Back

PHeP: TrustAlert Open-Source Platform for Enhancing Predictive Healthcare with Deep Learning

Contaldo, S. G.; Pietropaolo, E.; Bosio, L.; Pernice, S.; Terrone, I.; Baccega, D.; Wang, Y.; Sahoo, R. K.; Rizzo, G.; Visconti, A.; Berchialla, P.; Beccuti, M.

2024-08-23 epidemiology
10.1101/2024.08.22.24311205 medRxiv
Show abstract

Predictive healthcare, a field revolutionized by the availability of large medical datasets and computational advancements, plays a pivotal role in enhancing patient care and healthcare system performance. Despite its significance, the training and deployment of predictive healthcare models present substantial challenges. To address these, we introduce the Predictive Healthcare Platform (PHeP), an open-source platform that simplifies the use of pretrained models. PHeP, developed under the TrustAlert project, offers an intuitive web-based graphical interface, making advanced predictive healthcare accessible to users without extensive computational skills or expensive computational resources. This paper presents the design and functionality of PHeP, demonstrating its effectiveness in predictive healthcare tasks, such as predicting re-hospitalization at three months using pre-trained BERT models.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

1
GigaScience
◐ 212 papers in training set
Top 0.2%
8.0%
Similar papers in this journal
2
PLOS ONE
● 5266 papers in training set
Top 22%
7.4%
Similar papers in this journal
3
Nature Communications
○ 5641 papers in training set
Top 23%
6.8%
Similar papers in this journal
4
PLOS Computational Biology
● 1863 papers in training set
Top 6%
5.6%
Similar papers in this journal
5
Scientific Reports
○ 3612 papers in training set
Top 14%
5.5%
Similar papers in this journal
6
Patterns
○ 78 papers in training set
Top 0.2%
5.5%
7
npj Digital Medicine
○ 118 papers in training set
Top 1%
4.9%
8
PLOS Digital Health
● 106 papers in training set
Top 2%
4.1%
9
IEEE Journal of Biomedical and Health Informatics
● 37 papers in training set
Top 0.2%
4.1%
50% of probability mass above
10
Bioinformatics
◐ 1204 papers in training set
Top 6%
2.8%
11
Bioinformatics Advances
◐ 203 papers in training set
Top 2%
2.7%
12
Journal of Medical Internet Research
◐ 87 papers in training set
Top 1%
2.4%
13
Frontiers in Digital Health
○ 24 papers in training set
Top 0.4%
2.1%
14
Heliyon
○ 152 papers in training set
Top 3%
2.0%
15
Frontiers in Public Health
○ 148 papers in training set
Top 3%
1.8%
16
IEEE Access
● 35 papers in training set
Top 0.6%
1.8%
17
Communications Medicine
○ 113 papers in training set
Top 2%
1.8%
18
iScience
○ 1154 papers in training set
Top 18%
1.7%
19
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 5%
1.1%
20
Nature Machine Intelligence
○ 70 papers in training set
Top 2%
1.1%
21
Advanced Science
○ 286 papers in training set
Top 8%
1.0%
22
Biology
○ 45 papers in training set
Top 0.6%
1.0%
23
eLife
● 5828 papers in training set
Top 63%
1.0%
24
BMC Bioinformatics
○ 457 papers in training set
Top 5%
1.0%
25
Frontiers in Genetics
○ 230 papers in training set
Top 5%
0.9%
26
Nature Medicine
○ 125 papers in training set
Top 4%
0.6%
27
Genome Biology
○ 637 papers in training set
Top 9%
0.6%
28
JMIRx Med
◐ 32 papers in training set
Top 2%
0.6%
29
PLOS Global Public Health
● 344 papers in training set
Top 8%
0.6%
30
Database
◐ 61 papers in training set
Top 1%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.