Patricio Melendez Rojas

Prof. Patricio Melendez Rojas

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 December 2025 in Oral
Verified
Journal Article
Open access
PDF file
PRPatricio Melendez Rojas
Patricio Melendez Rojas
MRMacarena Rodriguez
Macarena Rodriguez
MAMarcelo Durán Anrique
Marcelo Durán Anrique
Sven NiklanderSven Niklander
Sven Niklander
MDMaría F. Villalobos Dellafiori
María F. Villalobos Dellafiori
AVAlejandro Veloz
Alejandro Veloz
Background/Objectives: Despite decades of technological progress, the diagnosis of dental caries still depends largely on subjective, operator-dependent assessment, leading to inconsistent detection of early lesions and delayed intervention. Artificial intelligence (AI) has emerged as a transformative approach capable of standardizing diagnostic performance and, in some cases, surpassing human accuracy. This scoping review critically synthesizes the current evidence on AI for caries detection and examines its true translational readiness for clinical practice. Methods: A comprehensive literature search was conducted in PubMed, Scopus, and Web of Science (WoS), covering studies published from January 2019 to June 2024, in accordance with PRISMA-ScR guidelines. Eligible studies included original research evaluating the use of AI for dental caries detection, published in English or Spanish. Review articles, editorials, opinion papers, and studies unrelated to caries detection were excluded. Two reviewers independently screened, extracted, and charted data on imaging modality, sample characteristics, AI architecture, validation approach, and diagnostic performance metrics. Extracted data were summarized narratively and comparatively across studies using tabulated and graphical formats. Results: Thirty studies were included from an initial pool of 617 records. Most studies employed convolutional neural network (CNN)-based architectures and reported strong diagnostic performance, although these results come mainly from experimental settings and should be interpreted with caution. Bitewing radiography dominated the evidence base, reflecting technological maturity and greater reproducibility compared with other imaging modalities. Conclusions: Although the reported metrics are technically robust, the current evidence remains insufficient for real-world clinical adoption. Most models were trained on small, single-source datasets that do not reflect clinical diversity, and only a few underwent external or multicenter validation. Until these translational and methodological gaps are addressed, AI for caries detection should be regarded as promising yet not fully clinically reliable. By outlining these gaps and emerging opportunities, this review offers readers a concise overview of the current landscape and the key steps needed to advance AI toward meaningful clinical implementation.

29 December 2025 in AI
Verified
Journal Article
Open access
PDF file
PRPatricio Melendez Rojas
Patricio Melendez Rojas
Jaime Eduardo Jamett RojasJaime Eduardo Jamett Rojas
Jaime Eduardo Jamett Rojas
MDMaría Fernanda Villalobos Dellafiori
María Fernanda Villalobos Dellafiori
PMPablo R Moya
Pablo R Moya
AVAlejandro Veloz
Alejandro Veloz
Automatic radiology report generation (ARRG) has emerged as a promising application of deep learning (DL) with the potential to alleviate reporting workload and improve diagnostic consistency. However, despite rapid methodological advances, the field remains technically fragmented and not yet mature for routine clinical adoption. This scoping review maps the current ARRG research landscape by examining DL architectures, multimodal integration strategies, and evaluation practices from 2015 to April 2025. Following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, a comprehensive literature search identified 89 eligible studies, revealing a marked predominance of chest radiography datasets (87.6%), primarily driven by their public availability and the accelerated development of automated tools during the COVID-19 pandemic. Most models employed hybrid architectures (73%), particularly CNN–Transformer pairings, reflecting a shift toward systems that combine local feature extraction with global contextual reasoning. Although these approaches have achieved measurable gains in textual and semantic coherence, several challenges persist, including limited anatomical diversity, weak alignment with radiological rationale, and evaluation metrics that insufficiently reflect diagnostic adequacy or clinical impact. Overall, the findings indicate a rapidly evolving but clinically immature field, underscoring the need for validation frameworks that more closely reflect radiological practice and support future deployment in real-world settings.

31 August 2022 in Journal of Oral Research
Verified
Journal Article
Closed access
FBFacultad de Odontología Universidad Andres Bello
Facultad de Odontología Universidad Andres Bello
FPFernando Peña-Bengoa
Fernando Peña-Bengoa
JMJuan Contreras-San Martín
Juan Contreras-San Martín
VPViña del Mar Practica Privada
Viña del Mar Practica Privada
PRPatricio Melendez Rojas
Patricio Melendez Rojas
Objetive: The aim of this study was to determine the prevalence, demographics, and root configuration of C-shaped canals of mandibular molars by means of cone beam computed tomography in the population of the Metropolitan Region, Chile. Material and Methods: 912 molars (456 first and 456 second molars) resulting from the analysis of 228 mandibular CT scans were evaluated. The root configuration was established by means of a panoramic reconstruction and axial tomographic sections, classifying the presence and type of canals through the analysis of five sections or cuts along the root. Data were statistically analyzed using a 5% confidence interval. Results: Of the 912 molars analyzed, 70 were classified as C-shaped canals (7.68%), corresponding to 58.33% of those molars that presented fused roots. 95.7% of this root canal configuration was observed in lower second molars, occurring more frequently in females (n=45, 64.29%). 45.65% of the cases that presented C-shaped canals were bilateral and the most frequent configuration was C3 (n=401, 66.63%) according to the Melton classification. Conclusion: The C-shaped canals of the mandibular molars in the studied population were observed mainly in second molars, showing a clear prevalence among females and a high percentage of bilaterality. The presence of fused roots significantly increases the possibility of finding this type of root configuration.

21 October 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
PRPatricio Melendez Rojas
Patricio Melendez Rojas
MRMacarena Rodriguez
Macarena Rodriguez
MAMarcelo Durán Anrique
Marcelo Durán Anrique
Sven NiklanderSven Niklander
Sven Niklander
MDMaría Fernanda Villalobos Dellafiori
María Fernanda Villalobos Dellafiori
AVAlejandro Veloz
Alejandro Veloz
Background/Objectives: Dental caries is one of the most prevalent oral diseases. Traditionally, the detection and diagnosis have been performed using conventional methods, such as visual inspection and radiographs. In this context, artificial intelligence-based tools have emerged as promising solutions to improve the efficiency and accuracy of dental caries detection. The objective of this scoping review was to map the scientific evidence available in the literature on the use of artificial intelligence tools for the detection of dental caries. Methods: This review was conducted following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A literature search was performed in the PubMed, Scopus, and Web of Science (WoS) databases using the search expression "artificial intelligence AND dental caries". Inclusion criteria were articles published in the last five years, in English or Spanish and available in full text. Results: The initial search yielded 617 records. After reviewing titles, 143 articles were selected, and upon removing duplicates, 93 unique entries remained. Following abstract evaluation, 40 articles were chosen for full-text review. Finally, 30 publications were included in this review. Conclusions: The evidence shows that artificial intelligence (AI) tools applied to dental caries detection have demonstrated significant improvements in diagnostic accuracy, with sensitivity and specificity values that are comparable to or even exceed those of traditional methods. Thus, the evidence indicates that the integration of AI is no longer a question of if, but how profoundly it will reshape the existing paradigms of dental diagnostics.

30 December 2019 in Journal of Oral Research
Verified
Journal Article
Open access
PDF file
VBViña del Mar Facultad de Odontología de la Universidad Andrés Bello
Viña del Mar Facultad de Odontología de la Universidad Andrés Bello
GBGermán Buchheister
Germán Buchheister
PRPatricio Melendez Rojas
Patricio Melendez Rojas
AHAlejandro Herrera
Alejandro Herrera
KLKevin Lever
Kevin Lever
The aim of this study was to evaluate the clinical utility of Cone Beam Computed Tomography (CBCT) in cases of medium and high endodontic complexity. The relevance of CBCT to define treatment was evaluated through the Wittenberg questionnaire and the variation in treatment plans after CBCT exam analysis. The sample (n=40) was chosen for convenience over a period of 4 months. It considered the current recommendations to request CBCT exams before performing root canal treatments. Data collection was carried out through a survey applied to the treating clinicians, after examining the information obtained by the CBCT system. Data were analyzed with the Stata version 13 software, and the Chi-square test was used for inferential analysis. A 95% confidence interval was considered. The most frequent dental groups corresponded to upper posterior and upper anterior teeth (47.5% and 30.0%); the cases were equally distributed according to complexity (50% and 50%). The main reason for requesting CBCT exams corresponded to complex anatomy and/or atypical canal system (37.5%). The use of CBCT increased confidence in the initial treatment chosen by clinicians in 50% of cases according to the Wittenberg questionnaire, and a 45% variation in treatment plans was observed. There was no statistical relationship between complexity and the variables studied. CBCT contributed greatly to the therapeutic management of cases regardless of their complexity. El objetivo de este estudio fue evaluar la utilidad clínica de la Tomografía Computarizada Cone Beam (CBCT) en casos de mediana y alta complejidad endodóntica. Se midió la relevancia del CBCT para definir conducta terapéutica a través del cuestionario de Wittenberg y en la variación de los planes de tratamientos posterior al análisis del examen. La muestra (n=40) se eligió por conveniencia en un período de 4 meses, considerando las recomendaciones actuales para solicitar este examen en Endodoncia. La recolección de datos se realizó por medio de una encuesta aplicada a los clínicos tratantes, después de examinar la información obtenida por el CBCT. Los datos se analizaron a través del software Stata version 13 y para el análisis inferencial se utilizó la prueba de chi cuadrado. Se utilizó un intervalo de confianza de 95%. Los grupos dentarios más frecuentes correspondieron a posteriores y anteriores superiores (47,5% y 30,0%), los casos se distribuyeron igualitariamente según complejidad (50% y 50%), el motivo principal para solicitar el CBCT, correspondió a anatomía del sistema de conductos de carácter complejo y/o atípico (37,5%), el CBCT aumentó la confianza en el tratamiento inicial escogido por los clínicos en el 50% de los casos según el cuestionario de Wittenberg y se obtuvo un 45% de variación en los planes de tratamientos. No se apreció relación estadística entre la complejidad con las variables estudiadas. El CBCT aportó en gran medida el manejo terapéutico de los casos independiente de su complejidad.

25 March 2026 in JMIR AI
Verified
Journal Article
Open access
Jaime Eduardo Jamett RojasJaime Eduardo Jamett Rojas
Jaime Eduardo Jamett Rojas
PRPatricio Melendez Rojas
Patricio Melendez Rojas
Ximena Collao-FerradaXimena Collao-Ferrada
Ximena Collao-Ferrada
Karina Cordero-TorresKarina Cordero-Torres
Karina Cordero-Torres
AVAlejandro Veloz
Alejandro Veloz
Background: Fuzzy logic has been progressively investigated as a viable alternative to traditional statistical and machine learning methods in health care modeling, especially in environments marked by uncertainty, nonlinearity, and missing information. Although its use in prediction, classification, and risk stratification is well established, its application to explicit causal inference remains limited, varied, and methodologically premature. Objective: This systematic review aimed to examine how fuzzy logic frameworks have been used to address causal questions in health care, focusing on their methodological characteristics, comparative performance, and degree of integration with formal causal inference approaches. Methods: A systematic search across 6 databases (PubMed, Web of Science, ScienceDirect, SpringerLink, Scopus, and IEEE Xplore) identified peer-reviewed studies published between 2014 and 2025 that applied fuzzy modeling in health care settings with explicit or implicit causal objectives. The review adhered to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines and used a modified PICO (population, intervention, comparator, and outcome) framework for study selection. Data were extracted on the health care domain, fuzzy method, comparator use, and causal framing. Risk of bias was evaluated using the Joanna Briggs Institute (JBI) checklist and the PROBAST+AI tool, according to study design. Results: A total of 37 studies met the inclusion criteria. The most frequently applied approaches were fuzzy inference systems, fuzzy cognitive maps, and neuro-fuzzy models, with applications spanning infectious diseases, cancer, cardiovascular health, mental health, and occupational health. Fourteen studies included comparator models; among these, 5 reported superior performance of fuzzy approaches, 3 showed comparable results, and 6 lacked sufficient detail for a robust comparison. Only 2 studies explicitly implemented formal causal inference frameworks, while most relied on predictive or associative modeling with implicit causal assumptions. Overall, the risk of bias was moderate to high. Conclusions: Fuzzy logic offers interpretability and flexibility well suited to complex health care problems, yet its application to explicit causal inference remains fragmented. Greater methodological transparency, systematic benchmarking, and integration with formal causal designs—such as counterfactual and target trial frameworks—are required to establish fuzzy logic as a robust paradigm for causal inference in health care.