1
|
Rokhshad R, Mohammad-Rahimi H, Sohrabniya F, Jafari B, Shobeiri P, Tsolakis IA, Ourang SA, Sultan AS, Khawaja SN, Bavarian R, Palomo JM. Deep learning for temporomandibular joint arthropathies: A systematic review and meta-analysis. J Oral Rehabil 2024; 51:1632-1644. [PMID: 38757865 DOI: 10.1111/joor.13701] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2023] [Revised: 02/20/2024] [Accepted: 04/09/2024] [Indexed: 05/18/2024]
Abstract
BACKGROUND AND OBJECTIVE The accurate diagnosis of temporomandibular disorders continues to be a challenge, despite the existence of internationally agreed-upon diagnostic criteria. The purpose of this study is to review applications of deep learning models in the diagnosis of temporomandibular joint arthropathies. MATERIALS AND METHODS An electronic search was conducted on PubMed, Scopus, Embase, Google Scholar, IEEE, arXiv, and medRxiv up to June 2023. Studies that reported the efficacy (outcome) of prediction, object detection or classification of TMJ arthropathies by deep learning models (intervention) of human joint-based or arthrogenous TMDs (population) in comparison to reference standard (comparison) were included. To evaluate the risk of bias, included studies were critically analysed using the quality assessment of diagnostic accuracy studies (QUADAS-2). Diagnostic odds ratios (DOR) were calculated. Forrest plot and funnel plot were created using STATA 17 and MetaDiSc. RESULTS Full text review was performed on 46 out of the 1056 identified studies and 21 studies met the eligibility criteria and were included in the systematic review. Four studies were graded as having a low risk of bias for all domains of QUADAS-2. The accuracy of all included studies ranged from 74% to 100%. Sensitivity ranged from 54% to 100%, specificity: 85%-100%, Dice coefficient: 85%-98%, and AUC: 77%-99%. The datasets were then pooled based on the sensitivity, specificity, and dataset size of seven studies that qualified for meta-analysis. The pooled sensitivity was 95% (85%-99%), specificity: 92% (86%-96%), and AUC: 97% (96%-98%). DORs were 232 (74-729). According to Deek's funnel plot and statistical evaluation (p =.49), publication bias was not present. CONCLUSION Deep learning models can detect TMJ arthropathies high sensitivity and specificity. Clinicians, and especially those not specialized in orofacial pain, may benefit from this methodology for assessing TMD as it facilitates a rigorous and evidence-based framework, objective measurements, and advanced analysis techniques, ultimately enhancing diagnostic accuracy.
Collapse
Affiliation(s)
- Rata Rokhshad
- Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health, Berlin, Germany
| | - Hossein Mohammad-Rahimi
- Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health, Berlin, Germany
- Division of Artificial Intelligence Research, University of Maryland School of Dentistry, Baltimore, Maryland, USA
| | - Fatemeh Sohrabniya
- Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health, Berlin, Germany
| | - Bahare Jafari
- Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health, Berlin, Germany
| | - Parnian Shobeiri
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, United States
| | - Ioannis A Tsolakis
- Department of Orthodontics, School of Dentistry, Aristotle University of Thessaloniki, Thessaloniki, Greece
- Department of Orthodontics, School of Dental Medicine, Case Western Reserve University, Cleveland, Ohio, USA
| | - Seyed AmirHossein Ourang
- Dentofacial Deformities Research Center, Research Institute of Dental Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Ahmed S Sultan
- Division of Artificial Intelligence Research, University of Maryland School of Dentistry, Baltimore, Maryland, USA
- Department of Oncology and Diagnostic Sciences, University of Maryland School of Dentistry, Baltimore, Maryland, USA
- University of Maryland Marlene and Stewart Greenebaum Comprehensive Cancer Center, Baltimore, Maryland, USA
| | - Shehryar Nasir Khawaja
- Orofacial Pain Medicine, Shaukat Khanum Memorial Cancer Hospitals and Research Centres, Lahore and Peshawar, Pakistan
- School of Dental Medicine, Tufts University, Boston, Massachusetts, USA
| | - Roxanne Bavarian
- Department of Oral and Maxillofacial Surgery, Massachusetts General Hospital, Boston, Massachusetts, USA
- Department of Oral and Maxillofacial Surgery, Harvard School of Dental Medicine, Boston, Massachusetts, USA
| | - Juan Martin Palomo
- Department of Orthodontics, School of Dental Medicine, Case Western Reserve University, Cleveland, Ohio, USA
| |
Collapse
|
2
|
Talian I, Laputková G, Schwartzová V. Identification of crucial salivary proteins/genes and pathways involved in pathogenesis of temporomandibular disorders. OPEN CHEM 2022. [DOI: 10.1515/chem-2022-0249] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/03/2022] Open
Abstract
Abstract
Temporomandibular disorder (TMD) is a collective term for a group of conditions that lead to impairment of the function of the temporomandibular joint. The proteins/genes and signaling pathways associated with TMD are still poorly understood. The aim of this study was to identify key differentially expressed salivary proteins/genes (DEGs) associated with TMD progression using LC-MS/MS coupled with a bioinformatics approach. The protein–protein interaction network was obtained from the STRING database and the hub genes were identified using Cytoscape including cytoHubba and MCODE plug-ins. In addition, enrichment of gene ontology functions and the Reactome signaling pathway was performed. A total of 140 proteins/genes were differentially expressed. From cluster analysis, a set of 20 hub genes were significantly modulated: ALB, APOA1, B2M, C3, CAT, CLU, CTSD, ENO1, GSN, HBB, HP, HSPA8, LTF, LYZ, MMP9, S100A9, SERPINA1, TF, TPI1, and TXN. Two enriched signaling pathways, glycolysis and gluconeogenesis, and tryptophan signaling pathway involving the hub genes CAT, ENO1, and TPI1 have been identified. The rest of the hub genes were mainly enriched in the innate immune system and antimicrobial peptides signaling pathways. In summary, hub DEGs and the signaling pathways identified here have elucidated the molecular mechanisms of TMD pathogenesis.
Collapse
Affiliation(s)
- Ivan Talian
- Department of Medical and Clinical Biophysics, Faculty of Medicine, University of P. J. Šafárik , Košice , 040 11 , Slovak Republic
| | - Galina Laputková
- Department of Medical and Clinical Biophysics, Faculty of Medicine, University of P. J. Šafárik , Košice , 040 11 , Slovak Republic
| | - Vladimíra Schwartzová
- Clinic of Stomatology and Maxillofacial Surgery, Faculty of Medicine, University of P. J. Šafárik and Louis Pasteur University Hospital , Košice , 041 90 , Slovak Republic
| |
Collapse
|
3
|
Influence of different sample preparation strategies on hypothesis-driven shotgun proteomic analysis of human saliva. OPEN CHEM 2022. [DOI: 10.1515/chem-2022-0216] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/03/2022] Open
Abstract
Abstract
This research aimed to find an efficient and repeatable bottom-up proteolytic strategy to process the unstimulated human saliva. The focus is on monitoring immune system activation via the cytokine and interleukin signaling pathways. Carbohydrate metabolism is also being studied as a possible trigger of inflammation and joint damage in the context of the diagnostic procedure of temporomandibular joint disorder. The preparation of clean peptide mixtures for liquid chromatography–mass spectrometry analysis was performed considering different aspects of sample preparation: the filter-aided sample preparation (FASP) with different loadings of salivary proteins, the unfractionated saliva, amylase-depleted, and amylase-enriched salivary fractions. To optimize the efficiency of the FASP method, the protocols with the digestion in the presence of 80% acetonitrile and one-step digestion in the presence of 80% acetonitrile were used, omitting protein reduction and alkylation. The digestion procedures were repeated in the standard in-solution mode. Alternatively, the temperature of 24 and 37°C was examined during the trypsin digestion. DyNet analysis of the hierarchical networks of Gene Ontology terms corresponding to each sample preparation method for the bottom-up assay revealed the wide variability in protein properties. The method can easily be tailored to the specific samples and groups of proteins to be examined.
Collapse
|
4
|
Applications of Tandem Mass Spectrometry (MS/MS) in Protein Analysis for Biomedical Research. Molecules 2022; 27:molecules27082411. [PMID: 35458608 PMCID: PMC9031286 DOI: 10.3390/molecules27082411] [Citation(s) in RCA: 31] [Impact Index Per Article: 15.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2022] [Revised: 04/05/2022] [Accepted: 04/06/2022] [Indexed: 01/27/2023] Open
Abstract
Mass Spectrometry (MS) allows the analysis of proteins and peptides through a variety of methods, such as Electrospray Ionization-Mass Spectrometry (ESI-MS) or Matrix-Assisted Laser Desorption Ionization-Mass Spectrometry (MALDI-MS). These methods allow identification of the mass of a protein or a peptide as intact molecules or the identification of a protein through peptide-mass fingerprinting generated upon enzymatic digestion. Tandem mass spectrometry (MS/MS) allows the fragmentation of proteins and peptides to determine the amino acid sequence of proteins (top-down and middle-down proteomics) and peptides (bottom-up proteomics). Furthermore, tandem mass spectrometry also allows the identification of post-translational modifications (PTMs) of proteins and peptides. Here, we discuss the application of MS/MS in biomedical research, indicating specific examples for the identification of proteins or peptides and their PTMs as relevant biomarkers for diagnostic and therapy.
Collapse
|