SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.12998 · 2022

Integrated multimodal artificial intelligence framework for healthcare applications

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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 3 have no contract verdict; 0 failures of our instrument; 3 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/2202.12998.json · badge: /api/ran/2202.12998.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
lrsoenksen/haim canonical (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
date_diff_hrs Ran
ran on a synthesized input
lrsoenksen/haim/MIMIC_IV_HAIM_API.py
code served (permissive licence) · get_code("9ebe0ca5a1bbda84")
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 float, 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 math
from datetime import datetime, timedelta

# The function expects two datetime objects (t1 and t0)
# that support subtraction and .total_seconds() method
# or will catch an exception and return nan

t1 = datetime(2024, 1, 15, 10, 30, 0)
t0 = datetime(2024, 1, 15, 8, 0, 0)

ARGS = {
    "t1": t1,
    "t0": t0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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_scores_clf Ran
ran on a synthesized input
lrsoenksen/haim/prediction_util.py
code served (permissive licence) · get_code("f0a6e2b2c5d3d8f7")
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 tuple. The image it ran in was not recorded. If your copy returns the same type 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 numpy as np
from sklearn import metrics
from sklearn.metrics import auc

# Set random seed for reproducibility
np.random.seed(0)

# Create small valid arguments for binary classification
# For binary classification with roc_auc_score, we need:
# - y_true: true binary labels
# - y_pred: predicted binary labels
# - y_pred_prob: predicted probabilities for the positive class

n_samples = 10

# True labels (binary: 0 or 1)
y_true = np.array([0, 1, 1, 0, 1, 0, 1, 1, 0, 1])

# Predicted labels (binary: 0 or 1)
y_pred = np.array([0, 1, 1, 0, 0, 0, 1, 1, 0, 1])

# Predicted probabilities for the positive class (values between 0 and 1)
y_pred_prob = np.array([0.1, 0.9, 0.8, 0.2, 0.3, 0.1, 0.85, 0.95, 0.15, 0.88])

ARGS = {
    'y_true': y_true,
    'y_pred': y_pred,
    'y_pred_prob': y_pred_prob
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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_timebound_patient_icustay Ran
ran on a synthesized input
lrsoenksen/haim/MIMIC_IV_HAIM_API.py
code served (permissive licence) · get_code("a154c9a7ebab4c9b")
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 PatientICUstay. The image it ran in was not recorded. If your copy returns the same type 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 pandas as pd
import datetime as dt
import math

class PatientICUstay:
    def __init__(self):
        # Create core dataframe with admittime and dischtime
        self.core = pd.DataFrame({
            'admittime': [dt.datetime(2020, 1, 1, 0, 0, 0)],
            'dischtime': [dt.datetime(2020, 1, 5, 12, 0, 0)]
        })
        
        # Create other event dataframes with charttime column
        base_time = dt.datetime(2020, 1, 1, 6, 0, 0)
        
        self.emar = pd.DataFrame({
            'charttime': [base_time, base_time + dt.timedelta(hours=2)]
        })
        
        self.labevents = pd.DataFrame({
            'charttime': [base_time + dt.timedelta(hours=1)]
        })
        
        self.microbiologyevents = pd.DataFrame({
            'charttime': [base_time + dt.timedelta(hours=3)]
        })
        
        self.outputevents = pd.DataFrame({
            'charttime': [base_time + dt.timedelta(hours=5)]
        })
        
        self.datetimeevents = pd.DataFrame({
            'charttime': [base_time + dt.timedelta(hours=4)]
        })
        
        self.chartevents = pd.DataFrame({
            'charttime': [base_time + dt.timedelta(hours=2), base_time + dt.timedelta(hours=8)]
        })
        
        self.noteevents = pd.DataFrame({
            'charttime': [base_time + dt.timedelta(hours=10)]
        })
        
        self.dsnotes = pd.DataFrame({
            'charttime': [base_time + dt.timedelta(hours=12)]
        })
        
        self.ecgnotes = pd.DataFrame({
            'charttime': [base_time + dt.timedelta(hours=7)]
        })
        
        self.echonotes = pd.DataFrame({
            'charttime': [base_time + dt.timedelta(hours=9)]
        })
        
        self.radnotes = pd.DataFrame({
            'charttime': [base_time + dt.timedelta(hours=11)]
        })
        
        self.cxr = pd.DataFrame({
            'StudyDate': ['20200101', '20200102'],
            'StudyTime': [60000.123, 120000.456]
        })
        
        self.imcxr = ['image1.dcm', 'image2.dcm']

patient = PatientICUstay()

ARGS = {
    'Patient_ICUstay': patient,
    'start_hr': 0,
    'end_hr': 24
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PatientICUstay — a PatientICUstay output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PatientICUstay output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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_patient_icustay Not yet run
unverified (harvested, no recorded run)
lrsoenksen/haim/MIMIC_IV_HAIM_API.py
code served (permissive licence) · get_code("22923f9091b05b3a")
How it ran

no invocation recorded.

run_xgb Not yet run
unverified (harvested, no recorded run)
lrsoenksen/haim/prediction_util.py
code served (permissive licence) · get_code("b724aa44fd0c9636")
How it ran

no invocation recorded.

update_result Not yet run
unverified (harvested, no recorded run)
lrsoenksen/haim/prediction_util.py
code served (permissive licence) · get_code("d983f341a80db5a1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

Artificial intelligence (AI) systems hold great promise to improve healthcare over the next decades. Specifically, AI systems leveraging multiple data sources and input modalities are poised to become a viable method to deliver more accurate results and deployable pipelines across a wide range of applications. In this work, we propose and evaluate a unified Holistic AI in Medicine (HAIM) framework to facilitate the generation and testing of AI systems that leverage multimodal inputs. Our approach uses generalizable data pre-processing and machine learning modeling stages that can be readily adapted for research and deployment in healthcare environments. We evaluate our HAIM framework by training and characterizing 14,324 independent models based on HAIM-MIMIC-MM, a multimodal clinical database (N=34,537 samples) containing 7,279 unique hospitalizations and 6,485 patients, spanning all possible input combinations of 4 data modalities (i.e., tabular, time-series, text, and images), 11 unique data sources and 12 predictive tasks. We show that this framework can consistently and robustly produce models that outperform similar single-source approaches across various healthcare demonstrations (by 6-33%), including 10 distinct chest pathology diagnoses, along with length-of-stay and 48-hour mortality predictions. We also quantify the contribution of each modality and data source using Shapley values, which demonstrates the heterogeneity in data modality importance and the necessity of multimodal inputs across different healthcare-relevant tasks. The generalizable properties and flexibility of our Holistic AI in Medicine (HAIM) framework could offer a promising pathway for future multimodal predictive systems in clinical and operational healthcare settings.

For agents

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

get_harvested_code_for_paper("2202.12998")
get_code_for_paper("2202.12998")
have("2202.12998")

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

curl https://syntology.ai/api/ran/2202.12998.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.12998.svg)](https://syntology.ai/paper/2202.12998)

Connect an agent — have() is free.