Machine learning-based medical imaging diagnosis in patients with temporomandibular disorders: a diagnostic test accuracy systematic review and meta-analysis

OBJECTIVES

Temporomandibular disorders (TMDs) are the second most common musculoskeletal condition which are challenging tasks for most clinicians. Recent research used machine learning (ML) algorithms to diagnose TMDs intelligently. This study aimed to systematically evaluate the quality of these studies and assess the diagnostic accuracy of existing models.

MATERIALS AND METHODS

Twelve databases (Europe PMC, Embase, etc.) and two registers were searched for published and unpublished studies using ML algorithms on medical images. Two reviewers extracted the characteristics of studies and assessed the methodological quality using the QUADAS-2 tool independently.

RESULTS

A total of 28 studies (29 reports) were included: one was at unclear risk of bias and the others were at high risk. Thus the certainty of evidence was quite low. These studies used many types of algorithms including 8 machine learning models (logistic regression, support vector machine, random forest, etc.) and 15 deep learning models (Resnet152, Yolo v5, Inception V3, etc.). The diagnostic accuracy of a few models was relatively satisfactory. The pooled sensitivity and specificity were 0.745 (0.660-0.814) and 0.770 (0.700-0.828) in random forest, 0.765 (0.686-0.829) and 0.766 (0.688-0.830) in XGBoost, and 0.781 (0.704-0.843) and 0.781 (0.704-0.843) in LightGBM.

CONCLUSIONS

Most studies had high risks of bias in Patient Selection and Index Test. Some algorithms are relatively satisfactory and might be promising in intelligent diagnosis. Overall, more high-quality studies and more types of algorithms should be conducted in the future.

CLINICAL RELEVANCE

We evaluated the diagnostic accuracy of the existing models and provided clinicians with much advice about the selection of algorithms. This study stated the promising orientation of future research, and we believe it will promote the intelligent diagnosis of TMDs.

Global prevalence of edentulism and dental caries in middle-aged and elderly persons: A systematic review and meta-analysis

OBJECTIVE

The aim of the study was to analyze data collected from studies worldwide on the prevalence of edentulism and dental caries, in community-dwellers aged ≥ 45 years.

DATA

Inclusion criteria; participants aged ≥ 45 years, community-dwellers. Exclusion criteria; participants aged < 45 years, in nursing homes, data obtained from dental clinics or pre-2005. The quality assessment tool by The National Heart, Lung and Blood Institute for Observational Cohort and Cross-sectional studies was used. Meta-analysis using the random-effects model (95% confidence interval) was done with data on participants who were edentulous and/or had active dental caries and stratified by regions of the world, age and Gross National Income per capita. Limitations in the data arose from several factors such as design of the studies included differences in socioeconomic status and access to health care among different countries.

SOURCES

Embase, MEDLINE via Pubmed and Scopus, manual searches, from January 2016, restricted to English. Experts from different countries were contacted to identify National oral health surveys (NOHS) conducted from 2010 onwards.

STUDY SELECTION

Eighty-six papers and seventeen NOHS were selected for data extraction. Majority of the studies (n = 69) were cross-sectional and of fair quality. 1.1%-70%, 4.9% - 98% prevalence of edentulism and dental caries, respectively. 22%, 45% estimated random-effects pooled prevalence of edentulism and dental caries, respectively.

CONCLUSIONS

Within the limitations of this study, the findings indicate that untreated dental caries and tooth loss are prevalent on a global level with wide variations among different countries, age groups and socioeconomic status.

CLINICAL SIGNIFICANCE

The findings demonstrate the reality of the new cohort of older adults, with higher tooth retention implying more dental caries incidence and the need for different care strategies to ensure better oral health. Large variations and difficulty in making comparisons among different countries highlight the need for more standardized, regular research.

Single-visit or multiple-visit root canal treatment: systematic review, meta-analysis and trial sequential analysis

OBJECTIVES

Single-visit root canal treatment has some advantages over conventional multivisit treatment, but might increase the risk of complications. We systematically evaluated the risk of complications after single-visit or multiple-visit root canal treatment using meta-analysis and trial-sequential analysis.

DATA

Controlled trials comparing single-visit versus multiple-visit root canal treatment of permanent teeth were included. Trials needed to assess the risk of long-term complications (pain, infection, new/persisting/increasing periapical lesions ≥1 year after treatment), short-term pain or flare-up (acute exacerbation of initiation or continuation of root canal treatment).

SOURCES

Electronic databases (PubMed, EMBASE, Cochrane Central) were screened, random-effects meta-analyses performed and trial-sequential analysis used to control for risk of random errors. Evidence was graded according to GRADE.

STUDY SELECTION

29 trials (4341 patients) were included, all but 6 showing high risk of bias. Based on 10 trials (1257 teeth), risk of complications was not significantly different in single-visit versus multiple-visit treatment (risk ratio (RR) 1.00 (95% CI 0.75 to 1.35); weak evidence). Based on 20 studies (3008 teeth), risk of pain did not significantly differ between treatments (RR 0.99 (95% CI 0.76 to 1.30); moderate evidence). Risk of flare-up was recorded by 8 studies (1110 teeth) and was significantly higher after single-visit versus multiple-visit treatment (RR 2.13 (95% CI 1.16 to 3.89); very weak evidence). Trial-sequential analysis revealed that firm evidence for benefit, harm or futility was not reached for any of the outcomes.

CONCLUSIONS

There is insufficient evidence to rule out whether important differences between both strategies exist.

CLINICAL SIGNIFICANCE

Dentists can provide root canal treatment in 1 or multiple visits. Given the possibly increased risk of flare-ups, multiple-visit treatment might be preferred for certain teeth (eg, those with periapical lesions).