Skip to content

Commit 36d4603

Browse files
better index
1 parent 0701b91 commit 36d4603

File tree

2 files changed

+33
-39
lines changed

2 files changed

+33
-39
lines changed

app/index/templates/index.html

Lines changed: 30 additions & 35 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,7 @@
11
{% extends "base.html" %} {% block content %}
22
<div class="col-xl-6 offset-xl-3">
33
<h1 align="center">
4-
EHRoes 🦸: an all-in-one web application for patients’ data digitization
5-
and exploration
4+
EHRoes 🦸: an all-in-one web application for patients’ data digitization and exploration
65
</h1>
76
<p align="center">
87
<img src="{{ url_for('static', filename='banner.png') }}" alt="EHRoes Banner" style="border-radius: 25px;" />
@@ -16,7 +15,7 @@ <h1 align="center">
1615
</p>
1716
<br />
1817
<h2>Demo Usage Instructions</h2>
19-
<p>
18+
<p align="justify">
2019
If you are on the demo instance (<a href="https://ehroes.lbgi.fr">https://ehroes.lbgi.fr</a>), you can login on top
2120
right with
2221
<strong>login: demo ; password: demo</strong><br /> The application is
@@ -39,46 +38,42 @@ <h2>Partners</h2>
3938
</a>
4039
</div>
4140
<div class="col-xl">
42-
<p>EHRoes is developped and used in collaboration with the <a
41+
<p align="justify">EHRoes is developped and used in collaboration with the <a
4342
href="https://www.institut-myologie.org/en/recherche-2/neuromuscular-exploration-and-evaluation-centre/laboratoire-dhistopathologie-dr-norma-b-romero/">
4443
Morphological Unit of the Institute of Myology of Paris</a>.
4544
A production instance is deployed to help discovering new relevant
4645
features for congenital myopathies classification and diagnosis.</p>
4746
</div>
4847
</div>
4948
<h2>EHRoes Abstract</h2>
50-
<p>
51-
<strong>Background</strong><br />With a growing amount of patient data such
52-
as sequencing, imaging, and medical records, electronic health records (EHR)
53-
became central to drive research and improve diagnosis of patients by using
54-
multimodal data. But EHR usage is challenging as they require tools to
55-
format, digitize and interpret data. Today’s EHR exploitation tools
56-
ecosystem is heavily fragmented among tools to create EHR (format and
57-
digitize) and tools to interpret the data (exploration and diagnosis).
58-
Also most of the tools are specialized for one specific type of data,
59-
multiplying the number of different software needed for multimodal
60-
approaches. There is a strong need for a simple, all-rounder and flexible
61-
platform.<br /><strong>Results</strong><br />In this paper we present
62-
EHRoes, an all-in-one web application for patients’ data digitization and
63-
exploration. With its module-based architecture, we developed four modules
64-
to: (i) create a set of standard vocabulary for a domain, (ii) automatically
65-
digitize free-text data to a set of standard terms, (iii) annotate images
66-
with standard vocabulary using automatic segmentation and (iv) generate an
67-
automatic visualization dashboard to provide insight on the data and perform
68-
automatic diagnosis suggestions. Using this platform, we successfully
69-
digitized 89 muscle histology reports from patients with congenital
70-
myopathies and we obtained an accuracy of 0.75 for congenital myopathy
71-
subtypes classification.<br /><strong>Conclusions</strong><br />With EHRoes
72-
we created a platform for both patients data digitization and exploration
73-
that can handle image data and free-text data. As it uses user designed
74-
standard vocabulary, it is highly flexible to fit any domain of research. It
75-
can be used both as a patient registry with automatic diagnosis or as a
76-
research tool to explore a cohort of patients. A demo instance of the
77-
application is available at
78-
<a href="https://ehroes.lbgi.fr">https://ehroes.lbgi.fr</a>.
49+
<p align="justify">
50+
<strong>Background</strong><br />With a growing amount of patient data such as sequencing, imaging, and medical
51+
records, electronic health records (EHR) are now central to drive research and improve diagnosis of patients by
52+
using multimodal data. Exploiting patient data is a challenge as patient data exploitation tools ecosystem is often
53+
fragmented into tools to digitize and format the data and those interpreting the data (exploration, diagnosis).
54+
Furthermore, as most of the tools are specialized in one type of data, a multitude of software is needed for
55+
multimodal approaches. There is a strong need for a simple, all-rounder and flexible platform.
56+
<br />
57+
<strong>Results</strong>
58+
<br />
59+
In this paper we present EHRoes, an all-in-one web application to digitize and explore patient data. EHRoes has a
60+
module-based architecture, composed of four modules to: (i) create a standard vocabulary for a domain (ii)
61+
automatically digitize free-text data to a set of standard terms (iii) annotate images with standard vocabulary
62+
using automatic segmentation and (iv) generate an automatic visualization dashboard to provide insight on the data
63+
and perform automatic diagnosis suggestions. We demonstrated the utility of EHRoes by digitizing 40 artificial
64+
muscle histology reports of patients with congenital myopathies.
65+
<br />
66+
<strong>Conclusions</strong>
67+
<br />
68+
With EHRoes we created a platform for both digitization and exploration of patient data that can handle image data
69+
and free-text data. As it uses user-designed standard vocabulary, it is highly flexible to fit any domain of
70+
research. It can be used both as a patient registry with automatic diagnosis or as a research tool to explore a
71+
cohort of patients. A demo instance of the application is available at <a
72+
href="https://ehroes.lbgi.fr">https://ehroes.lbgi.fr</a>.
73+
7974
</p>
8075
<h2>MYO-xIA Project</h2>
81-
<p>
76+
<p align="justify">
8277
The MYO-xIA project aims to collect data from patients with
8378
<strong>congenital myopathies</strong> in order to analyse them using
8479
<strong>explainable AI approaches</strong>. In the field of congenital
@@ -87,7 +82,7 @@ <h2>MYO-xIA Project</h2>
8782
to use modern data analysis methods.<br />This project has tree mains
8883
objectives:
8984
</p>
90-
<ul>
85+
<ul align="justify">
9186
<li>
9287
<strong>Gather and format patient data</strong> to be ready for automatic
9388
exploitation (patient histology-report form, image annotation, OCR/NLP)

app/index/templates/index.md

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -14,12 +14,11 @@ EHRoes is developped and used in collaboration with the [Morphological Unit of t
1414
## EHRoes Abstract
1515

1616
**Background**
17-
With a growing amount of patient data such as sequencing, imaging, and medical records, electronic health records (EHR) became central to drive research and improve diagnosis of patients by using multimodal data. But EHR usage is challenging as they require tools to format, digitize and interpret data. Today’s EHR exploitation tools ecosystem is heavily fragmented among tools to create EHR (format and digitize) and tools to interpret the data (exploration and diagnosis). Also most of the tools are specialized for one specific type of data, multiplying the number of different software needed for multimodal approaches. There is a strong need for a simple, all-rounder and flexible platform.
17+
With a growing amount of patient data such as sequencing, imaging, and medical records, electronic health records (EHR) are now central to drive research and improve diagnosis of patients by using multimodal data. Exploiting patient data is a challenge as patient data exploitation tools ecosystem is often fragmented into tools to digitize and format the data and those interpreting the data (exploration, diagnosis). Furthermore, as most of the tools are specialized in one type of data, a multitude of software is needed for multimodal approaches. There is a strong need for a simple, all-rounder and flexible platform.
1818
**Results**
19-
In this paper we present EHRoes, an all-in-one web application for patients’ data digitization and exploration. With its module-based architecture, we developed four modules to: (i) create a set of standard vocabulary for a domain, (ii) automatically digitize free-text data to a set of standard terms, (iii) annotate images with standard vocabulary using automatic segmentation and (iv) generate an automatic visualization dashboard to provide insight on the data and perform automatic diagnosis suggestions. Using this platform, we successfully digitized 89 muscle histology reports from patients with congenital myopathies and we obtained an accuracy of 0.75 for congenital myopathy subtypes classification.
19+
In this paper we present EHRoes, an all-in-one web application to digitize and explore patient data. EHRoes has a module-based architecture, composed of four modules to: (i) create a standard vocabulary for a domain (ii) automatically digitize free-text data to a set of standard terms (iii) annotate images with standard vocabulary using automatic segmentation and (iv) generate an automatic visualization dashboard to provide insight on the data and perform automatic diagnosis suggestions. We demonstrated the utility of EHRoes by digitizing 40 artificial muscle histology reports of patients with congenital myopathies.
2020
**Conclusions**
21-
With EHRoes we created a platform for both patients data digitization and exploration that can handle image data and free-text data. As it uses user designed standard vocabulary, it is highly flexible to fit any domain of research. It can be used both as a patient registry with automatic diagnosis or as a research tool to explore a cohort of patients.
22-
A demo instance of the application is available at https://ehroes.lbgi.fr.
21+
With EHRoes we created a platform for both digitization and exploration of patient data that can handle image data and free-text data. As it uses user-designed standard vocabulary, it is highly flexible to fit any domain of research. It can be used both as a patient registry with automatic diagnosis or as a research tool to explore a cohort of patients. A demo instance of the application is available at https://ehroes.lbgi.fr.
2322

2423
## MYO-xIA Project
2524

0 commit comments

Comments
 (0)