Artificial intelligence in medicine
-
An electroencephalogram-based (EEG-based) brain-computer-interface (BCI) provides a new communication channel between the human brain and a computer. Amongst the various available techniques, artificial neural networks (ANNs) are well established in BCI research and have numerous successful applications. However, one of the drawbacks of conventional ANNs is the lack of an explicit input optimization mechanism. In addition, results of ANN learning are usually not easily interpretable. In this paper, we have applied an ANN-based method, the genetic neural mathematic method (GNMM), to two EEG channel selection and classification problems, aiming to address the issues above. ⋯ We demonstrate that GNMM is able to perform effective channel selections/reductions, which not only reduces the difficulty of data collection, but also greatly improves the generalization of the classifier. An important step that affects the effectiveness of GNMM is the pre-processing method. In this paper, we also highlight the importance of choosing an appropriate time window position.
-
Using an automatic data-driven approach, this paper develops a prediction model that achieves more balanced performance (in terms of sensitivity and specificity) than the Canadian Assessment of Tomography for Childhood Head Injury (CATCH) rule, when predicting the need for computed tomography (CT) imaging of children after a minor head injury. ⋯ Automatically derived prediction models cannot replace a physician's acumen. However, they help establish reference performance indicators for the purpose of developing clinical decision rules so the trade-off between prediction sensitivity and specificity is better understood.
-
The most serious medication errors occur during intravenous administration. The potential consequences are more serious the more critical and younger the patient. Smart pumps can help to prevent infusion-related programming errors, thanks to associated dose-limiting software known as "drug library". Drug libraries alert the user if pre-determined high dosage limits are exceeded or if entry is below pre-determined low dosage limits. ⋯ Drug libraries are specifically designed for a particular hospital unit, and may condition the success in implementing this technology. Implementation of smart pumps proved effective in intercepting infusion-related programming errors after nine months of implementation in a PICU.
-
The problem of designing and managing teams of workers that can collaborate working together towards common goals is a challenging one. Incomplete or ambiguous specification of responsibilities and accountabilities, lack of continuity in teams working in shifts, inefficient organization of teams due to lack of information about workers' competences and lack of clarity to determine if the work is delegated or assigned are examples of important problems related to collaborative work in healthcare teams. Here we address these problems by specifying goal-based patterns for abstracting the delegation and assignment of services. The proposed patterns should provide generic and reusable solutions and be flexible enough to be customizable at run time to the particular context of execution. Most importantly the patterns should support a mechanism for detecting abnormal events (exceptions) and for transferring responsibility and accountability for recovering from exceptions to the appropriate actor. ⋯ The proposed patterns are generic and abstract enough to capture the normal and abnormal scenarios of assignment and delegation of tasks in collaborative work in health care teams.
-
To develop a mathematical model for multi-category patient scheduling decisions in computed tomography (CT), and to investigate associated tradeoffs from economic and operational perspectives. ⋯ The performance of the optimal policy is competitive with the operational and economic metrics considered in this paper. Such a policy can be implemented relatively easily and could be tested in practice in the future. The priority-based heuristics are next-best to the optimal policy and are much easier to implement.