David Andrew

Over recent years, machine learning and artificial intelligence have become critical components of many cancer detection tests, in particular multi-omic tests such as spectroscopic liquid biopsies. The complexity and multi-variate nature of spectral datasets makes machine learning invaluable in uncovering patterns that enable robust differentiation of cancer signals. However, introducing any AI-enabled medical device into clinical practice is challenging due to the regulatory requirements needed to progress from fundamental research to clinical and patient use. This review explores some of the fundamental concerns in bringing spectroscopic liquid biopsies to the clinic, including the need for explainable artificial intelligence and diverse validation sets. Addressing these issues is essential to accelerate clinical uptake with the ultimate goal of improving patient survival and quality of life.

Faculty of Arts, Business, & Social Sciences, University of Surrey, Guildford GU2 7XH, UK Faculty of Health & Medical Sciences, University of Surrey, Guildford GU2 7XH, UK

Australians are living through one of the strangest economic moments in memory: the numbers say “boom”, but people feel anything but confident.

This study compares implicit stochastic optimization (ISO) and explicit stochastic optimization (ESO) for deriving operational rules for conjunctive use of surface water and groundwater, and proposes an improved ISO formulation that accounts for capturing interdependence among sequential decisions. In the present formulation, previously determined decision variables are introduced as additional inputs to the rule model. The analysis is carried out using the example of the conjunctive use system of the Qazvin Plain, Iran. ESO-based operational rules are derived using stochastic dynamic programming (SDP), whereas ISO-based rules are extracted from the analysis of optimization results using the M5 decision tree algorithm. The derived rules are evaluated in a simulation model driven by the historical inflow record and 14 synthetic inflow series. Incorporating previously determined decisions substantially improves the accuracy of ISO-based rules, increasing the correlation coefficient by up to 40.5% relative to the conventional ISO formulation. Nevertheless, ESO-based rules provide better overall system performance across all inflow scenarios, producing lower agricultural water deficits and better groundwater control. Under ESO-based operation, groundwater storage remains close to the prescribed bounds (0–80 ± 10 MCM), whereas ISO-based rules produce substantial deviations. These results show that the proposed ISO modification improves rule accuracy, but ESO remains the more reliable framework for conjunctive operation when groundwater sustainability is a primary objective.

ADAP--a mixed-signal array processor with early vision applications