Conference Agenda

Surgical backlog in low- and middle-income countries (LMICs) is exacerbated by fragmented information systems and weak process governance. Existing process mining solutions often assume data environments and governance maturity absent in LMIC public hospitals. We propose and evaluate a governance-integrated process mining framework architected for resource-constrained, digitally fragmented settings. The framework translates five inputs—clinical data, process definitions, infrastructure, controls, and policies—into actionable outputs through a four-layer architecture. A proof-of-concept in a Peruvian tertiary public hospital (1,234 surgical episodes, 2023–2024) revealed a critical 15-hour bottleneck between admission and preoperative preparation (IQR: 11–19), accounting for 62.5% of planned preoperative stay, and 39 distinct process variants indicating extreme pathway fragmentation. Conformance against the institutional protocol was 75% (fitness=0.75). Expert validation (n=15) rated integration of information between areas (4.81/5) and active participation of medical staff (4.75/5) as critical factors. However, a significant gap emerged between high perceived usefulness (4.50/5) and willingness to use (4.63/5) versus lower implementation feasibility (4.00/5) (p=0.010, Cohen’s d=0.77). Reliability analysis yielded Cronbach’s alpha of 0.89. This study provides a transferable, empirically grounded framework that moves beyond aggregate indicators to diagnose surgical inefficiencies, offering a roadmap aligned with national backlog reduction policies in LMICs.

Un patrón de diseño permite estructurar y optimizar soluciones en entornos tecnológicos complejos, como lo es caso de la tecnología de blockchain, facilitando la reutilización de conocimientos y experiencias previas. Este artículo presenta un análisis orientado a la incorporación de patrones de diseño en aplicaciones soportadas sobre en Hyperledger Fabric, una blockchain de tipo permisionada. Mediante una revisión de la literatura y la clasificación de estudios previos, se identificaron patrones de diseño aplicables a contratos inteligentes, dichos patrones fueron implementados en una red de prueba para evaluar su comportamiento y efectividad, considerando métricas de rendimiento, mejoras de seguridad y de escalabilidad. Los resultados obtenidos demuestran que la aplicación de estos patrones no solo mejora la eficiencia en la ejecución de transacciones, sino que también facilitan el proceso de desarrollo y mantenimiento del software.

Deep technology entrepreneurship education, requiring independent judgment under uncertainty, is either advanced or undermined by AI mentoring, depending on system architecture. Current AI systems have three flaws: unvalidated feedback, lack of session memory, and relying on pre-training data rather than entrepreneurial precedents. This article details the first Design Science Research (DSR) cycle of ProjectIA, designed to address these limitations. ProjectIA uses two complementary artifacts: Eight structured validation frameworks operationalizing the Technology Startup Roadmap (TRL 1-5), specifying evidence and experiment protocols; and an AI platform constrained to Socratic interrogation and evidence-grounded feedback against these frameworks. Evaluation with 13 professionals over 16 weeks tested three hypotheses: H1 (frameworks surface missed risks), H2 (Socratic AI complements human mentoring), and H3 (LLM fidelity failures are the main trust barrier). H1 and H2 were confirmed, with frameworks achieving unanimous utility (5.0/5.0) and the AI platform scoring high on complementarity (4.69/5.0). H3 was confirmed and refined: hallucination control (3.23/5.0) and session memory (3.31/5.0) scored lowest. Their consequences were expertise-asymmetric, recoverable for experts but potentially corrupting for novices. Whether the system develops or substitutes for independent judgment is an open question; this cycle measured perceived utility and fidelity, not unassisted performance post-intervention. Unassisted performance measurement is the primary design requirement for Cycle 2.

Classifying citizen service requests in public tax offices is harder than it looks. Citizens describe their problems in their own words, select the wrong service category more often than not, and force staff to reclassify every submission before routing can begin. This paper examines whether that reclassification burden can be automated using NLP and supervised machine learning, drawing on 4,021 real requests submitted to Chile's Taxpayer Ombudsman Office (DEDECON) in Spanish free text. The feature engineering strategy combines TF-IDF text representation with two domain-grounded signals: a proxy for the user's knowledge level (scored 0 to 2) and binary indicators of class-specific keyword presence. Six classifiers were evaluated under identical conditions: Logistic Regression, Support Vector Machines, Naive Bayes, Decision Trees, Random Forest, and K-Nearest Neighbors. Random Forest reached 92.18% accuracy and an F1-macro score of 0.921, competitive with transformer-based approaches at a fraction of the computational cost. The main source of residual error is semantic overlap between adjacent service categories, a problem that text features alone are unlikely to resolve. Beyond DEDECON, the pipeline is directly applicable to other Spanish-language public service institutions facing the same intake classification problem.

Musculoskeletal disorders (MSDs) represent a critical occupational health challenge for maintenance personnel in open-pit mining, where awkward postures, heavy load handling, and repetitive tasks substantially increase the risk of injury. This study develops and validates an innovative automated ergonomic assessment system, based on artificial intelligence (AI), for the real-time identification of postural risk. The methodology integrates on-site image capture, processing with the MediaPipe library for joint angle extraction, and classification using a convolutional neural network (CNN). The model, trained on a dataset of 2,450 annotated images of critical tasks (tire changing, nut extraction, etc.), demonstrated robust performance, achieving an accuracy of 89.4% when validated against expert ergonomic assessments using the REBA method. The results show that the system overcomes the limitations of traditional observational methods by providing an objective, quantitative, and scalable evaluation. It is concluded that the integration of this AI system enables not only proactive monitoring and the prioritization of specific ergonomic interventions but also establishes the foundation for improving health outcomes and productivity in this high-risk industrial environment.