Gender and sex bias in COVID-19 epidemiological data through the lens of causality.

The COVID-19 pandemic has spurred a large amount of experimental and observational studies reporting clear correlation between the risk of developing severe COVID-19 (or dying from it) and whether the individual is male or female. This paper is an attempt to explain the supposed male vulnerability to COVID-19 using a causal approach. We proceed by identifying a set of confounding and mediating factors, based on the review of epidemiological literature and analysis of sex-dis-aggregated data. Those factors are then taken into consideration to produce explainable and fair prediction and decision models from observational data. The paper outlines how non-causal models can motivate discriminatory policies such as biased allocation of the limited resources in intensive care units (ICUs). The objective is to anticipate and avoid disparate impact and discrimination, by considering causal knowledge and causal-based techniques to compliment the collection and analysis of observational big-data. The hope is to contribute to more careful use of health related information access systems for developing fair and robust predictive models.

Explaining Aha! moments in artificial agents through IKE-XAI: Implicit Knowledge Extraction for eXplainable AI.

During the learning process, a child develops a mental representation of the task he or she is learning. A Machine Learning algorithm develops also a latent representation of the task it learns. We investigate the development of the knowledge construction of an artificial agent through the analysis of its behavior, i.e., its sequences of moves while learning to perform the Tower of Hanoï (TOH) task. The TOH is a well-known task in experimental contexts to study the problem-solving processes and one of the fundamental processes of children's knowledge construction about their world. We position ourselves in the field of explainable reinforcement learning for developmental robotics, at the crossroads of cognitive modeling and explainable AI. Our main contribution proposes a 3-step methodology named Implicit Knowledge Extraction with eXplainable Artificial Intelligence (IKE-XAI) to extract the implicit knowledge, in form of an automaton, encoded by an artificial agent during its learning. We showcase this technique to solve and explain the TOH task when researchers have only access to moves that represent observational behavior as in human-machine interaction. Therefore, to extract the agent acquired knowledge at different stages of its training, our approach combines: first, a Q-learning agent that learns to perform the TOH task; second, a trained recurrent neural network that encodes an implicit representation of the TOH task; and third, an XAI process using a post-hoc implicit rule extraction algorithm to extract finite state automata. We propose using graph representations as visual and explicit explanations of the behavior of the Q-learning agent. Our experiments show that the IKE-XAI approach helps understanding the development of the Q-learning agent behavior by providing a global explanation of its knowledge evolution during learning. IKE-XAI also allows researchers to identify the agent's Aha! moment by determining from what moment the knowledge representation stabilizes and the agent no longer learns.

Developmentally Arrested Basket/Stellate Cells in Postnatal Human Brain as Potential Tumor Cells of Origin for Cerebellar Hemangioblastoma in von Hippel-Lindau Patients.

von Hippel-Lindau (VHL) disease is an autosomal dominant hereditary cancer disorder caused by a germline mutation in the VHL tumor suppressor gene. Loss of the wild-type allele results in VHL deficiency and the potential formation of cerebellar hemangioblastomas, which resemble embryonic hemangioblast proliferation and differentiation processes. Multiple, microscopic, VHL-deficient precursors, termed developmentally arrested structural elements (DASEs), consistently involve the cerebellar molecular layer in VHL patients, indicating the tumor site of origin. Unlike hemangioblastomas, however, cerebellar DASEs do not express brachyury, a mesodermal marker for hemangioblasts. In this study, neuronal progenitors occupying the molecular layer were investigated as tumor cells of origin. By immunohistochemistry, cerebellar DASEs and hemangioblastomas lacked immunoreactivity with antibody ZIC1 (Zic family member 1), a granule cell progenitor marker with concordance from oligonucleotide RNA expression array analyses. Rather, cerebellar DASEs and hemangioblastomas were immunoreactive with antibody PAX2 (paired box 2), a marker of basket/stellate cell progenitors. VHL cerebellar cortices also revealed PAX2-positive cells in Purkinje and molecular layers, resembling the histological and molecular development of basket/stellate cells in postnatal non-VHL mouse and human cerebella. These data suggest that VHL deficiency can result in the developmental arrest of basket/stellate cells in the human cerebellum and that these PAX2-positive, initiated cells await another insult or signal to form DASEs and eventually, tumors.

How We Would Treat Our Own Pulmonary Hypertension if We Needed to Undergo Cardiac Surgery.

Pulmonary hypertension (PH) is a disease that has many etiologies and is particularly prevalent in patients presenting for cardiac surgery, with which it is linked to poor outcomes. This manuscript is intended to provide a comprehensive review of the impact of PH on the perioperative management of patients who are undergoing cardiac surgery. The diagnosis of PH often involves a combination of noninvasive and invasive testing, whereas preoperative optimization frequently necessitates the use of specific medications that affect anesthetic management of these patients. The authors postulate that a thoughtful, multidisciplinary approach is required to deliver excellent perioperative care. Furthermore, they use an index case to illustrate the implications of managing a patient with pulmonary hypertension who presents for cardiac surgery with cardiopulmonary bypass.

Update on Perioperative Pediatric Pulmonary Hypertension Management.

Pediatric pulmonary hypertension is a disease that has many etiologies and can present anytime during childhood. Its newly revised hemodynamic definition follows that of adult pulmonary hypertension: a mean pulmonary artery pressure >20 mmHg. However, the pediatric definition stipulates that the elevated pressure must be present after the age of three months. The definition encompasses many different etiologies, and diagnosis often involves a combination of noninvasive and invasive testing. Treatment often is extrapolated from adult studies or based on expert opinion. Moreover, although general anesthesia may be required for pediatric patients with pulmonary hypertension, it poses certain risks. A thoughtful, multidisciplinary approach is needed to deliver excellent perioperative care.

Factors Associated With Pediatric Emergency Airway Management by the Difficult Airway Response Team.

Background The goal of this study was to determine if difficult airway risk factors were similar in children cared for by the difficult airway response team (DART) and those cared for by the rapid response team (RRT). Methods In this retrospective database analysis of prospectively collected data, we analyzed patient demographics, comorbidities, history of difficult intubation, and intubation event details, including time and place of the emergency and devices used to successfully secure the airway. Results Within the 110-patient cohort, median age (IQR) was higher among DART patients than among RRT patients [8.5 years (0.9-14.6) versus 0.3 years (0.04-3.6); P < 0.001]. The odds of DART management were higher for children ages 1-2 years (aOR, 43.3; 95% CI: 2.73-684.3) and >5 years (aOR, 13.1; 95% CI: 1.85-93.4) than for those less than one-year-old. DART patients were more likely to have craniofacial abnormalities (aOR, 51.6; 95% CI: 2.50-1065.1), airway swelling (aOR, 240.1; 95% CI: 13.6-4237.2), or trauma (all DART managed). Among patients intubated by the DART, children with a history of difficult airway were more likely to have musculoskeletal (P = 0.04) and craniofacial abnormalities (P < 0.001), whereas children without a known history of difficult airway were more likely to have airway swelling (P = 0.04). Conclusion Specific clinical risk factors predict the need for emergency airway management by the DART in the pediatric hospital setting. The coordinated use of a DART to respond to difficult airway emergencies may limit attempts at endotracheal tube placement and mitigate morbidity.

Interdisciplinary Research in Artificial Intelligence: Challenges and Opportunities.

The use of artificial intelligence (AI) in a variety of research fields is speeding up multiple digital revolutions, from shifting paradigms in healthcare, precision medicine and wearable sensing, to public services and education offered to the masses around the world, to future cities made optimally efficient by autonomous driving. When a revolution happens, the consequences are not obvious straight away, and to date, there is no uniformly adapted framework to guide AI research to ensure a sustainable societal transition. To answer this need, here we analyze three key challenges to interdisciplinary AI research, and deliver three broad conclusions: 1) future development of AI should not only impact other scientific domains but should also take inspiration and benefit from other fields of science, 2) AI research must be accompanied by decision explainability, dataset bias transparency as well as development of evaluation methodologies and creation of regulatory agencies to ensure responsibility, and 3) AI education should receive more attention, efforts and innovation from the educational and scientific communities. Our analysis is of interest not only to AI practitioners but also to other researchers and the general public as it offers ways to guide the emerging collaborations and interactions toward the most fruitful outcomes.

Development of a Multidisciplinary Pediatric Airway Program: An Institutional Experience.

Rapid response teams have become necessary components of patient care within the hospital community, including for airway management. Pediatric patients with an increased risk of having a difficult airway emergency can often be predicted on the basis of clinical scenarios and medical history. This predictability has led to the creation of airway consultation services designed to develop airway management plans for patients experiencing respiratory distress and who are at risk for having a difficult airway requiring advanced airway management. In addition, evolving technology has facilitated airway management outside of the operating suite. Training and continuing education on the use of these tools for airway management is imperative for clinicians responding to airway emergencies. We describe the comprehensive multidisciplinary, multicomponent Pediatric Difficult Airway Program we created that addresses each component identified above: the Pediatric Difficult Airway Response Team (PDART), the Pediatric Difficult Airway Consult Service, and the pediatric educational airway program. Approximately 41% of our PDART emergency calls occurred in the evening hours, requiring a specialized team ready to respond throughout the day and night. A multitude of devices were used during the calls, obviating the need for formal education and hands-on experience with these devices. Lastly, we observed that the majority of PDART calls occurred in patients who either were previously designated as having a difficult airway and/or had anatomic variations that suggest challenges during airway management. By instituting the Pediatric Difficult Airway Consult Service, we have decreased emergent Difficult Airway Response Team calls with the ultimate goal of first-attempt intubation success.

Open-Ended Learning: A Conceptual Framework Based on Representational Redescription.

Reinforcement learning (RL) aims at building a policy that maximizes a task-related reward within a given domain. When the domain is known, i.e., when its states, actions and reward are defined, Markov Decision Processes (MDPs) provide a convenient theoretical framework to formalize RL. But in an open-ended learning process, an agent or robot must solve an unbounded sequence of tasks that are not known in advance and the corresponding MDPs cannot be built at design time. This defines the main challenges of open-ended learning: how can the agent learn how to behave appropriately when the adequate states, actions and rewards representations are not given? In this paper, we propose a conceptual framework to address this question. We assume an agent endowed with low-level perception and action capabilities. This agent receives an external reward when it faces a task. It must discover the state and action representations that will let it cast the tasks as MDPs in order to solve them by RL. The relevance of the action or state representation is critical for the agent to learn efficiently. Considering that the agent starts with a low level, task-agnostic state and action spaces based on its low-level perception and action capabilities, we describe open-ended learning as the challenge of building the adequate representation of states and actions, i.e., of redescribing available representations. We suggest an iterative approach to this problem based on several successive Representational Redescription processes, and highlight the corresponding challenges in which intrinsic motivations play a key role.

State representation learning for control: An overview.

Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent. The representation is learned to capture the variation in the environment generated by the agent's actions; this kind of representation is particularly suitable for robotics and control scenarios. In particular, the low dimension characteristic of the representation helps to overcome the curse of dimensionality, provides easier interpretation and utilization by humans and can help improve performance and speed in policy learning algorithms such as reinforcement learning. This survey aims at covering the state-of-the-art on state representation learning in the most recent years. It reviews different SRL methods that involve interaction with the environment, their implementations and their applications in robotics control tasks (simulated or real). In particular, it highlights how generic learning objectives are differently exploited in the reviewed algorithms. Finally, it discusses evaluation methods to assess the representation learned and summarizes current and future lines of research.

Focused Review of Perioperative Care of Patients with Pulmonary Hypertension and Proposal of a Perioperative Pathway.

Morbidity and mortality risk increase considerably for patients with pulmonary hypertension (PH) undergoing non-cardiac surgery. Unfortunately, there are no comprehensive, evidence-based guidelines for perioperative evaluation and management of these patients. We present a brief review of the literature on perioperative outcomes for patients with PH and describe the implementation of a collaborative perioperative management program for these high-risk patients at a tertiary academic center.

Physical activity among children: objective measurements using Fitbit One® and ActiGraph.

BACKGROUND: Self-quantification of health parameters is becoming more popular; thus, the validity of the devices requires assessments. The aim of this study was to evaluate the validity of Fitbit One step counts (Fitbit Inc., San Francisco, CA, USA) against Actigraph wActisleep-BT step counts (ActiGraph, LLC, Pensacola, FL, USA) for measuring habitual physical activity among children. DESIGN: The study was implemented as a cross-sectional experimental design in which participants carried two waist-worn activity monitors for five consecutive days. METHODS: The participants were chosen with a purposive sampling from three fourth grade classes (9-10 year olds) in two comprehensive schools. Altogether, there were 34 participants in the study. From these, eight participants were excluded from the analysis due to erroneous data. Primary outcome measures for step counts were Fitbit One and Actigraph wActisleep-BT. The supporting outcome measures were based on activity diaries and initial information sheets. Classical Bland-Altman plots were used for reporting the results. RESULTS: The average per-participant daily difference between the step counts from the two devices was 1937. The range was [116, 5052]. Fitbit One gave higher step counts for all but the least active participant. According to a Bland-Altman plot, the hourly step counts had a relative large mean bias across participants (161 step counts). The differences were partially explained by activity intensity: higher intensity denoted higher differences, and light intensity denoted lower differences. CONCLUSIONS: Fitbit One step counts are comparable to Actigraph step counts in a sample of 9-10-year-old children engaged in habitual physical activity in sedentary and light physical activity intensities. However, in moderate-to-vigorous physical activity, Fitbit One gives higher step counts when compared to Actigraph.

Anesthetic Management of Pheochromocytoma Resection in Adults with Single Ventricle Physiology.

Survival rates for patients with palliated congenital heart disease are increasing, and an increasing number of adults with cyanotic congenital heart disease (CCHD) might require surgical resection of pheochromocytoma-paraganglioma (PHEO-PGL). A recent study supports the idea that patients with a history of CCHD and current or historical cyanosis might be at increased risk for developing PHEO-PGL. We review the anesthetic management of two adults with single-ventricle physiology following Fontan palliation presenting for PHEO-PGL resection and review prior published case reports. We found the use of epidural analgesia to be safe and effective in the operative and postoperative management of our patients.

Handling real-world context awareness, uncertainty and vagueness in real-time human activity tracking and recognition with a fuzzy ontology-based hybrid method.

Human activity recognition is a key task in ambient intelligence applications to achieve proper ambient assisted living. There has been remarkable progress in this domain, but some challenges still remain to obtain robust methods. Our goal in this work is to provide a system that allows the modeling and recognition of a set of complex activities in real life scenarios involving interaction with the environment. The proposed framework is a hybrid model that comprises two main modules: a low level sub-activity recognizer, based on data-driven methods, and a high-level activity recognizer, implemented with a fuzzy ontology to include the semantic interpretation of actions performed by users. The fuzzy ontology is fed by the sub-activities recognized by the low level data-driven component and provides fuzzy ontological reasoning to recognize both the activities and their influence in the environment with semantics. An additional benefit of the approach is the ability to handle vagueness and uncertainty in the knowledge-based module, which substantially outperforms the treatment of incomplete and/or imprecise data with respect to classic crisp ontologies. We validate these advantages with the public CAD-120 dataset (Cornell Activity Dataset), achieving an accuracy of 90.1% and 91.07% for low-level and Sensors 2014, 14 18132 high-level activities, respectively. This entails an improvement over fully data-driven or ontology-based approaches.