SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.07805 · 2022

A Comprehensive Benchmark for COVID-19 Predictive Modeling Using Electronic Health Records in Intensive Care

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 3 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2209.07805.json · badge: /api/ran/2209.07805.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
yhzhu99/pyehr canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
yhzhu99/covid-ehr-benchmarks canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_los_statistics Ran
ran; our contract draft was wrong, not the code
yhzhu99/covid-ehr-benchmarks/app/apis/dl_los_pipeline.py
pointer only (licence: GPL-2.0) · get_code("b7cd239976f57e30")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, yhzhu99/covid-ehr-benchmarks, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_los_statistics Ran
ran; our contract draft was wrong, not the code
yhzhu99/covid-ehr-benchmarks/app/apis/ml_los_pipeline.py
pointer only (licence: GPL-2.0) · get_code("38f7f8ad3286b936")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, yhzhu99/covid-ehr-benchmarks, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_codes Ran
ran on a synthesized input
yhzhu99/pyehr/models/grasp.py
code served (permissive licence) · get_code("efdc8fa2e3f3e60f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family int, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors for dataset and centers
# dataset: shape (num_points, dimension)
# centers: shape (num_centers, dimension)
dataset = torch.randn(2, 4)  # 2 points, 4 dimensions
centers = torch.randn(3, 4)  # 3 centers, 4 dimensions

ARGS = {
    "dataset": dataset,
    "centers": centers,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family int, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_multitask_loss Ran
ran; our contract draft was wrong, not the code
yhzhu99/pyehr/losses/multitask_loss.py
code served (permissive licence) · get_code("093b34abc64726bc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F
from torch import nn

torch.manual_seed(0)

class MultitaskLoss(nn.Module):

    def __init__(self, task_num=2):
        super(MultitaskLoss, self).__init__()
        self.task_num = task_num
        self.log_vars = nn.Parameter(torch.zeros(task_num))

    def forward(self, outcome_pred, los_pred, outcome, los):
        loss0 = F.binary_cross_entropy(outcome_pred, outcome)
        loss1 = F.mse_loss(los_pred, los)
        task_losses = torch.stack([loss0, loss1])
        precision = torch.exp(-self.log_vars)
        return torch.sum(precision * task_losses + self.log_vars)

    @property
    def alpha(self):
        return torch.exp(-self.log_vars).detach()

def get_multitask_loss(outcome_pred, los_pred, outcome, los):
    mtl = MultitaskLoss(task_num=2)
    return mtl(outcome_pred, los_pred, outcome, los)

batch_size = 2
outcome_pred = torch.sigmoid(torch.randn(batch_size, 1))
los_pred = torch.randn(batch_size, 3)
outcome = torch.randint(0, 2, (batch_size, 1)).float()
los = torch.randn(batch_size, 3)

ARGS = {
    "outcome_pred": outcome_pred,
    "los_pred": los_pred,
    "outcome": outcome,
    "los": los,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_time_aware_loss Ran
ran on a synthesized input
yhzhu99/pyehr/losses/time_aware_loss.py
code served (permissive licence) · get_code("b2ce212b04b4c0ac")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import nn

torch.manual_seed(0)

# Create small tensors for the function arguments
batch_size = 2

# outcome_pred: probabilities between 0 and 1 (output of sigmoid)
outcome_pred = torch.sigmoid(torch.randn(batch_size, 1))

# outcome_true: binary labels (0 or 1)
outcome_true = torch.randint(0, 2, (batch_size, 1)).float()

# los_true: length of stay values (can be normalized or raw)
los_true = torch.randn(batch_size, 1)

# los_info: optional dict with normalization parameters
los_info = {
    'los_mean': torch.tensor(5.0),
    'los_std': torch.tensor(2.0)
}

ARGS = {
    'outcome_pred': outcome_pred,
    'outcome_true': outcome_true,
    'los_true': los_true,
    'los_info': los_info
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
random_init Ran
ran on a synthesized input
yhzhu99/pyehr/models/grasp.py
code served (permissive licence) · get_code("ecf8d0b932ea3b5e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import random
import numpy as np
import torch

torch.manual_seed(0)
random.seed(0)

# Create a small dataset tensor
# Shape: (num_points, dimension) = (5, 3)
dataset = torch.randn(5, 3, dtype=torch.float32, device='cpu')

# Number of centers to select
num_centers = 2

# Device to use
device = 'cpu'

ARGS = {
    'dataset': dataset,
    'num_centers': num_centers,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
update_centers Ran
ran on a synthesized input
yhzhu99/pyehr/models/grasp.py
code served (permissive licence) · get_code("628681867a4d6000")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small dataset tensor: 2 points, 4 dimensions
dataset = torch.randn(2, 4, dtype=torch.float32, device='cpu')

# Create codes tensor: cluster assignment for each point (values 0 to num_centers-1)
codes = torch.tensor([0, 1], dtype=torch.long, device='cpu')

# Number of cluster centers
num_centers = 3

# Device
device = 'cpu'

ARGS = {
    'dataset': dataset,
    'codes': codes,
    'num_centers': num_centers,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (3, 4) — shape (3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
train_epoch Not yet run
unverified (harvested, no recorded run)
yhzhu99/covid-ehr-benchmarks/app/apis/dl_los_pipeline.py
pointer only (licence: GPL-2.0) · get_code("e3ce9bc01495f660")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, yhzhu99/covid-ehr-benchmarks, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_multitask_loss 1 other paper
1 later
2402.01713 (2024-02)
Prompting Large Language Models for Zero-Shot Clinical Prediction with Structured Longitudinal Electronic Health Record Data

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The COVID-19 pandemic has posed a heavy burden to the healthcare system worldwide and caused huge social disruption and economic loss. Many deep learning models have been proposed to conduct clinical predictive tasks such as mortality prediction for COVID-19 patients in intensive care units using Electronic Health Record (EHR) data. Despite their initial success in certain clinical applications, there is currently a lack of benchmarking results to achieve a fair comparison so that we can select the optimal model for clinical use. Furthermore, there is a discrepancy between the formulation of traditional prediction tasks and real-world clinical practice in intensive care. To fill these gaps, we propose two clinical prediction tasks, Outcome-specific length-of-stay prediction and Early mortality prediction for COVID-19 patients in intensive care units. The two tasks are adapted from the naive length-of-stay and mortality prediction tasks to accommodate the clinical practice for COVID-19 patients. We propose fair, detailed, open-source data-preprocessing pipelines and evaluate 17 state-of-the-art predictive models on two tasks, including 5 machine learning models, 6 basic deep learning models and 6 deep learning predictive models specifically designed for EHR data. We provide benchmarking results using data from two real-world COVID-19 EHR datasets. One dataset is publicly available without needing any inquiry and another dataset can be accessed on request. We provide fair, reproducible benchmarking results for two tasks. We deploy all experiment results and models on an online platform. We also allow clinicians and researchers to upload their data to the platform and get quick prediction results using our trained models. We hope our efforts can further facilitate deep learning and machine learning research for COVID-19 predictive modeling.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2209.07805")
get_code_for_paper("2209.07805")
have("2209.07805")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2209.07805.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2209.07805.svg)](https://syntology.ai/paper/2209.07805)

Connect an agent — have() is free.