ClarusC64/clinical-quad-oxygen-demand-buffer-lag-coupling-respiratory-collapse-v1.4

---
language: en
license: mit
task_categories:
- text-classification
tags:
- clinical-trials
- quad-coupling
- clarus
- clarus-v1.4
- counterfactual-intervention-timing
- respiratory-collapse
- oxygen-demand
size_categories:
- 1K<n<10K
pretty_name: Clinical Quad Oxygen Demand Buffer Lag Coupling Respiratory Collapse v1.4
---

# Clinical Quad Oxygen Demand Buffer Lag Coupling Respiratory Collapse v1.4

## What this repo does

This repository contains a Clarus v1.4 benchmark dataset.

The v1.4 layer introduces Counterfactual Intervention Timing Geometry.

Earlier layers evaluate:

- system state
- trajectory
- boundary proximity
- recovery feasibility
- intervention selection
- control sequence correctness
- temporal policy stability
- failure reconstruction

v1.4 evaluates whether respiratory collapse could still have been prevented in time.

The benchmark asks:

- could the respiratory collapse have been prevented
- which intervention would have prevented it
- was the recovery window still open when that intervention should have occurred

This is a benchmark for actionable prevention reasoning under timing constraints.

## Core quad

- oxygen_demand
- buffer_capacity
- lag_burden
- coupling_stress

These define the respiratory instability state.

## Prediction targets

- `label_counterfactual_prevention`
- `label_correct_intervention_step`

`label_counterfactual_prevention = 1` means the respiratory collapse remained preventable within the recovery window.

`label_counterfactual_prevention = 0` means the system had crossed into effective irreversibility before the stabilizing intervention could still succeed.

`label_correct_intervention_step` identifies the earliest stabilizing intervention.

## New v1.4 signals

- `intervention_timing_index`
- `recovery_window_open`
- `recovery_window_width`
- `cascade_irreversibility_score`
- `counterfactual_intervention_effect`
- `policy_divergence_score`

These signals allow evaluation of intervention timing geometry rather than failure explanation alone.

## Row structure

Each row represents one respiratory collapse scenario.

Core state variables:

- `oxygen_demand`
- `buffer_capacity`
- `lag_burden`
- `coupling_stress`

Timing and prevention geometry:

- `failure_decision_sequence`
- `intervention_timing_index`
- `recovery_window_open`
- `recovery_window_width`
- `cascade_irreversibility_score`
- `counterfactual_intervention_effect`
- `policy_divergence_score`

Labels:

- `label_counterfactual_prevention`
- `label_correct_intervention_step`

## Files

- `data/train.csv`
Labeled training examples

- `data/tester.csv`
Evaluation set with label columns removed

- `scorer.py`
Scores predictions against held-out truth

- `dataset_schema.json`
Machine-readable dataset structure and field contract

- `benchmark_spec.json`
Machine-readable evaluation contract

## Evaluation

Primary metric:

- `composite_prevention_success`

Secondary metric:

- `false_prevention_prediction_rate`

Additional reported metrics:

- `prevention_label_accuracy`
- `correct_intervention_step_accuracy`
- `accuracy`
- `precision`
- `recall`
- `f1`

Diagnostics:

- `window_consistent_prevention_accuracy`
- `late_intervention_miss_rate`
- `irreversible_cascade_misclassification_rate`
- `high_policy_divergence_prevention_accuracy`

## Example clinical mappings

- `oxygen_demand` can reflect work of breathing, oxygen requirement, respiratory rate burden, or metabolic demand on gas exchange
- `buffer_capacity` can reflect reserve in oxygenation, ventilatory tolerance, or pulmonary compensation
- `lag_burden` can reflect delayed escalation, delayed NIV, delayed airway support, or delayed bronchodilation
- `coupling_stress` can reflect cardiopulmonary coupling strain, CO2 retention effects, pulmonary edema burden, or systemic respiratory feedback stress

## Construction note

The v1.4 layer tests a stricter capability than failure reconstruction.

A model must infer not only what caused respiratory collapse, but whether intervention remained viable before the recovery window closed.

This makes the task closer to real operational safety reasoning in respiratory deterioration, ICU escalation, and emergency triage.

## Structural Note

Clarus v1.4 extends failure reconstruction into counterfactual prevention timing.

The benchmark is not asking only whether a system can narrate respiratory decline.

It asks whether a model can detect the boundary between recoverable instability and irreversible respiratory cascade.

## Production Deployment

In production environments, this class of benchmark supports systems that must decide not only what went wrong, but whether corrective action is still viable under live time constraints.

This matters in acute respiratory deterioration, emergency escalation, ward-to-ICU transfer logic, and ventilatory support decisions.

## Enterprise and Research Collaboration

Clarus benchmarks are designed to evaluate state-space intelligence around instability, recoverability, and intervention timing.

For research, deployment, or enterprise collaboration:
[e-mail]

Instability is detectable. Governance determines whether it propagates.

## License

MIT

---
语言：英语
许可证：MIT协议
任务类别：
- 文本分类
标签：
- 临床试验（clinical-trials）
- 四元耦合（quad-coupling）
- Clarus
- Clarus v1.4
- 反事实干预时机（counterfactual-intervention-timing）
- 呼吸衰竭（respiratory-collapse）
- 氧需求（oxygen-demand）
样本规模：
- 1K<n<10K
数据集名称：临床四元氧需求-缓冲延迟-耦合呼吸衰竭数据集v1.4
---

# 临床四元氧需求-缓冲延迟-耦合呼吸衰竭数据集v1.4

## 本仓库内容说明
本仓库包含Clarus v1.4基准数据集。
该v1.4版本新增了反事实干预时机几何分析模块。
此前版本的评估维度包括：
- 系统状态
- 轨迹
- 边界临近性
- 恢复可行性
- 干预选择
- 控制序列正确性
- 时间策略稳定性
- 失败重构

v1.4版本则评估呼吸衰竭是否仍可被及时阻止。
该基准测试需解决以下问题：
- 是否可避免该呼吸衰竭事件
- 何种干预措施可阻止该事件
- 该干预措施实施时，恢复窗口是否仍未关闭

本基准面向时序约束下的可操作预防推理任务。

## 核心四元变量
- 氧需求（oxygen_demand）
- 缓冲容量（buffer_capacity）
- 延迟负荷（lag_burden）
- 耦合应激（coupling_stress）

上述变量共同定义了呼吸不稳定状态。

## 预测目标
- 反事实预防标签（label_counterfactual_prevention）
- 正确干预步骤标签（label_correct_intervention_step）

`label_counterfactual_prevention = 1` 表示在恢复窗口内，该呼吸衰竭仍可被预防；`label_counterfactual_prevention = 0` 表示在稳定干预成功前，系统已进入有效不可逆状态。`label_correct_intervention_step` 用于标识最早可实施的稳定干预步骤。

## v1.4版本新增信号
- 干预时机索引（intervention_timing_index）
- 恢复窗口开放状态（recovery_window_open）
- 恢复窗口宽度（recovery_window_width）
- 级联不可逆性评分（cascade_irreversibility_score）
- 反事实干预效果（counterfactual_intervention_effect）
- 策略分歧评分（policy_divergence_score）

上述信号可用于评估干预时机几何特征，而非仅局限于失败原因解释。

## 数据行结构
每一行对应一个呼吸衰竭场景。

### 核心状态变量
- 氧需求（oxygen_demand）
- 缓冲容量（buffer_capacity）
- 延迟负荷（lag_burden）
- 耦合应激（coupling_stress）

### 时序与预防几何特征
- 失败决策序列（failure_decision_sequence）
- 干预时机索引（intervention_timing_index）
- 恢复窗口开放状态（recovery_window_open）
- 恢复窗口宽度（recovery_window_width）
- 级联不可逆性评分（cascade_irreversibility_score）
- 反事实干预效果（counterfactual_intervention_effect）
- 策略分歧评分（policy_divergence_score）

### 标签
- 反事实预防标签（label_counterfactual_prevention）
- 正确干预步骤标签（label_correct_intervention_step）

## 数据文件
- `data/train.csv`：带标签的训练集样本
- `data/tester.csv`：移除了标签列的评估集
- `scorer.py`：用于基于留存真实标签对预测结果进行评分的脚本
- `dataset_schema.json`：机器可读的数据集结构与字段契约
- `benchmark_spec.json`：机器可读的评估契约

## 评估指标
### 核心评估指标
- 综合预防成功率（composite_prevention_success）

### 次要评估指标
- 错误预防预测率（false_prevention_prediction_rate）

### 额外报告指标
- 预防标签准确率（prevention_label_accuracy）
- 正确干预步骤准确率（correct_intervention_step_accuracy）
- 准确率（accuracy）
- 精确率（precision）
- 召回率（recall）
- F1值（f1）

### 诊断指标
- 窗口一致性预防准确率（window_consistent_prevention_accuracy）
- 延迟干预漏检率（late_intervention_miss_rate）
- 不可逆级联事件误分类率（irreversible_cascade_misclassification_rate）
- 高策略分歧下的预防准确率（high_policy_divergence_prevention_accuracy）

## 临床示例映射
- 氧需求（oxygen_demand）可反映呼吸做功、氧需求量、呼吸频率负荷或气体交换的代谢需求
- 缓冲容量（buffer_capacity）可反映氧合储备、通气耐受度或肺部代偿能力
- 延迟负荷（lag_burden）可反映病情升级延迟、无创通气（NIV）延迟、气道支持延迟或支气管扩张治疗延迟
- 耦合应激（coupling_stress）可反映心肺耦合应激、二氧化碳潴留效应、肺水肿负荷或全身呼吸反馈应激

## 数据集构建说明
v1.4版本的测试难度高于失败重构任务。
模型不仅需要推断呼吸衰竭的成因，还需判断在恢复窗口关闭前，干预措施是否仍具备可行性。
这使得该任务更贴近呼吸恶化、ICU病情升级与急诊分诊场景中的实际临床安全推理需求。

## 结构说明
Clarus v1.4将失败重构任务拓展至反事实预防时序分析领域。
该基准不仅测试模型能否复述呼吸衰竭的发展过程，更需测试模型能否识别可恢复不稳定状态与不可逆呼吸级联反应之间的边界。

## 生产部署应用
在生产环境中，此类基准可支撑需在实时时序约束下，不仅判断故障成因，还需评估纠正措施是否仍具备可行性的系统。
这在急性呼吸恶化、急诊病情升级、病房转ICU决策与通气支持决策场景中具有重要应用价值。

## 企业与研究合作
Clarus基准集旨在评估围绕不稳定状态、可恢复性与干预时机的状态空间智能。
如需开展研究、部署应用或企业合作，请联系：[e-mail]
不稳定状态可被检测，而管控措施决定其是否会扩散。

## 许可证
MIT协议