V1 V2 V3
ACLART / 15022
rev.03 · 26.04.26
Classif.R&D · open
DomainBiomechanics · ML
Period2024 → 2027
FundCOMPETE2023-FEDER-00867200
PIJ. A. Simões
Status● In progress
Research dossier Ed. 2025 / 2026 ESAD.IDEA INESC TEC × UA

AI·driven
in silico
simulation
for ACL reconstruction.

A predictive model coupling clinical-surgery data with finite-element biomechanics — built to tell a surgeon, before surgery, how a given patient's reconstruction is likely to perform.
Dataset
1,000+
ACLR records · PT / SE / NO / DK
Researchers
13
4 research teams
0
5
10
15
20
25
30
35
§ 01 / 07
00
Abstract
A predictive model for ACLR — informed by biomechanics, not hope.

ACLART intersects anterior cruciate ligament reconstruction (ACLR) with AI machine learning and in silico simulation. Individual patient clinical & surgery data are fed into ML algorithms and coupled with finite-element computational simulation.

The output is a per-patient prediction of surgical outcome, measured across validated instruments: KOOS, TALS, LKSS, and IKDC-SKF — used both to improve patient selection and to stratify revision-surgery probability.

Deliverable: a point-of-care clinical calculator for ACLR, externally validated on independent datasets, disseminated through peer-reviewed publication and a national SPOT seminar.

ACL reconstruction machine learning finite element KOOS · TALS · LKSS · IKDC in silico revision probability
§ 02 / 07
06
Objectives
Six targets, arranged as a matrix.
A · Patient
B · Practice
C · Research
01
A·01
i.

Patient outcomes & long-term prognosis

Subjective failure risk at patient-specific level during pre-op discussion.

B·01
ii.

Refined technique & rehabilitation

Tailored to graft choice, tunnel orientation, fixation device.

C·01
iii.

Reduce complications & failures

Identify risk factors before the surgical team commits to a plan.

02
A·02
iv.

Research platform beyond the grant

Large-scale continuous analysis; protocol for new contributing centres.

B·02
v.

Deeper biomechanical insight

Simulations that expose graft / bone / boundary interactions.

C·02
vi.

Advance knowledge & dissemination

Journals, conferences and a national SPOT seminar.

§ 03 / 07
05
Methodology
The research pipeline — five stages, TRIPOD-compliant.
i · input01

Clinical data collection

Pre- and post-op records, surgical reports, MRI imaging; Portuguese centres + Scandinavian registers.

n~1000
vars> 40
sources4 registers
ii · clean02

Pre-processing & data mining

Outliers, normalization, one-hot encoding, feature selection, dimensionality reduction.

methodPCA · χ²
split70 / 15 / 15
cvk-fold · LOO
iii · model03

ML modelling

Logistic regression · SVM · random forests · neural networks, ensembled for regression on KOOS QOL.

targetKOOS QOL
auxTALS · LKSS · IKDC
metricR² · MAE · AUC
iv · simulate04

In silico FEA

FE models of graft/bone/fixation, validated against experimental knee replicas.

solverAbaqus
meshtet4 / hex8
valid.in vitro
v · ship05

Validation & dissemination

External datasets, point-of-care calculator, peer-reviewed publication.

pubs≥ 3
conf.SICOT · SPOT
toolclinical calc.
§ 04 / 07
05
Tasks
Work packages on a 36-month schedule.
Work pkg.
M3
M6
M9
M12
M15
M18
M21
M24
M27
M30
M33
M36
T1
Mgmt & diss.
Management · dissemination · SPOT seminar
T2
Data collection
ACLR data collection & statistics
T3
ML modelling
ML applied to clinical-surgery data
T4
In silico
AI applied to in silico simulation
T5
Prediction
Outcome predictions · revision probability
Baseline work package Principal ML modelling (T3) Synthesis / prediction 36 months · Start 2024 · End 2027
§ 05 / 07
13
Team
Thirteen researchers across four teams.
#
Researcher
Role
Team
CiênciaVitae
01
José António de Oliveira Simões
Principal investigator
Coordination
F81E·8F49·9353
02
José Carlos Noronha
Senior researcher
Surgical medical
8419·D869·FAF5
03
Fernando Manuel Pereira da Fonseca
Senior researcher
Surgical medical
3C10·DDBF·97AD
04
Orlando José de Almeida Branco Simões
Researcher
Surgical medical
2618·2B91·AA09
05
Orlando José Reis Frazão
Researcher
Surgical medical
FF16·7804·383D
06
Susana Cristina Ribeiro Novais
Researcher
Surgical medical
EB1B·D0B4·4A20
07
Ricardo Jorge Teixeira de Sousa
Researcher
Surgical medical
CC1D·816B·FF31
08
João Miguel Pinto Pereira da Silva
Senior researcher
AI · ML
8A11·186A·3F2F
09
António Manuel Amaral Monteiro Ramos
Senior researcher
In silico
AF12·6860·6E65
10
João Pedro Moreira de Oliveira
Researcher
In silico
4415·3067·D56A
11
José Luís Santos
Senior researcher
In vitro
9D12·BC3E·ECAA
12
Paulo Roriz
Researcher
In vitro
8416·5174·26DE
13
Gonçalo Duarte Nunes
PhD researcher
Cross-team
B81F·9A45·6B22
§ 06 / 07
06
Outputs
Publications & dissemination, to date.

International journal 02 entries

[J1]
Simões, O. B., Ramos, A., Sevivas, N., Simões, J. A. (2025). Artificial intelligence-driven in silico simulation for prediction of anterior cruciate ligament reconstruction clinical outcomes. Computational and Artificial Intelligence for Mechanics and Biomechanics, 1, 45–51.
[J2]
Ramos, A., Anacleto, C., Simões, J. A. (2025). Insights from a computational model of the Anterior Cruciate Ligament Reconstruction. Results in Engineering, 27, 106125.

National journal 01 entry

[J3]
Matos, A., Oliveira, J. P., Simões, J. A., Ramos, A. (2026). Modelo experimental para medição das forças dos ligamentos na articulação do joelho intacta — modelo I. Mecânica Experimental (in press).

International conference 02 entries

[C1]
Simões, O. B., Ramos, A., Sevivas, N., Simões, J. A. (2025, Sep 18–19). AI-driven in silico simulation for ACLR clinical outcomes. 1st Conf. Computational & AI for Mechanics and Biomechanics, Porto.
[C2]
Simões, O. B., Sousa, R., Sevivas, N., Simões, J. A., Ramos, A. (2026, Sep 29 – Oct 1). Large language models as assistive tools for outcome analysis after ACL reconstruction. 46th SICOT Orthopaedic World Congress, Kyoto.

National conference 01 entry

[C3]
Matos, A., Oliveira, J. P., Simões, J. A., Ramos, A. (2026, Feb 25–27). Modelo experimental para medição das forças dos ligamentos. 13º Congresso Nacional em Mecânica Experimental, Porto.
§ 07 / 07
03
Partners & Funding
Coordination, partners & financing instrument.
Coordination
esad.idea
esadidea.pt
Research partner
INESC TEC
inesctec.pt
Research partner
Univ. Aveiro
ua.pt
ProgrammePITD · ERDF
Source fundEuropean Regional Development Fund
Operation typeScientific R&D
Specific objectiveResearch & innovation capacity
Operation codeCOMPETE2023-FEDER-00867200
Project №15022
ACLART.
Document
  • Rev. 03
  • 26 · 04 · 2026
  • EN / PT
Filing
  • 15022 / ACLART
  • COMPETE 2030
  • ERDF
Type
  • Inter · 300–900
  • DM Serif Display
  • JetBrains Mono
© 2026 ACLART · All research materials available under open licence where noted. V3 — Data Index