OBJECTIVES: This study develops and validates the confidence-linked and uncertainty-based staged (CLUES) framework by integrating large language models (LLMs) with uncertainty quantification to assist manual chart review while ensuring reliability through a selective human review. MATERIALS AND METHODS: The CLUES framework assesses stroke-related hospitalizations using imaging reports for 1739 patients across 24 Korean hospitals (2011-2022). Uncertainty was quantified via entropy from LLM-derived confidence values. Our framework operated in 3 stages: (1) zero-shot prompting with ensemble averaging, where high-uncertainty cases advanced to stage 2, (2) few-shot prompting using retrieved low-uncertainty cases, with remaining high-uncertainty cases proceeding to stage 3, and (3) manual chart review for final uncertain cases. Performance was evaluated against physician-labeled data using F1-score and Cohen's Kappa. RESULTS: Among 1072 test cases, stage 1 classified 507 cases as low uncertainty, while 565 were high uncertainty. Stage 2 reclassified 280 cases as low uncertainty, leaving 285 for manual review. Low-uncertainty cases consistently outperformed high-uncertainty cases in both stages (weighted F1-scores: 0.94 vs 0.57 in stage 1 and 0.82 vs 0.58 in stage 2). The overall framework performance showed a progressive improvement in F1-scores from 0.840 (stage 1) to 0.878 (stage 2) to 0.955 (stage 3). DISCUSSION: The CLUES framework reduced manual review burden by 75% while maintaining high accuracy. By integrating uncertainty quantification with selective human oversight, it provides an efficient and reliable approach to phenotype validation. CONCLUSION: This framework demonstrates the effective integration of LLMs into clinical workflows while ensuring human oversight, enhancing both accuracy and efficiency.

Probabilistic inference is fundamentally hard, yet many tasks require optimization on top of inference, which is even harder. We present a new optimization-via-compilation strategy to scalably solve a certain class of such problems. In particular, we introduce a new intermediate representation (IR), binary decision diagrams weighted by a novel notion of branch-and-bound semiring, that enables a scalable branch-and-bound based optimization procedure. This IR automatically factorizes problems through program structure and prunes suboptimal values via a straightforward branch-and-bound style algorithm to find optima. Additionally, the IR is naturally amenable to staged compilation, allowing the programmer to query for optima mid-compilation to inform further executions of the program. We showcase the effectiveness and flexibility of the IR by implementing two performant languages that both compile to it: dappl and pineappl . dappl is a functional language that solves maximum expected utility problems with first-class support for rewards, decision making, and conditioning. pineappl is an imperative language that performs exact probabilistic inference with support for nested marginal maximum a posteriori (MMAP) optimization via staging.

As technical computing software, such as MATLAB and SciPy, has gained popularity, ecosystems of interdependent software solutions and communities have formed around these technologies. The development and maintenance of these technical computing ecosystems requires expertise in both software engineering and the underlying technical domain. The inherently interdisciplinary nature of these ecosystems presents unique challenges and opportunities that shape software development practices.

Today’s growth in the volume of wireless devices coupled with the demand for data-intensive use cases has motivated the deployment of millimeter-wave (mmWave) small-cell networks. Although it is true that mmWave networks can carry a large volume of traffic, highly intermittent connectivity and the challenges related to installing many small-cell base stations (BSs) in urban geometry have impeded its progression into practical networks. To cope with these challenges, we present, in this paper, an approach to the mmWave BS deployment (site planning) problem, based on the minimum-deployment-cost criterion that is subject to user equipment (UE) outage constraints. Unlike the prior works, the proposed model captures the randomness of link blockage and signal-to-interference-plus-noise-ratio (SINR) statistics in mmWave networks. We formulate the minimum-cost deployment problem as large-scale integer nonlinear programming (INP). To deal with the coupled and combinatorial of the problem, the large-scale INP has approached to devise a suboptimal but efficient algorithm by decomposing it into two subproblems: (i) cell coverage optimization and (ii) minimum subset selection. We provide the solutions to each subproblem as well as theoretical justifications of them. Simulation results that illustrate UE outage guarantees of the proposed BS deployment method are presented. The results reveal that the proposed method uniquely distributes the macro-diversity orders that are distinct from other benchmarks.