Introduction: Clinical decision support systems (CDSS) developed in Indonesia for caries and periodontal risk assessment show diagnostic performance comparable to conventional practice. Objective: To synthesize reported diagnostic accuracy, comparative performance, and early implementation outcomes of Indonesian dental CDSS for caries and periodontal assessment. Methods: We summarized an evidence set identified from a large academic corpus and screened to include Indonesian dentistry studies that (i) developed/validated a CDSS with Indonesian patient data, (ii) compared against conventional or expert assessment, and (iii) reported diagnostic accuracy or implementation outcomes. Data elements extracted included study design, CDSS type, validation approach, and quantitative outcomes (e.g., sensitivity, specificity, accuracy, odds ratios, user acceptance). Discussion: Across caries detection, reported sensitivity ranged from 81.3% to 96.3% and specificity from 92% to 100%; accuracies spanned 82.7% to 100%. Methods included MobileNet-v3/U-net, Naive Bayes, Dempster–Shafer, fuzzy logic, case-based reasoning, and bespoke tools (e.g., SKOR GIGI; Pediatric Caries Predictor). Periodontal assessments reported accuracies of 90–96%, with an RCT noting higher odds of correct staging (OR 4.43, p=0.001) and grading (OR 30.30, p<0.001) versus conventional evaluation; an NLP (BERT) pipeline outperformed a multilayer perceptron for staging/grade classification. Early implementations (web-based tools, school screening) indicated improved detection/coverage, better oral-health indices, high parent awareness (96%), and user satisfaction (~88%). Conclusion: Within Indonesian settings, dental CDSS can match or exceed conventional diagnostic accuracy and support treatment recommendations, though generalizability is limited by small samples, incomplete reporting, and scarce pragmatic evaluations.