Robust mortality prediction on a recirculating aquaculture system.

Aquaculture presents itself as one of the most rapidly developing means of sustainable production of animal protein to feed ever-growing populations. Recirculating aquaculture systems offer higher control and fewer inconveniences than traditional systems, making them an attractive option for fish production. Although the sector's digitalization is in its early stages, its application should increase its rentability while conserving the environment. This paper aims to promote the sector's evolution by assessing parameter importance in mortality with tree-based machine learning models, verifying the method's natural robustness and how it compares to a specially devised one, and at the same time evaluating the concept's relevance in predicting categorical mortality values. In particular, to better understand the aquaculture production process through a systematic data evaluation, an exploration based on real-time data acquisition is fully needed. Moreover, algorithm robustness is a key ingredient in this application since measurements are greatly affected by errors. This invalidates the application of traditional machine learning methods, where models are sensitive to production data variations and sensor noise. The study found the parameters that play relevant roles in the production phases, such as pH and nitrate concentration. While the obtained predictive metrics are still sub-optimal, further enhancements could be achieved through rigorous analysis of feature engineering, fine-tuning model hyperparameters, and exploring more advanced algorithms. Additionally, incorporating larger and more diverse datasets, refining data pre-processing techniques, and iteratively optimizing the model architecture may contribute to significant improvements in predictive performance. Despite that, the impact costs of using adjusted machine learning metrics are clear, as are the importance of data rounding in pre-processing and directions for improvement regarding data acquisition and transformation.

Understanding Differential Stress and Mental Health Reactions to COVID-19-Related Events.

The effects of the pandemic on mental health can be studied through different variables, such as the number of COVID-19 stressors, the stressor types, and the stress responses. Understanding the sources of mental strain is crucial for developing effective interventions. The present study analyzed the relationship between these COVID-19-related variables and positive and negative mental health. A cross-sectional study was conducted with 666 individuals from the Portuguese general population, mostly females (65.5%) between 16-93 years old. They completed self-report measures regarding the number of COVID-19 stressors, the stressor types, the stress responses (IES-R), and positive (MHC-SF) and negative mental health (BSI-18). The results demonstrated that a higher number of COVID-19-experienced stressors and more stress responses were related to worse mental health. Regarding stressor types, experiences not related to the COVID-19 infection (e.g., tension at home) presented the largest effects on mental health. The strongest predictor was the stress responses for negative (ß = 0.50) and positive mental health (ß = -0.17). The predictors explained more about negative mental health than positive. These findings support the idea that individual appraisals play a crucial role in mental health.

Test-re-test reliability and dynamics of the Fukuda-Unterberger stepping test.

Background: The Fukuda-stepping-test (FST), i.e., repetitive walking on the spot while blindfolded, has been proposed as a means to assess the integrity of the vestibular pathways. While its sensitivity to detect abnormalities in patients is limited, it may be useful in studying the physiology of the subjective-straight-ahead (SSA). Considering reported systematic shifts in SSA in humans, we hypothesize that such asymmetries arise from individual differences in the orientation/configuration of the macular organs and in central processing of vestibular input. We hypothesize that such asymmetries are stable over time in individual subjects. Alternatively, such asymmetries may arise from random noise in the sensory/motor systems involved, demonstrating low reproducibility over time. Materials and methods: Twenty-four subjects walked on the spot over 60 s while blindfolded (n = 6 trials per subject). Using an inertial measurement unit (IMU) placed at the chest, angular deviations were recorded and compared to manually-measured final positions. Both static (direction, magnitude) and dynamic (time-to-onset of deviation, pattern of deviations) parameters were retrieved from the yaw slopes. Results: Significant deviations were found in 15/24 participants for the manual measurements (leftwards = 8; rightwards = 7), whereas when using the IMU-sensor 13/24 participants showed significant shifts (leftwards = 9; rightwards = 4). There was a high correlation (0.98) between manually measured rotation angles (average absolute deviations = 58.0 deg ± 48.6 deg; intra-individual variability = 39 deg ± 24 deg) and sensor-based yaw slopes (1.00 deg/s ± 0.88 deg/s; 0.67 deg/s ± 0.41 deg/s). Relevant yaw deviation was detected 22.1 s ± 12.3 s (range = 5.6 s-59.2 s) after the onset of marching (no relevant yaw-deviation in 15/139 measurements), showing a mostly linear behavior over time. Conclusion: We observed significant inter-individual variability in task performance in the FST, reproducing findings from previous studies. With test-re-test reliability being moderate only, but at the same time observing a preference in the side of shifts in most trials and subjects, we conclude that likely both individually varying estimates of straight-ahead and random noise contribute to the pattern of angular deviations observed. Using an IMU-sensory based approach, additional dynamic parameters could be retrieved, emphasizing the value of such a quantitative approach over manual measurements. Such an approach may provide useful additional information to distinguish patients from healthy controls.

Heading Direction Is Significantly Biased by Preceding Whole-Body Roll-Orientation While Lying.

Background: After a prolonged static whole-body roll-tilt, a significant bias of the internal estimates of the direction of gravity has been observed when assessing the subjective visual vertical. Objective: We hypothesized that this post-tilt bias represents a more general phenomenon, broadly affecting spatial orientation and navigation. Specifically, we predicted that after the prolonged roll-tilt to either side perceived straight-ahead would also be biased. Methods: Twenty-five healthy participants were asked to rest in three different lying positions (supine, right-ear-down, and left-ear-down) for 5 min ("adaptation period") prior to walking straight-ahead blindfolded for 2 min. Walking was recorded with the inertial measurement unit sensors attached to different body locations and with sensor shoe insoles. The raw data was segmented with a gait-event detection method. The Heading direction was determined and linear mixed-effects models were used for statistical analyses. Results: A significant bias in heading into the direction of the previous roll-tilt position was observed in the post-adaptation trials. This bias was identified in both measurement systems and decreased again over the 2-min walking period. Conclusions: The bias observed further confirms the influence of prior knowledge on spatial orientation and navigation. Specifically, it underlines the broad impact of a shifting internal estimate of direction of gravity over a range of distinct paradigms, illustrating similar decay time constants. In the broader context, the observed bias in perceived straight-ahead emphasizes that getting up in the morning after a good night's sleep is a vulnerable period, with an increased risk of falls and fall-related injuries due to non-availability of optimally tuned internal estimates of the direction of gravity and the direction of straight-ahead.

Predictive value of D-dimer in the clinical outcome of severe COVID19 patients: Are we giving it too much credit?

BACKGROUND: COVID-19 is a new form of acute respiratory failure leading to multiorgan failure and ICU admission. Gathered evidence suggests that a 3-fold rise in D-dimer concentrations may be linked to poor prognosis and higher mortality. PURPOSE: To describe D-dimer admission profile in severe ICU COVID19 patients and its predictive role in outcomes and mortality. METHODS: Single-center retrospective cohort study. All adult patients admitted to ICU with COVID19 were divided into 3 groups: (1) Lower-values group (D-dimer levels < 3-fold normal range value [NRV] [500ng/mL]), Intermediate-values group (D-dimer ≥3-fold and <10-fold NRV) and Higher-value group (≥10-fold NRV). RESULTS: 118 patients (mean age 63 years, 73% males) were included (N = 73 Lower-values group, N = 31 Intermediate-values group; N = 11 Higher-values group). Mortality was not different between groups (p = 0.51). Kaplan-Meier survival curves revealed no differences (p = 0.52) between groups, nor it was verified even when gender, age, ICU length of stay, and SOFA score were considered as covariables. CONCLUSIONS: In severe COVID19 patients, the D-dimer profile does not retain a predictive value regarding patients' survivability and should not be used as a surrogate of disease severity.

Septic shock 3.0 criteria application in severe COVID-19 patients: An unattended sepsis population with high mortality risk.

BACKGROUND: Coronavirus disease 2019 (COVID-19) can be associated with life-threatening organ dysfunction due to septic shock, frequently requiring intensive care unit (ICU) admission, respiratory and vasopressor support. Therefore, clear clinical criteria are pivotal for early recognition of patients more likely to need prompt organ support. Although most patients with severe COVID-19 meet the Sepsis-3.0 criteria for septic shock, it has been increasingly recognized that hyperlactatemia is frequently absent, possibly leading to an underestimation of illness severity and mortality risk. AIM: To identify the proportion of severe COVID-19 patients with vasopressor support requirements, with and without hyperlactatemia, and describe their clinical outcomes and mortality. METHODS: We performed a single-center prospective cohort study. All adult patients admitted to the ICU with COVID-19 were included in the analysis and were further divided into three groups: Sepsis group, without both criteria; Vasoplegic Shock group, with persistent hypotension and vasopressor support without hyperlactatemia; and Septic Shock 3.0 group, with both criteria. COVID-19 was diagnosed using clinical and radiologic criteria with a severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) positive RT-PCR test. RESULTS: 118 patients (mean age 63 years, 87% males) were included in the analysis (n = 51 Sepsis group, n = 26 Vasoplegic Shock group, and n = 41 Septic Shock 3.0 group). SOFA score at ICU admission and ICU length of stay were different between the groups (P < 0.001). Mortality was significantly higher in the Vasoplegic Shock and Septic Shock 3.0 groups when compared with the Sepsis group (P < 0.001) without a significant difference between the former two groups (P = 0.713). The log rank tests of Kaplan-Meier survival curves were also different (P = 0.007). Ventilator-free days and vasopressor-free days were different between the Sepsis vs Vasoplegic Shock and Septic Shock 3.0 groups (both P < 0.001), and similar in the last two groups (P = 0.128 and P = 0.133, respectively). Logistic regression identified the maximum dose of vasopressor therapy used (AOR 1.046; 95%CI: 1.012-1.082, P = 0.008) and serum lactate level (AOR 1.542; 95%CI: 1.055-2.255, P = 0.02) as the major explanatory variables of mortality rates (R 2 0.79). CONCLUSION: In severe COVID-19 patients, the Sepsis 3.0 criteria of septic shock may exclude approximately one third of patients with a similarly high risk of a poor outcome and mortality rate, which should be equally addressed.

Sedation, analgesia, and delirium management in Portugal: a survey and point prevalence study. / Abordagem da sedação, da analgesia e do delirium em Portugal: inquérito nacional e estudo de prevalência.

OBJECTIVE: To establish current Portuguese critical care practices regarding analgesia, sedation, and delirium based on a comparison between the activities reported and daily clinical practice. METHODS: A national survey was conducted among physicians invited to report their practice toward analgesia, sedation, and delirium in intensive care units. A point prevalence study was performed to analyze daily practices. RESULTS: A total of 117 physicians answered the survey, and 192 patients were included in the point prevalence study. Survey and point prevalence studies reflect a high sedation assessment (92%; 88.5%), with the Richmond Agitated Sedation Scale being the most reported and used scale (41.7%; 58.2%) and propofol being the most reported and used medication (91.4%; 58.6%). Midazolam prescribing was reported by 68.4% of responders, but a point prevalence study revealed a use of 27.6%.Although 46.4% of responders reported oversedation, this was actually documented in 32% of the patients. The survey reports the daily assessment of pain (92%) using standardized scales (71%). The same was identified in the point prevalence study, with 91.1% of analgesia assessment mainly with the Behavioral Pain Scale. In the survey, opioids were reported as the first analgesic. In clinical practice, acetaminophen was the first option (34.6%), followed by opioids. Delirium assessment was reported by 70% of physicians but was performed in less than 10% of the patients. CONCLUSION: The results from the survey did not accurately reflect the common practices in Portuguese intensive care units, as reported in the point prevalence study. Efforts should be made specifically to avoid oversedation and to promote delirium assessment.

OBJETIVO: Determinar as práticas atuais de cuidados intensivos em Portugal quanto à analgesia, à sedação e ao delirium, com base em uma comparação entre as atividades relatadas e a prática clínica diária. MÉTODOS: Inquérito nacional em que os médicos foram convidados a relatar sua prática em relação à analgesia, à sedação e ao delirium em unidades de terapia intensiva. Para analisar a prática diária, realizou-se um estudo de prevalência pontual. RESULTADOS: Responderam ao inquérito 117 médicos, e 192 pacientes foram incluídos no estudo de prevalência pontual. O inquérito e o estudo de prevalência mostraram uma avaliação generalizada do nível de sedação (92%; 88,5%). A Escala de Agitação e Sedação de Richmond foi a mais reportada e utilizada (41,7%; 58,2%), e o propofol foi o medicamento mais reportado e utilizado (91,4%; 58,6%). A prescrição de midazolam foi relatada por 68,4% dos respondentes, mas o estudo de prevalência pontual revelou a sua utilização em 27,6%.Embora 46,4% dos respondentes tenham relatado excesso de sedação, na realidade foi documentado em 32% dos pacientes. O inquérito relatou avaliação diária de dor (92%) com uso de escalas padronizadas (71%). Identificou-se resultado semelhante no estudo de prevalência pontual, com 91,1% de avaliação da analgesia feita principalmente com a Escala Comportamental de Dor. No inquérito, os opioides foram relatados como analgésicos de primeira linha. Na prática clínica, o paracetamol foi a primeira opção (34,6%), seguido de opioides. A avaliação do delirium foi relatada por 70% dos médicos, embora tenha sido realizada em menos de 10% dos pacientes. CONCLUSÃO: Os resultados do inquérito não refletiram com precisão as práticas habituais nas unidades de terapia intensiva portuguesas, tal como relatado no estudo de prevalência pontual. Devem ser feitos esforços principalmente para evitar o excesso de sedação e promover a avaliação do delirium.

Abordagem da sedação, da analgesia e do delirium em Portugal: inquérito nacional e estudo de prevalência / Sedation, analgesia, and delirium management in Portugal: a survey and point prevalence study

RESUMO Objetivo: Determinar as práticas atuais de cuidados intensivos em Portugal quanto à analgesia, à sedação e ao delirium, com base em uma comparação entre as atividades relatadas e a prática clínica diária. Métodos: Inquérito nacional em que os médicos foram convidados a relatar sua prática em relação à analgesia, à sedação e ao delirium em unidades de terapia intensiva. Para analisar a prática diária, realizou-se um estudo de prevalência pontual. Resultados: Responderam ao inquérito 117 médicos, e 192 pacientes foram incluídos no estudo de prevalência pontual. O inquérito e o estudo de prevalência mostraram uma avaliação generalizada do nível de sedação (92%; 88,5%). A Escala de Agitação e Sedação de Richmond foi a mais reportada e utilizada (41,7%; 58,2%), e o propofol foi o medicamento mais reportado e utilizado (91,4%; 58,6%). A prescrição de midazolam foi relatada por 68,4% dos respondentes, mas o estudo de prevalência pontual revelou a sua utilização em 27,6%. Embora 46,4% dos respondentes tenham relatado excesso de sedação, na realidade foi documentado em 32% dos pacientes. O inquérito relatou avaliação diária de dor (92%) com uso de escalas padronizadas (71%). Identificou-se resultado semelhante no estudo de prevalência pontual, com 91,1% de avaliação da analgesia feita principalmente com a Escala Comportamental de Dor. No inquérito, os opioides foram relatados como analgésicos de primeira linha. Na prática clínica, o paracetamol foi a primeira opção (34,6%), seguido de opioides. A avaliação do delirium foi relatada por 70% dos médicos, embora tenha sido realizada em menos de 10% dos pacientes. Conclusão: Os resultados do inquérito não refletiram com precisão as práticas habituais nas unidades de terapia intensiva portuguesas, tal como relatado no estudo de prevalência pontual. Devem ser feitos esforços principalmente para evitar o excesso de sedação e promover a avaliação do delirium.

ABSTRACT Objective: To establish current Portuguese critical care practices regarding analgesia, sedation, and delirium based on a comparison between the activities reported and daily clinical practice. Methods: A national survey was conducted among physicians invited to report their practice toward analgesia, sedation, and delirium in intensive care units. A point prevalence study was performed to analyze daily practices. Results: A total of 117 physicians answered the survey, and 192 patients were included in the point prevalence study. Survey and point prevalence studies reflect a high sedation assessment (92%; 88.5%), with the Richmond Agitated Sedation Scale being the most reported and used scale (41.7%; 58.2%) and propofol being the most reported and used medication (91.4%; 58.6%). Midazolam prescribing was reported by 68.4% of responders, but a point prevalence study revealed a use of 27.6%. Although 46.4% of responders reported oversedation, this was actually documented in 32% of the patients. The survey reports the daily assessment of pain (92%) using standardized scales (71%). The same was identified in the point prevalence study, with 91.1% of analgesia assessment mainly with the Behavioral Pain Scale. In the survey, opioids were reported as the first analgesic. In clinical practice, acetaminophen was the first option (34.6%), followed by opioids. Delirium assessment was reported by 70% of physicians but was performed in less than 10% of the patients. Conclusion: The results from the survey did not accurately reflect the common practices in Portuguese intensive care units, as reported in the point prevalence study. Efforts should be made specifically to avoid oversedation and to promote delirium assessment.

Evolution of Collective Behaviors for a Real Swarm of Aquatic Surface Robots.

Swarm robotics is a promising approach for the coordination of large numbers of robots. While previous studies have shown that evolutionary robotics techniques can be applied to obtain robust and efficient self-organized behaviors for robot swarms, most studies have been conducted in simulation, and the few that have been conducted on real robots have been confined to laboratory environments. In this paper, we demonstrate for the first time a swarm robotics system with evolved control successfully operating in a real and uncontrolled environment. We evolve neural network-based controllers in simulation for canonical swarm robotics tasks, namely homing, dispersion, clustering, and monitoring. We then assess the performance of the controllers on a real swarm of up to ten aquatic surface robots. Our results show that the evolved controllers transfer successfully to real robots and achieve a performance similar to the performance obtained in simulation. We validate that the evolved controllers display key properties of swarm intelligence-based control, namely scalability, flexibility, and robustness on the real swarm. We conclude with a proof-of-concept experiment in which the swarm performs a complete environmental monitoring task by combining multiple evolved controllers.