation Information
@article{fu2021hint,
title={HINT: Hierarchical Interaction Network for Trial Outcome Prediction Leveraging Web Data},
author={Fu, Tianfan and Huang, Kexin and Xiao, Cao and Glass, Lucas M and Sun, Jimeng},
journal={arXiv preprint arXiv:2102.04252},
year={2021}
}
Contributions
Thanks to araag2 for adding this dataset.
- Downloads last month
- 30