Critical Art and Media Practice

Analysing cough sounds is vital in pulmonary medicine. Recently, AI tools are being trained to analyse the acoustic signals of cough sounds so that more cases can be quickly tested, thereby reducing the patient load on primary healthcare systems. In this paper, we evaluate ”Swaasa”, our AI-based platform for rapid respiratory screening, highlighting its efficacy and ease of use. We applied our trained classifier to catch underlying pathologies from cough sound data collected from diverse sources. We then used a pattern classifier to identify specific respiratory conditions based on cough sound patterns. We tested the robustness of our methods by comparing our results with that of a pulmonary physician in 355 cases and show that Swaasa correctly predicted associated risk in 87.32% of those cases. Our platform has a sensitivity of 97.27% with a Positive Predictive Value (PPV) of 88.54%, giving us the potential to revolutionise disease screening, especially for large populations and in isolated rural areas. Our rapid and easy-to-use Software as a Service (SaaS) solution efficiently diagnoses and conserves resources, improves patient outcomes, and establishes a comprehensive and accessible healthcare framework.

Abstract The Advent of Artificial Intelligence (AI) has led to the use of auditory data for detecting various diseases, including COVID-19. SARS-CoV-2 infection has claimed more than six million lives to date and therefore, needs a robust screening technique to control the disease spread. In the present study we created and validated the Swaasa AI platform, which uses the signature cough sound and symptoms presented by patients to screen and prioritize COVID-19 patients. We collected cough data from 234 COVID-19 suspects to validate our Convolutional Neural Network (CNN) architecture and Feedforward Artificial Neural Network (FFANN) (tabular features) based algorithm. The final output from both models was combined to predict the likelihood of having the disease. During the clinical validation phase, our model showed a 75.54% accuracy rate in detecting the likely presence of COVID-19, with 95.45% sensitivity and 73.46% specificity. We conducted pilot testing on 183 presumptive COVID subjects, of which 58 were truly COVID-19 positive, resulting in a Positive Predictive Value of 70.73%. Due to the high cost and technical expertise required for currently available rapid screening methods, there is a need for a cost-effective and remote monitoring tool that can serve as a preliminary screening method for potential COVID-19 subjects. Therefore, Swaasa would be highly beneficial in detecting the disease and could have a significant impact in reducing its spread.

Introduction: Statin therapy might be associated with an increased risk of hemorrhagic stroke, which has been attributed to low LDL-cholesterol levels and antithrombotic effects. Hypothesis: Previous statin therapy is associated with surrogate markers of amyloid and hypertensive angiopathies in patients with cardioembolic stroke who need to start long-term oral anticoagulation (OA). Methods: A prospective multicenter study of patients included in the HERO study (Intracerebral Hemorrhage due to Oral Anticoagulants: Prediction of the Risk by Magnetic Resonance). Patients were naïve for OA and had an acute cardioembolic ischemic stroke (TIA or infarct). A MR examination was performed during admission to evaluate: 1) Microbleeds (-MB-, number, distribution, burden); 2) Leukoaraiosis (-LK- presence and degree); 3) Superficial siderosis (-SS-, presence). We collected data on the specific statin, the dose and the statin intensity (low, medium or high according to accepted classifications). We also recorded demographic data and traditional vascular risk factors. Results: We studied 470 patients (age 77.5±6.4 years, 43.7% were men). A total of 193 (41.1%) patients received prior treatment with any statin, of whom 43.5% received simvastatin and 41.3% atorvastatin. Statin intensity was low in 14.5%, medium in 61.1%, high in 16.5% and unknown in 10.8%. LK was detected in 82.5% and was severe in 19.8%. SS was detected in 20 (4.3%) patients. MBs were detected in 140 (29.8%) patients and the distribution was lobar in 55%, deep in 30% and both in 15%. Of the MB group 74 (53%) had 1 MB, 66 (47%) had >1 MB, and 11.4% had >5 MBs. The presence of MB, LK or SS was not related to the pre-treatment with statin. The statin intensity was not related to the presence of SS, the presence/degree of LK, and the presence/distribution/burden of MBs. MBs were detected with increased frequency in hypertensive patients (p=0.09). LK presence and degree were increased in patients with MB (p=0.012) and SS (p=0.041). Conclusion: In conclusion, prior treatment with statins is not associated with surrogate markers of bleeding-prone cerebral angiopathies in patients with cardioembolic stroke. Therefore previous statin treatment should not influence the decision to start long-term oral anticoagulation.

Introduction: The microvascular cerebral blood flow response (rCBF) to orthostatic stress has been shown to be altered in acute ischemic stroke (AIS) by diffuse correlation spectroscopy (DCS). However, its relevance to the outcome is unknown. Hypothesis: CBF response to head-of-the-bed (HOB) elevation within the first hours after AIS is related to outcome. Methods: Patients with a large anterior circulation stroke of less than 48h from the stroke onset were monitored with DCS to follow rCBF in the frontal lobes during a HOB elevation from supine to 30°. All patients were placed flat during the first 24 hours and later, mobilization was initiated depending on the clinical condition. We categorized measurements as early (<12h) or late (>12h) from stroke onset. NIHSS was recorded at baseline, during HOB, at 24h and 48h. The modified Rankin scale (mRS) score was utilized as the outcome measure (favorable when 0-2). Results: We studied 34 patients (age 78±13y, male 47%, median NIHSS 19 (14-21)) at 16±11 hours from stroke. Ipsilateral extracranial and/or intracranial occlusion was present in 61%. Frontal CBF decreased in both hemispheres after HOB (-5±14%). A paradoxical response (increase/no change) was observed in 18%. rCBF was not correlated to NIHSS and age. Unfavorable outcome was found in 85%. Only at early hours (<12h, n=16), rCBF to HOB elevation in the ipsilateral (not in contralateral) hemisphere (p=0.04, Figure 1) and NIHSS HOB (p=0.008) were associated with poor outcome. Conclusions: This result suggests that paradoxical CBF response to a mild HOB elevation in the early hours of stroke onset is associated with a poor outcome in patients with AIS. Optical continuous monitoring in the bedside may help to individualize management strategies in the early hours of AIS. Figure 1: rCBF due to HOB elevation versus mRS for the ipsi-lateral side in patients measured <12h after stroke.

Two nearly identical plasma jet-like systems with water misting were investigated for effective pathogen inactivation regimens on Escherichia coli in atmospheric conditions. Although the electrode construction is quite similar, we show that the concentration of active species generated at the exit of the discharge is quite different, and inactivation of bacteria by this treatment also varies. Inactivation and production rates of hydrogen peroxide, nitrate, and nitrite in liquid were higher when a single quartz barrier was utilized in the dielectric barrier discharge and one of the electrodes was open stainless steel.

Książka jest zbiorem tekstów prezentujących szeroki wachlarz zagadnień dotyczących historii średniowiecznej Polski i Europy. W czterech działach ‒ na wybranych, konkretnych przykładach ‒ podjęto tematykę dotyczącą monarchów i ich rodzin, społeczeństwa i jego poczynań, sztuki, architektury i artefaktów życia codziennego, jak również światopoglądu ludzi wieków średnich. Tak różnorodne problemy badawcze zaciekawią wszystkich, którzy interesują się historią średniowiecza, w tym heraldyką, genealogią, archeologią czy historią sztuki.

Abstract:We examined changes in a community of seedlings/saplings 10–150 cm tall associated with the presence of a widely invasive plant, Lantana camara and environmental covariates along 67 randomly located transects, in Mudumalai, India. We compared plant species assemblage and grass cover in L. camara-invaded and uninvaded plots in three habitats. Multivariate analyses revealed a significant association of all environmental covariates with plant species assemblage. Pairwise tests indicated that L. camara was significantly associated with changes in plant species assemblage and grass cover within the moist and dry deciduous forest, but not in the thorn forest. The relationship between L. camara and that of elephant browse plants varied with species. A linear regression analysis indicated that L. camara invasion was the only significant predictor of grass occupancy. Our results indicate that in addition to other factors, L. camara was associated with altering plant species assemblage, some elephant browse plants and grass cover in the moist and dry deciduous forest. It appears that L. camara can have a major effect on diversity within this reserve, but whether this effect is by L. camara driving the change or being associated with other habitat change requires further experimental evidence.

Abstract:Invasive weeds likeLantana camarahave a range of effects on animals such as elephant. These plants are not edible by the Asian elephant (Elephas maximus). They also compete for space with elephant food plants and take over large areas of elephant habitat. We tested whether the addition ofL. camarato a model consisting of measured environmental variables improved predictions of habitat use by elephant in Mudumalai Tiger Reserve, India. Elephant dung density was used to assess elephant habitat use from 62 line transects 1-km in length. Results indicated that habitat and impact of human settlements significantly influenced elephant habitat use at a landscape scale. However, we found no evidence for the hypothesis that the addition ofL. camarasignificantly predicted elephant habitat use at the landscape level. We then tested the association ofL. camaraon elephant habitat use in the dry deciduous forest (DDF) where there was a significant interaction between DDF andL. camara. In the DDF,L. camarasignificantly predicted elephant habitat use. We conclude that while no significant effects ofL.camarawere seen at the level of an entire reserve, at a finer scale and in specific habitats negative effects of this invasive plant on elephant habitat use were observed.

We evaluated the efficacy of the biorational insecticides azadirachtin and spinetoram, as well as the neonicotinoid thiametoxam, the organophosphates chlorpyrifos and malathion, and the pyrethroid λ-cyhalothrin against the pepper weevil, Anthonomus eugenii Cano, in a field of jalapeño pepper, Capsicum annuum L., in South-Central Chihuahua. Thiametoxam and chlorpyrifos had an impact on the reduction of this pest as many as five days after application. Also, we evaluated the insecticide rotation effect of Treatment 1 (spinetoram → chlorpyrifos → chlorpyrifos → thiametoxam) and Treatment 2 (thiametoxam → chlorpyrifos → chlorpyrifos → thiametoxam) where both treatments suppressed populations of this insect. Treatment 1 had the fewest fallen fruits.