Decentralized digital twins of complex dynamical systems.

In this article, we introduce a decentralized digital twin (DDT) modeling framework and its potential applications in computational science and engineering. The DDT methodology is based on the idea of federated learning, a subfield of machine learning that promotes knowledge exchange without disclosing actual data. Clients can learn an aggregated model cooperatively using this method while maintaining complete client-specific training data.

Effect of Peritumoral Infiltration of Local Anesthetic Before Surgery on Survival in Early Breast Cancer.

Purpose: Preventing metastases by using perioperative interventions has not been adequately explored. Local anesthesia blocks voltage-gated sodium channels and thereby prevents activation of prometastatic pathways. We conducted an open-label, multicenter randomized trial to test the impact of presurgical, peritumoral infiltration of local anesthesia on disease-free survival (DFS).

Kolhapur Cancer Centre … Aiming for Perfection at Grass Root Level, Spreading Care to Those in Need!

There is a big need for more comprehensive cancer centres in tier 3 cities in India. These small cities are the most accessible to the majority of the rural population of India. Most of these patients are economically compromised and thus cannot manage treatment options in metropolitan cities.

Variational multiscale reinforcement learning for discovering reduced order closure models of nonlinear spatiotemporal transport systems.

A central challenge in the computational modeling and simulation of a multitude of science applications is to achieve robust and accurate closures for their coarse-grained representations due to underlying highly nonlinear multiscale interactions. These closure models are common in many nonlinear spatiotemporal systems to account for losses due to reduced order representations, including many transport phenomena in fluids. Previous data-driven closure modeling efforts have mostly focused on supervised learning approaches using high fidelity simulation data.

Physics guided neural networks for modelling of non-linear dynamics.

The success of the current wave of artificial intelligence can be partly attributed to deep neural networks, which have proven to be very effective in learning complex patterns from large datasets with minimal human intervention. However, it is difficult to train these models on complex dynamical systems from data alone due to their low data efficiency and sensitivity to hyperparameters and initialisation. This work demonstrates that injection of partially known information at an intermediate layer in a DNN can improve model accuracy, reduce model uncertainty, and yield improved convergence during the training.

Parameter Identification of Cardiovascular System Model Used for Left Ventricular Assist Device Algorithms.

Advancement of implanted left ventricular assist device (LVAD) technology includes modern sensing and control methods to enable online diagnostics and monitoring of patients using on-board sensors. These methods often rely on a cardiovascular system (CVS) model, the parameters of which must be identified for the specific patient. Some of these, such as the systemic vascular resistance (SVR), can be estimated online while others must be identified separately.

Role of ado-trastuzumab emtansine (T-DM1) in HER2 positive salivary gland tumour with brain metastasis.

Malignant neoplasms of salivary gland neoplasms are rare and often involve the parotid gland. The primary treatment of these malignancies is surgery with or without adjuvant therapy. Chemotherapy or systemic therapy is indicated in recurrent or metastatic disease where surgery or radiotherapy is not possible.

Multi-fidelity information fusion with concatenated neural networks.

Recently, computational modeling has shifted towards the use of statistical inference, deep learning, and other data-driven modeling frameworks. Although this shift in modeling holds promise in many applications like design optimization and real-time control by lowering the computational burden, training deep learning models needs a huge amount of data. This big data is not always available for scientific problems and leads to poorly generalizable data-driven models.

Hybrid Mock Circulatory Loop Simulation of Extreme Cardiac Events.

Objective: This paper presents preliminary methods of incorporating the pathological conditions of cardiac arrhythmias and valvular stenosis in hybrid mock circulation loop (hMCL) operation for the enhanced verification and validation of mechanical circulatory support devices such as VADs.

Methods: The MGH/MF Waveform datasets from PhysioNet database (including both nominal and clinically diagnosed arrhythmic ECG measurements) as well as cardiovascular system model updates are used to recreate arrhythmic events and valvular stenosis in vitro.

Results: Preliminary results show the hMCL can recreate each tested cardiac event within 2% and 4% mean error for reference pressure tracking in the aortic and left ventricular pressure chambers, respectively.

Minimally Invasive Esophagectomy in Semi-Prone Position (Pawar Technique): Technical Aspects and Outcome in 224 Patients.

 There are two patient positions described for minimally invasive esophagectomy (MIE) for esophageal cancer, viz., left lateral and prone positions. To retain the benefits and overcome the disadvantages of these positions, a semi-prone position was developed by us.

Preoperative Chemoradiation in Locally-Advanced Resectable Carcinoma of the Esophagus in a Single Rural Cancer Hospital in Western India.

 The current standard of care for the treatment of surgically resectable carcinoma of the esophagus is preoperative chemoradiation followed by surgery. There is strong evidence that this trimodality approach improves survival as compared with surgery alone.  The objective of this study is to determine the feasibility of this approach in a rural cancer institute in western India.

Retrospective analysis of patients with carcinoma cervix in a rural/semi-urban setting in Western India.

Objectives: To compare the presentation of cervical cancer and the treatment modalities received by the patients at a semi-urban/rural area of Western India with that of published literature from urban centers.

Materials And Methods: We conducted a retrospective analysis of patients with cervical cancer who presented at a semi-urban/rural cancer center between 2010 and 2013. A total of 141 patients with the median age of 51 years (25-81) were studied.

Evaluation of ER, PR and HER-2 receptor expression in breast cancer patients presenting to a semi urban cancer centre in Western India.

Background: Hormone receptor expression has been reported to be low in breast cancer patients from developing countries. The pattern of receptor expression from urban and rural areas is not well studied.

Materials And Methods: This is a retrospective analysis of 206 consecutive breast cancer patients presenting to a semi urban cancer centre from 2009-2010.