W. Faber

Wouter Faber, Renske Eline Bootsma, Tom Huibers et al.

Generative Artificial Intelligence (AI) can be used to automatically generate medical reports based on transcripts of medical consultations. The aim is to reduce the administrative burden that healthcare professionals face. The accuracy of the generated reports needs to be established to ensure their correctness and usefulness. There are several metrics for measuring the accuracy of AI generated reports, but little work has been done towards the application of these metrics in medical reporting. A comparative experimentation of 10 accuracy metrics has been performed on AI generated medical reports against their corresponding General Practitioner's (GP) medical reports concerning Otitis consultations. The number of missing, incorrect, and additional statements of the generated reports have been correlated with the metric scores. In addition, we introduce and define a Composite Accuracy Score which produces a single score for comparing the metrics within the field of automated medical reporting. Findings show that based on the correlation study and the Composite Accuracy Score, the ROUGE-L and Word Mover's Distance metrics are the preferred metrics, which is not in line with previous work. These findings help determine the accuracy of an AI generated medical report, which aids the development of systems that generate medical reports for GPs to reduce the administrative burden.

W. Faber, S. Chakravorty, Islam I. Hussein

In multi-object tracking one may encounter situations were at any time step the number of possible hypotheses is too large to generate exhaustively. These situations generally occur when there are multiple ambiguous measurement returns that can be associated to many objects. This paper contains a newly developed approach that keeps the aforementioned situations computationally tractable. Utilizing a hypothesis level derivation of the Finite Set Statistics (FISST) Bayesian recursions for multi-object tracking we are able to propose a randomized method called randomized FISST (R-FISST). Like our previous methods, this approach utilizes Markov Chain Monte Carlo (MCMC) methods to sample highly probable hypotheses, however, the newly developed (R-FISST) can account for hypotheses containing multiple births and death within the MCMC sampling. This alleviates the burden of having to exhaustively enumerate all birth and death hypotheses and makes the method more equipped to handle spawn scenarios. We test our method on Space Situational Awareness (SSA) scenarios with spawn events.