ROAD2H: Development and evaluation of an open-source explainable artificial intelligence approach for managing co-morbidity and clinical guidelines.

Introduction: Clinical decision support (CDS) systems (CDSSs) that integrate clinical guidelines need to reflect real-world co-morbidity. In patient-specific clinical contexts, transparent recommendations that allow for contraindications and other conflicts arising from co-morbidity are a requirement. In this work, we develop and evaluate a non-proprietary, standards-based approach to the deployment of computable guidelines with explainable argumentation, integrated with a commercial electronic health record (EHR) system in Serbia, a middle-income country in West Balkans. Methods: We used an ontological framework, the Transition-based Medical Recommendation (TMR) model, to represent, and reason about, guideline concepts, and chose the 2017 International global initiative for chronic obstructive lung disease (GOLD) guideline and a Serbian hospital as the deployment and evaluation site, respectively. To mitigate potential guideline conflicts, we used a TMR-based implementation of the Assumptions-Based Argumentation framework extended with preferences and Goals (ABA+G). Remote EHR integration of computable guidelines was via a microservice architecture based on HL7 FHIR and CDS Hooks. A prototype integration was developed to manage chronic obstructive pulmonary disease (COPD) with comorbid cardiovascular or chronic kidney diseases, and a mixed-methods evaluation was conducted with 20 simulated cases and five pulmonologists. Results: Pulmonologists agreed 97% of the time with the GOLD-based COPD symptom severity assessment assigned to each patient by the CDSS, and 98% of the time with one of the proposed COPD care plans. Comments were favourable on the principles of explainable argumentation; inclusion of additional co-morbidities was suggested in the future along with customisation of the level of explanation with expertise. Conclusion: An ontological model provided a flexible means of providing argumentation and explainable artificial intelligence for a long-term condition. Extension to other guidelines and multiple co-morbidities is needed to test the approach further.

Investigating Deep Sedation With Intravenous Ketamine in Spontaneous Respiration During Pulsed-Field Ablation.

OBJECTIVES: The authors report their experience of a protocol for deep sedation with ketamine in spontaneous respiration during the pulsed-field ablation (PFA) of atrial fibrillation (AF). DESIGN: Observational, prospective, nonrandomized fashion. SETTING: Single-center hospitalized patients. PARTICIPANTS: All consecutive patients undergoing PFA of AF. INTERVENTIONS: Patients undergoing deep sedation with intravenous ketamine. MEASUREMENTS AND MAIN RESULTS: The authors' sedation protocol involves the intravenous administration of fentanyl (1.5 µg/kg) and midazolam (2 mg) at low doses before local anesthesia with lidocaine. A ketamine adjunct (1 mg/kg) in 5-minute boluses was injected about 5 minutes before the first PFA delivery. The authors enrolled 117 patients (age = 59 ± 10 y, 74.4% males, body mass index = 27.6 ± 5 kg/m2, fluoroscopy time = 24 ± 14 minutes, skin-to-skin time = 80 ± 40 minutes and PFA LA dwell time = 24 ± 7 minutes). By the end of the procedure, pulmonary vein isolation had been achieved in all patients using PFA alone. The mean time under sedation was 54.9 ± 6 minutes, with 92 patients (79%) being sedated for <1 hour. A satisfactory Ramsay Sedation Scale level before ketamine administration was achieved in all patients, except one (80.3% of the patients with rank 3; 18.4% with rank 2). In all procedures, the satisfaction level was found acceptable by both the patient and the primary operator (satisfactory in 98.2% of cases). All patients achieved a Numeric Rating Scale for Pain ≤3 (none or mild). No major procedure or anesthesia-related complications were reported. CONCLUSION: The authors' standardized sedation protocol with the administration of drugs with rapid onset and pharmacologic offset at low doses was safe and effective, with an optimal degree of patient and operator satisfaction.

Achieving descriptive accuracy in explanations via argumentation: The case of probabilistic classifiers.

The pursuit of trust in and fairness of AI systems in order to enable human-centric goals has been gathering pace of late, often supported by the use of explanations for the outputs of these systems. Several properties of explanations have been highlighted as critical for achieving trustworthy and fair AI systems, but one that has thus far been overlooked is that of descriptive accuracy (DA), i.e., that the explanation contents are in correspondence with the internal working of the explained system. Indeed, the violation of this core property would lead to the paradoxical situation of systems producing explanations which are not suitably related to how the system actually works: clearly this may hinder user trust. Further, if explanations violate DA then they can be deceitful, resulting in an unfair behavior toward the users. Crucial as the DA property appears to be, it has been somehow overlooked in the XAI literature to date. To address this problem, we consider the questions of formalizing DA and of analyzing its satisfaction by explanation methods. We provide formal definitions of naive, structural and dialectical DA, using the family of probabilistic classifiers as the context for our analysis. We evaluate the satisfaction of our given notions of DA by several explanation methods, amounting to two popular feature-attribution methods from the literature, variants thereof and a novel form of explanation that we propose. We conduct experiments with a varied selection of concrete probabilistic classifiers and highlight the importance, with a user study, of our most demanding notion of dialectical DA, which our novel method satisfies by design and others may violate. We thus demonstrate how DA could be a critical component in achieving trustworthy and fair systems, in line with the principles of human-centric AI.

Density of states in gauge theories.

The density of states is calculated for the SU(2), SU(3), and a compact U(1) lattice gauge theories using a modified version of the Wang-Landau algorithm. We find that the density of states of the SU(2) gauge theory can be reliably calculated over a range of 120,000 orders of magnitude for lattice sizes as big as 20(4). We demonstrate the potential of the algorithm by reproducing the SU(2) average action, its specific heat, and the critical couplings of the weak first order transition in U(1).