1
|
Wirth W, Maschek S, Marijnissen ACA, Lalande A, Blanco FJ, Berenbaum F, van de Stadt LA, Kloppenburg M, Haugen IK, Ladel CH, Bacardit J, Wisser A, Eckstein F, Roemer FW, Lafeber FPJG, Weinans HH, Jansen M. Test-retest precision and longitudinal cartilage thickness loss in the IMI-APPROACH cohort. Osteoarthritis Cartilage 2023; 31:238-248. [PMID: 36336198 DOI: 10.1016/j.joca.2022.10.015] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/06/2022] [Revised: 09/22/2022] [Accepted: 10/30/2022] [Indexed: 11/06/2022]
Abstract
OBJECTIVE To investigate the test-retest precision and to report the longitudinal change in cartilage thickness, the percentage of knees with progression and the predictive value of the machine-learning-estimated structural progression score (s-score) for cartilage thickness loss in the IMI-APPROACH cohort - an exploratory, 5-center, 2-year prospective follow-up cohort. DESIGN Quantitative cartilage morphology at baseline and at least one follow-up visit was available for 270 of the 297 IMI-APPROACH participants (78% females, age: 66.4 ± 7.1 years, body mass index (BMI): 28.1 ± 5.3 kg/m2, 55% with radiographic knee osteoarthritis (OA)) from 1.5T or 3T MRI. Test-retest precision (root mean square coefficient of variation) was assessed from 34 participants. To define progressor knees, smallest detectable change (SDC) thresholds were computed from 11 participants with longitudinal test-retest scans. Binary logistic regression was used to evaluate the odds of progression in femorotibial cartilage thickness (threshold: -211 μm) for the quartile with the highest vs the quartile with the lowest s-scores. RESULTS The test-retest precision was 69 μm for the entire femorotibial joint. Over 24 months, mean cartilage thickness loss in the entire femorotibial joint reached -174 μm (95% CI: [-207, -141] μm, 32.7% with progression). The s-score was not associated with 24-month progression rates by MRI (OR: 1.30, 95% CI: [0.52, 3.28]). CONCLUSION IMI-APPROACH successfully enrolled participants with substantial cartilage thickness loss, although the machine-learning-estimated s-score was not observed to be predictive of cartilage thickness loss. IMI-APPROACH data will be used in subsequent analyses to evaluate the impact of clinical, imaging, biomechanical and biochemical biomarkers on cartilage thickness loss and to refine the machine-learning-based s-score. CLINICALTRIALS GOV IDENTIFICATION NCT03883568.
Collapse
Affiliation(s)
- W Wirth
- Department of Imaging & Functional Musculoskeletal Research, Institute of Anatomy & Cell Biology, Paracelsus Medical University Salzburg & Nuremberg, Salzburg, Austria; Ludwig Boltzmann Inst. for Arthritis and Rehabilitation, Paracelsus Medical University Salzburg & Nuremberg, Salzburg, Austria; Chondrometrics GmbH, Freilassing, Germany.
| | - S Maschek
- Department of Imaging & Functional Musculoskeletal Research, Institute of Anatomy & Cell Biology, Paracelsus Medical University Salzburg & Nuremberg, Salzburg, Austria; Chondrometrics GmbH, Freilassing, Germany.
| | - A C A Marijnissen
- University Medical Center Utrecht and Utrecht University, Utrecht, the Netherlands.
| | - A Lalande
- Institut de Recherches Internationales Servier, Suresnes, France.
| | - F J Blanco
- Grupo de Investigación de Reumatología (GIR), INIBIC - Complejo Hospitalario Universitario de A Coruña, SERGAS. Centro de Investigación CICA, Departamento de Fisioterapia y Medicina, Universidad de A Coruña, A Coruña, Spain.
| | - F Berenbaum
- Department of Rheumatology, AP-HP Saint-Antoine Hospital, Paris, France; INSERM, Sorbonne University, Paris, France.
| | - L A van de Stadt
- Rheumatology, Leiden University Medical Center, Leiden, the Netherlands.
| | - M Kloppenburg
- Rheumatology, Leiden University Medical Center, Leiden, the Netherlands; Clinical Epidemiology, Leiden University Medical Center, Leiden, the Netherlands.
| | - I K Haugen
- Division of Rheumatology and Research, Diakonhjemmet Hospital, Oslo, Norway.
| | - C H Ladel
- CHL4special consultancy, Darmstadt, Germany.
| | - J Bacardit
- School of Computing, Newcastle University, Newcastle, United Kingdom.
| | - A Wisser
- Department of Imaging & Functional Musculoskeletal Research, Institute of Anatomy & Cell Biology, Paracelsus Medical University Salzburg & Nuremberg, Salzburg, Austria; Ludwig Boltzmann Inst. for Arthritis and Rehabilitation, Paracelsus Medical University Salzburg & Nuremberg, Salzburg, Austria; Chondrometrics GmbH, Freilassing, Germany.
| | - F Eckstein
- Department of Imaging & Functional Musculoskeletal Research, Institute of Anatomy & Cell Biology, Paracelsus Medical University Salzburg & Nuremberg, Salzburg, Austria; Ludwig Boltzmann Inst. for Arthritis and Rehabilitation, Paracelsus Medical University Salzburg & Nuremberg, Salzburg, Austria; Chondrometrics GmbH, Freilassing, Germany.
| | - F W Roemer
- Quantitative Imaging Center, Department of Radiology, Boston University School of Medicine, Boston, MA, USA; Department of Radiology, Universitätsklinikum Erlangen and Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Erlangen, Germany.
| | - F P J G Lafeber
- University Medical Center Utrecht and Utrecht University, Utrecht, the Netherlands.
| | - H H Weinans
- University Medical Center Utrecht and Utrecht University, Utrecht, the Netherlands.
| | - M Jansen
- University Medical Center Utrecht and Utrecht University, Utrecht, the Netherlands.
| |
Collapse
|
2
|
Ruiz-Romero C, Önnerfjord P, Calamia V, Fernández Puente P, Lourido L, Paz González R, Widera P, Bacardit J, Bay-Jensen AC, Berenbaum F, Haugen IK, Kloppenburg M, Mastbergen S, Larkin J, Mobasheri A, Blanco FJ. OP0224 DISCOVERY PROTEOMICS ANALYSIS IN THE IMI-APPROACH COHORT SHOWS THE DIFFERENTIAL MODULATION AT 24 MONTHS OF PROTEIN PROFILES ASSOCIATED WITH STRUCTURAL OR PAIN PROGRESSION IN OSTEOARTHRITIS. Ann Rheum Dis 2022. [DOI: 10.1136/annrheumdis-2022-eular.1091] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022]
Abstract
BackgroundThe characterization of differential molecular endotypes in osteoarthritis (OA) is essential for enabling patient stratification to enhance clinical trials, facilitate the development of targeted and individualized treatments.ObjectivesThis study aimed to characterize the profile and dynamics over 24 months (24M) of proteins present in the sera from patients in the IMI-Applied Public-Private Research enabling OsteoArthritis Clinical Headway (APPROACH) cohort who exhibited structural (radiographic) and pain progression compared to participants who did not progressed during this period.MethodsForty-five patients enrolled in the IMI-APPROACH cohort were selected for the proteomic analysis. Among these, 15 showed the highest structural progression (group S) and 15 the highest pain progression (group P) at 24M, according to the APPROACH criteria [1], while 15 did not progressed neither in S nor in P. Baseline (BL) and 24M serum samples were depleted of the top 14 most abundant proteins and then analysed by liquid chromatography coupled to tandem mass spectrometry (LC-MS/MS) on a nanoElute-LC coupled to a high-resolution TIMS-QTOF (timsTOF Pro, Bruker Daltonics). Proteins were identified and quantified using the LFQ algorithm of MaxQuant software. Further statistical and bioinformatic analyses were performed using Perseus and OmicsAnalyst software.ResultsThe proteomic analysis resulted in the identification of 558 proteins (10,466 peptides) in the serum samples. A label-free quantification algorithm was employed to quantify 468 proteins in the samples. Hierarchical clustering of the data showed the differences in protein abundance were more relevant longitudinally (BL to 24M) than in cross-sectional comparisons between the three groups under study (N, P or S). Sixty-three proteins were significantly altered (fold change >=1.5, p<0.05) when comparing BL to 24M in the N group (15 increased and 48 decreased), 53 in the P group (20 increased and 33 decreased) and 93 in the S group (19 increased and 74 decreased). Interestingly, two different endotypes were detected at baseline in the N and S groups, based on these protein modulations.The overlapping of these proteomic profiles was analyzed between groups and is shown in the Figure 1. Proteins modulated specifically in the N group may be associated with mechanisms related with joint repair. On the other hand, six proteins (including two apolipoproteins) were increased at 24M only in the P group. Finally, 30 proteins were modulated only in the S group: five of them increased and 25 decreased. Remarkably, this latter group includes lubricin, chaperones and proteins related with proteoglycan binding, such as COMP, fibronectin or histidine-rich glycoprotein.Figure 1.Circulating proteins identified as modulated after 24M follow-up in 45 patients from the APPROACH cohort that progressed in structure (S group; n=15), pain (P group; n=15) or did not progressed (N group; n=15). The numbers with arrows indicate those proteins that decrease (arrow pointing down) or increase (arrow pointing up) compared to baseline.ConclusionThe modulation of specific protein profiles in serum were identified as associated with the progression in structure, pain or non-progression in patients from the APPROACH cohort. Proteomic changes found specifically in the S group may be interesting circulating markers of the structural affectation occurring in the joint.References[1]van Helvoort EM, et al., BMJ Open. 2020 Jul 28;10(7):e035101. doi: 10.1136/bmjopen-2019-035101.Disclosure of InterestsCristina Ruiz-Romero: None declared, Patrik Önnerfjord: None declared, Valentina Calamia: None declared, Patricia Fernández Puente: None declared, Lucía Lourido: None declared, Rocío Paz González: None declared, Pawel Widera: None declared, Jaume Bacardit: None declared, Anne-Christine Bay-Jensen Shareholder of: Nordic Bioscience, Employee of: Nordic Bioscience, Francis Berenbaum Consultant of: AstraZeneca, Boehringer, Bone Therapeutics, CellProthera, Expanscience, Galapagos, Gilead, Grunenthal, GSK, Eli Lilly, Merck Sereno, MSD, Nordic, Nordic Bioscience, Novartis, Pfizer, Roche, Sandoz, Sanofi, Servier, UCB, Peptinov, 4P Pharma, 4Moving Biotech, Grant/research support from: TRB Chemedica, Ida K. Haugen Consultant of: Abbvie and Novartis, Grant/research support from: Pfizer, Margreet Kloppenburg Consultant of: Abbvie, Pfizer, Levicept, GlaxoSmithKline, Merck-Serono, Kiniksa, Flexion, Galapagos, Jansen, CHDR, Novartis, UCB, Simon Mastbergen: None declared, Jonathan Larkin Shareholder of: GlaxoSmithKline, Employee of: GlaxoSmithKline, Ali Mobasheri Consultant of: Merck KGaA, Kolon TissueGene, Pfizer Inc., Galapagos-Servier, Image Analysis Group (IAG), Artialis SA, Aché Laboratórios Farmacêuticos, AbbVie, Guidepoint Global, Alphasights, Science Branding Communications, GSK, Flexion Therapeutics, Pacira Biosciences, Sterifarma, Bioiberica, SANOFI, Genacol, Kolon Life Science, BRASIT/BRASOS, GEOS, MCI Group, Alcimed, Abbot, Laboratoires Expansciences, SPRIM Communications, Frontiers Media and University Health Network (UHN) Toronto, Grant/research support from: Merck KGaA, Kolon TissueGene, Pfizer Inc., Galapagos-Servier, Image Analysis Group (IAG), Artialis SA, Aché Laboratórios Farmacêuticos, AbbVie, Guidepoint Global, Alphasights, Science Branding Communications, GSK, Flexion Therapeutics, Pacira Biosciences, Sterifarma, Bioiberica, SANOFI, Genacol, Kolon Life Science, BRASIT/BRASOS, GEOS, MCI Group, Alcimed, Abbot, Laboratoires Expansciences, SPRIM Communications, Frontiers Media and University Health Network (UHN) Toronto, Francisco J. Blanco Consultant of: Gedeon Richter Plc., Bristol-Myers Squibb International Corporation (BMSIC), Sun Pharma Global FZE, Celgene Corporation, Janssen Cilag International N.V, Janssen Research & Development, Viela Bio, Inc., Astrazeneca AB, UCB BIOSCIENCES GMBH, UCB BIOPHARMA SPRL, AbbVie Deutschland GmbH & Co.KG, Merck KGaA, Amgen, Inc., Novartis Farmacéutica, S.A., Boehringer Ingelheim España, S.A, CSL Behring, LLC, Glaxosmithkline Research & Development Limited, Pfizer Inc, Lilly S.A., Corbus Pharmaceuticals Inc., Biohope Scientific Solutions for Human Health S.L., Centrexion Therapeutics Corp., Sanofi, TEDEC-MEIJI FARMA S.A., Kiniksa Pharmaceuticals, Ltd., Fundación para la Investigación Biomédica Del Hospital Clínico San Carlos, Grünenthal and Galapagos, Grant/research support from: Pfizer
Collapse
|
3
|
Rajgor A, McQueen A, Ali T, Aboagye E, Obara B, Bacardit J, McCuloch D, Hamilton D. 195 The Application of Radiomics in Laryngeal Cancer: The Forgotten Cohort. Br J Surg 2021. [DOI: 10.1093/bjs/znab259.925] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022]
Abstract
Abstract
Background
Radiomics is a novel method of extracting data from medical images that is difficult to visualise through the naked eye. This technique transforms digital images that hold information on pathology into high-dimensional-data for analysis. Radiomics has the potential to enhance laryngeal cancer care and to date, has shown promise in various other specialties.
Aim
The aim of this review is to summarise the applications of this technique to laryngeal cancer and potential future benefits.
Method
A comprehensive systematic review-informed search of the MEDLINE and EMBASE online databases was undertaken. Keywords ‘laryngeal cancer’ OR ‘larynx’ OR ‘larynx cancer’ OR ‘head and neck cancer’ were combined with ‘radiomic’ OR ‘signature’ OR ‘machine learning’ OR ‘artificial intelligence’. Additional articles were obtained from bibliographies using the ‘snowball method’.
Results
Seventeen articles were identified that evaluated the role of radiomics in laryngeal cancer. Two studies affirmed the value of radiomics in improving the accuracy of staging, whilst fifteen studies highlighted the potential prognostic value of radiomics in laryngeal cancer. Twelve (of thirteen) studies incorporated an array of different head and neck cancers in the analysis and only one study assessed laryngeal cancer exclusively.
Conclusions
Literature to date has various limitations including, small and heterogeneous cohorts incorporating patients with head and neck cancers of distinct anatomical subsites and stages. The lack of uniform data on solely laryngeal cancer and radiomics means drawing conclusions is difficult, although these studies have affirmed its value. Further large prospective studies exclusively in laryngeal cancer are required to unlock its true potential.
Collapse
Affiliation(s)
- A Rajgor
- Newcastle University, Newcastle-Upon-Tyne, United Kingdom
- Newcastle-Upon-Tyne NHS Foundation Trust, Newcastle-Upon-Tyne, United Kingdom
| | - A McQueen
- Newcastle-Upon-Tyne NHS Foundation Trust, Newcastle-Upon-Tyne, United Kingdom
| | - T Ali
- Newcastle-Upon-Tyne NHS Foundation Trust, Newcastle-Upon-Tyne, United Kingdom
| | - E Aboagye
- Imperial College London, London, United Kingdom
| | - B Obara
- Newcastle University, Newcastle-Upon-Tyne, United Kingdom
| | - J Bacardit
- Newcastle University, Newcastle-Upon-Tyne, United Kingdom
| | - D McCuloch
- Newcastle University, Newcastle-Upon-Tyne, United Kingdom
| | - D Hamilton
- Newcastle-Upon-Tyne NHS Foundation Trust, Newcastle-Upon-Tyne, United Kingdom
| |
Collapse
|
4
|
Lazzarini N, Runhaar J, Bay-Jensen AC, Thudium CS, Bierma-Zeinstra SMA, Henrotin Y, Bacardit J. A machine learning approach for the identification of new biomarkers for knee osteoarthritis development in overweight and obese women. Osteoarthritis Cartilage 2017; 25:2014-2021. [PMID: 28899843 DOI: 10.1016/j.joca.2017.09.001] [Citation(s) in RCA: 51] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/08/2017] [Revised: 08/16/2017] [Accepted: 09/02/2017] [Indexed: 02/02/2023]
Abstract
OBJECTIVE Knee osteoarthritis (OA) is among the higher contributors to global disability. Despite its high prevalence, currently, there is no cure for this disease. Furthermore, the available diagnostic approaches have large precision errors and low sensitivity. Therefore, there is a need for new biomarkers to correctly identify early knee OA. METHOD We have created an analytics pipeline based on machine learning to identify small models (having few variables) that predict the 30-months incidence of knee OA (using multiple clinical and structural OA outcome measures) in overweight middle-aged women without knee OA at baseline. The data included clinical variables, food and pain questionnaires, biochemical markers (BM) and imaging-based information. RESULTS All the models showed high performance (AUC > 0.7) while using only a few variables. We identified both the importance of each variable within the models as well its direction. Finally, we compared the performance of two models with the state-of-the-art approaches available in the literature. CONCLUSIONS We showed the potential of applying machine learning to generate predictive models for the knee OA incidence. Imaging-based information were found particularly important in the proposed models. Furthermore, our analysis confirmed the relevance of known BM for knee OA. Overall, we propose five highly predictive small models that can be possibly adopted for an early prediction of knee OA.
Collapse
Affiliation(s)
- N Lazzarini
- ICOS Research Group, School of Computing, Newcastle University, UK; D-BOARD Consortium, An FP7 Programme By the European Committee
| | - J Runhaar
- D-BOARD Consortium, An FP7 Programme By the European Committee; Erasmus University Medical Center Rotterdam, the Netherlands, Dept. of General Practice
| | - A C Bay-Jensen
- D-BOARD Consortium, An FP7 Programme By the European Committee; Nordic Bioscience, Copenhagen, Denmark
| | - C S Thudium
- D-BOARD Consortium, An FP7 Programme By the European Committee; Nordic Bioscience, Copenhagen, Denmark
| | - S M A Bierma-Zeinstra
- D-BOARD Consortium, An FP7 Programme By the European Committee; Erasmus University Medical Center Rotterdam, the Netherlands, Dept. of General Practice; Erasmus University Medical Center Rotterdam, the Netherlands, Dept. of Orthopedics
| | - Y Henrotin
- D-BOARD Consortium, An FP7 Programme By the European Committee; University of Liège, Belgium; Artialis SA, Liège, Belgium
| | - J Bacardit
- ICOS Research Group, School of Computing, Newcastle University, UK; D-BOARD Consortium, An FP7 Programme By the European Committee.
| |
Collapse
|