With the rise of "big data", finding computationally efficient and privacy-preserving solutions for large-scale machine learning problems has gained paramount importance, especially in the case of ...medical data which is collected in huge volumes by modern healthcare systems. Since a large amount of data resides in different locations and owned by different entities, accessing sufficient data while keeping ethical, legal, economic, and technical challenges related to privacy in mind, precludes the medical data from being fully exploited by ML. Thus, to counter these challenges, we propose a novel blockchain-based Federated Learning architecture for healthcare consortia, which provides a solution to the current problems while highlighting the challenges and considerations that need to be addressed. The authors suggest a multi-modular system that can be broken down into three main modules - decentralized medical history module, differentially private institutional analytics module, and Federated Learning based patient prognosis. We conduct extensive experimentation using Logistic Regression and TabNet and receive an accuracy of 83.82 under IID settings with a client fraction of 10%. Further, we show that TabNet outperforms Logistic Regression under conditions of showing less data.
The use of emojis affords a visual modality to, often private, textual communication. The task of predicting emojis however provides a challenge for machine learning as emoji use tends to cluster ...into the frequently used and the rarely used emojis. Much of the machine learning research on emoji use has focused on high resource languages and has conceptualised the task of predicting emojis around traditional server-side machine learning approaches. However, traditional machine learning approaches for private communication can introduce privacy concerns, as these approaches require all data to be transmitted to a central storage. In this paper, we seek to address the dual concerns of emphasising high resource languages for emoji prediction and risking the privacy of people's data. We introduce a new dataset of \(118\)k tweets (augmented from \(25\)k unique tweets) for emoji prediction in Hindi, and propose a modification to the federated learning algorithm, CausalFedGSD, which aims to strike a balance between model performance and user privacy. We show that our approach obtains comparative scores with more complex centralised models while reducing the amount of data required to optimise the models and minimising risks to user privacy.
Brain tumors are the most common solid tumors and the leading cause of cancer-related death among children. Tumor segmentation is essential in surgical and treatment planning, and response assessment ...and monitoring. However, manual segmentation is time-consuming and has high inter-operator variability, underscoring the need for more efficient methods. We compared two deep learning-based 3D segmentation models, DeepMedic and nnU-Net, after training with pediatric-specific multi-institutional brain tumor data using based on multi-parametric MRI scans.Multi-parametric preoperative MRI scans of 339 pediatric patients (n=293 internal and n=46 external cohorts) with a variety of tumor subtypes, were preprocessed and manually segmented into four tumor subregions, i.e., enhancing tumor (ET), non-enhancing tumor (NET), cystic components (CC), and peritumoral edema (ED). After training, performance of the two models on internal and external test sets was evaluated using Dice scores, sensitivity, and Hausdorff distance with reference to ground truth manual segmentations. Dice score for nnU-Net internal test sets was (mean +/- SD (median)) 0.9+/-0.07 (0.94) for WT, 0.77+/-0.29 for ET, 0.66+/-0.32 for NET, 0.71+/-0.33 for CC, and 0.71+/-0.40 for ED, respectively. For DeepMedic the Dice scores were 0.82+/-0.16 for WT, 0.66+/-0.32 for ET, 0.48+/-0.27, for NET, 0.48+/-0.36 for CC, and 0.19+/-0.33 for ED, respectively. Dice scores were significantly higher for nnU-Net (p<=0.01). External validation of the trained nnU-Net model on the multi-institutional BraTS-PEDs 2023 dataset revealed high generalization capability in segmentation of whole tumor and tumor core with Dice scores of 0.87+/-0.13 (0.91) and 0.83+/-0.18 (0.89), respectively. Pediatric-specific data trained nnU-Net model is superior to DeepMedic for whole tumor and subregion segmentation of pediatric brain tumors.
Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to ...their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs challenge, focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors.
We propose a novel approach for visualizing reverse-engineered Unified Modeling Language (UML) diagrams (class, object, and sequence) to improve Object-Oriented Program (OOP) comprehension on a ...web-based programming environment, JaguarCode. It aims to help students better understand static structure and dynamic behavior of Java programs and object-oriented programming concepts. This paper presents an evaluation of JaguarCode, supporting those UML diagrams to investigate its effectiveness and user satisfaction. The results of the experimental study revealed having synchronized UML diagrams positively impacted students' understanding of program execution. It was also observed that students were satisfied with the aspects of the synchronized visualizations of UML diagrams with source code.
This paper proposes a novel method for estimation of strength of excitation (SoE) from speech signal. Using lowpass filtering to remove the effect of relatively high frequency vocal tract ...characteristics, we estimate epoch locations. Using these epoch locations we estimate SoE. The database used for evaluation purpose is CMU-ARCTIC database consisting of electroglottograph (EGG) signals. In addition, robustness of proposed method is evaluated against signal degraded conditions for additive white noise, babble noise, vehicular noise and high frequency noise at various SNR levels. Root mean square error (RMSE) is calculated for performance measurement with SoE derived from differenced electroglottograph (DEGG) as the ground truth. Finally, proposed algorithm is compared with SoE estimated by zero frequency resonator method. Experimental results show that proposed method gives good performance for clean speech with respect to existing technique whereas in noisy environment, proposed method gives comparable results.
Background and Aims: Intracranial arterial dissections commonly involve the vertebrobasilar system leading to subarachnoid hemorrhage (SAH) or cerebral infarction attributable to a dissecting ...aneurysm of the vessel or occlusion of the lumen depending on the depth of dissection. However, isolated posterior cerebral artery dissections (PCADs) are rare and sparsely reported in the literature. Methodology: A retrospective multicentric observational study was carried out after collecting data from 14 patients admitted with PCAD in three hospitals of Kolkata, Jaipur, and Patna within the period of July 2021 to June 2022. Results: The median age of the population was 48.5 years, and 64.28% were females. SAH was the most common presentation with dissecting aneurysms in all patients barring one, who presented with a left occipital infarct consequent to ipsilateral PCAD. Among the 14 patients, three patients denied endovascular intervention and were lost to follow-up; one patient with an occipital infarct and another patient with a dissecting left P3 aneurysm, which underwent spontaneous thrombosis, were managed conservatively. Among the nine patients scheduled for endovascular coiling, one patient succumbed before intervention and one patient succumbed to sepsis in the postoperative period. A complete recovery was noted in six patients, whereas residual neurodeficits were present in three patients. Among the six patients who had an uneventful recovery at the end of 3 months, five patients had an endovascular intervention. Conclusion: PCAD may present with large-scale neurodeficits and is associated with high morbidity and mortality, hence necessitating prompt management. Conservative management is preferable for consequent infarcts, whereas endovascular management is desirable in cases of dissecting aneurysms, which usually tend to have a favorable outcome if intervened early.
The Gram pod borer, Helicoverpa armigera (Noctuidae: Lepidoptera) is a cosmopolitan agricultural insect pest that prefers to feed on plant’s protein biomolecules. Out of different density-independent ...factors, surface air temperature majorly affects the incidence and damage of the H. armigera on the crops. Early prediction of H. armigera generations (voltinism) in future climate years perhaps prevent additional damage in various crops and improve the farmers preparedness. In this study, future climate data that is temperature obtained for eleven Agro-Climatic Zones (ACZs) of India under four Representative Concentration Pathways (RCPs) scenarios in different climate years (2010, 2030, 2050, 2070, 2090) using weather file generator MarkSim web application. The accumulation of Growing Degree-days (GDD) by H. armigera at eleven ACZs in each climate year under different RCP scenarios was estimated using temperature data. The mean surface air temperature is predicted to 0.51 °C, 1.03 °C, 1.57 °C and 2.1 °C in climate years 2030, 2050, 2070 and 2090, which escalated annual H. armigera Gen. to 12.88, 13.33, 13.79 and 14.23, respectively over the baseline climate year 2010. Likewise, under RCP 2.6, RCP 4.5, RCP 6.0 and RCP 8.5 scenarios H. armigera Gen. is predicted to 12.86, 13.29, 13.23 and 13.97 per annum with mean surface air temperatures 27.4 °C, 27.92 °C, 27.86 °C and 28.72 °C, respectively. The Eastern Coastal Plains and Hills Zone (ACZ 11) across climate years and RCPs has experienced a considerable increase in mean surface air temperature minimum (25.22 °C) and maximum (34.61 °C), which likely favor the GDD accumulation (6319.91) and the Genrations (14.97) in H. armigera. Therefore, the Eastern Coastal Plains and Hills Zone of India could be identified as H. armigera risk zone in near future. The present predictions in various ACZs of India may be significant in planning H. armigera management.
•MarkSim GCM weather data under four RCPs are considered for this study.•Predicted H. armigera Generations and Generation time in different climate years.•2–7% increase in mean surface air temperature was predicted in future climate years.•3–12% increase in H. armigera generations was predicted in future climate years.•The Eastern coastal plains and hills zone of India was most suitable for H. armigera.
Display omitted
•Subcutaneous (SC) injections can be associated with local pain and discomfort.•Multiple intertwined factors contribute to SC injection site pain/discomfort.•Device, delivery, and ...formulation factors influencing injection pain are reviewed.•Emotional/psychological aspects impacting pain perception are discussed.•The SC Consortium provides insights on knowledge gaps to improve patient experience.
Subcutaneous (SC) injections can be associated with local pain and discomfort that is subjective and may affect treatment adherence and overall patient experience. With innovations increasingly focused on finding ways to deliver higher doses and volumes (≥2 mL), there is a need to better understand the multiple intertwined factors that influence pain upon SC injection. As a priority for the SC Drug Development & Delivery Consortium, this manuscript provides a comprehensive review of known attributes from published literature that contribute to pain/discomfort upon SC injection from three perspectives: (1) device and delivery factors that cause physical pain, (2) formulation factors that trigger pain responses, and (3) human factors impacting pain perception. Leveraging the Consortium’s collective expertise, we provide an assessment of the comparative and interdependent factors likely to impact SC injection pain. In addition, we offer expert insights and future perspectives to fill identified gaps in knowledge to help advance the development of patient-centric and well tolerated high-dose/high-volume SC drug delivery solutions.