Personalized Data Research Articles

Exploration of the personalized immune checkpoint atlas of plasma cell dyscrasias patients using high‑dimensional single‑cell analysis.

Immune checkpoint blockade endows patients with unparalleled success in conquering cancer. Unfortunately, inter-individual heterogeneity causes failure in controlling tumors in many patients. Emerging mass cytometry technology is capable of revealing a multiscale onco-immune landscape that improves the efficacy of cancer immunotherapy. We introduced mass cytometry to determine the personalized immune checkpoint status in bone marrow and peripheral blood samples from 3 patients with multiple myeloma, amyloid light-chain amyloidosis, and solitary bone plasmacytoma and 1 non-hematologic malignancy patient. The expression of 18 immune regulatory receptors and ligands on 17 defined cell populations was simultaneously examined. By single-cell analyses, we identified the T cell clusters that serve as immunosuppressive signal source and revealed integrated immune checkpoint axes of individuals, thereby providing multiple potential immunotherapeutic targets, including programmed cell death protein 1 (PD-1), inducible co-stimulator (ICOS), and cluster of differentiation 28 (CD28), for each patient. Distinguishing the cell populations that function as providers and receivers of the immune checkpoint signals demonstrated a distinct cross-interaction network of immunomodulatory signals in individuals. These in-depth personalized data demonstrate mass cytometry as a powerful innovation to discover the systematical immune status in the primary and peripheral tumor microenvironment.

Design and test water intake monitor to improve human’s well-being

Water is a substance that the human body needs in order to survive. Drinking the right amount of water has many health benefits, including maximum physical performance, high energy levels, and improved brain function. Dehydration occurs when the body uses or loses more fluid than it takes in. When dehydration happens, the body doesn’t have enough fluids in it to carry out its normal functions. In older adults, dehydration is the most common disorder that can occur. As adults get older, the body’s fluid reserve becomes smaller, and the ability to process and conserve water is reduced. We have designed a sensor to track to the amount of water put into the body. This monitor will help seniors, especially those in a nursing home, to track their daily water intake. The sensor works with other personalized data to create a dashboard to their medical provider for better health care. There are still some limitations of the sensor. We will continue to improve the accuracy of measurement and the material we used.

Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback

Recommendation from implicit feedback is a highly challenging task due to the lack of the reliable observed negative data. A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence. Naturally, how to assign confidence weights and how to handle the large number of the unobserved data are two key problems for implicit recommendation models. However, existing methods either pursuit fast learning by manually assigning simple confidence weights, which lacks flexibility and may create empirical bias in evaluating user's preference; or adaptively infer personalized confidence weights but suffer from low efficiency.To achieve both adaptive weights assignment and efficient model learning, we propose a fast adaptively weighted matrix factorization (FAWMF) based on variational auto-encoder. The personalized data confidence weights are adaptively assigned with a parameterized neural network (function) and the network can be inferred from the data. Further, to support fast and stable learning of FAWMF, a new specific batch-based learning algorithm fBGD has been developed, which trains on all feedback data but its complexity is linear to the number of observed data. Extensive experiments on real-world datasets demonstrate the superiority of the proposed FAWMF and its learning algorithm fBGD.

Personalized cardiovascular intervention simulation system

BackgroundThis study proposes a series of geometry and physics modeling methods for personalized cardiovascular intervention procedures, which can be applied to a virtual endovascular simulator. MethodsBased on personalized clinical computed tomography angiography (CTA) data, mesh models of the cardiovascular system were constructed semi-automatically. By coupling 4D magnetic resonance imaging (MRI) sequences corresponding to a complete cardiac cycle with related physics models, a hybrid kinetic model of the cardiovascular system was built to drive kinematics and dynamics simulation. On that basis, the surgical procedures related to intervention instruments were simulated using specially-designed physics models. These models can be solved in real-time; therefore, the complex interactions between blood vessels and instruments can be well simulated. Additionally, X-ray imaging simulation algorithms and realistic rendering algorithms for virtual intervention scenes are also proposed. In particular, instrument tracking hardware with haptic feedback was developed to serve as the interaction interface of real instruments and the virtual intervention system. Finally, a personalized cardiovascular intervention simulation system was developed by integrating the techniques mentioned above. ResultsThis system supported instant modeling and simulation of personalized clinical data and significantly improved the visual and haptic immersions of vascular intervention simulation. ConclusionsIt can be used in teaching basic cardiology and effectively satisfying the demands of intervention training, personalized intervention planning, and rehearsing.

ISEA: IoT-based smartphone energy assistant for prompting energy-aware behaviors in commercial buildings

Providing personalized energy-use information to individual occupants enables the adoption of energy-aware behaviors in commercial buildings. However, the implementation of individualized feedback still remains challenging due to the difficulties in collecting personalized data, tracking personal behaviors, and delivering personalized tailored information to individual occupants. Nowadays, the Internet of Things (IoT) technologies are used in a variety of applications including real-time monitoring, control, and decision-making due to the flexibility of these technologies for fusing different data streams. In this paper, we propose a novel IoT-based smartphone energy assistant (iSEA) framework which prompts energy-aware behaviors in commercial buildings. iSEA tracks individual occupants through tracking their smartphones, uses a deep learning approach to identify their energy usage, and delivers personalized tailored feedback to impact their usage. iSEA particularly uses an energy-use efficiency index (EEI) to understand behaviors and categorize them into efficient and inefficient behaviors. The iSEA architecture includes four layers: physical, cloud, service, and communication. The results of implementing iSEA in a commercial building with ten occupants over a twelve-week duration demonstrate the validity of this approach in enhancing individualized energy-use behaviors. An average of 34% energy savings was measured by tracking occupants’ EEI by the end of the experimental period. In addition, the results demonstrate that commercial building occupants often ignore controlling over lighting systems at their departure events that leads to wasting energy during non-working hours. By utilizing the existing IoT devices in commercial buildings, iSEA significantly contributes to support research efforts into sensing and enhancing energy-aware behaviors at minimal costs.

The role of new technologies in monitoring the evolution ofpsychopathology and providing measurement-based care in youngpeople.

The role of new technologies in monitoring the evolution ofpsychopathology and providing measurement-based care in youngpeople.

МОРФОФУНКЦІОНАЛЬНИЙ СТАН ПІДШЛУНКОВОЇ ЗАЛОЗИ ЩУРІВ ПРИ ВВЕДЕННІ МЕЛАТОНІНУ ПІД ЧАС РОЗВИТКУ ОЖИРІННЯ: ХРОНОТЕРАПЕВТИЧНИЙ ПІДХІД

Overweight and obesity often cause some comorbidity like insulin resistance, diabetes type 2, cancer, cardio-vascular pathology etc. Pancreas is the important organ in carbohydrate metabolism and insulin signaling, that under obesity conditions undergo pathologic changes. For diminish adverse effects of obesity in the role of therapeutic agent is considered melatonin – pineal gland pleiotropic multifunctional molecule. In view of development precision medicine, which include processing personalized data of whole genome sequencing, microbiome, individual day/night regime etc., time selection of drug administration for maximize efficacy and minimize side effects to each patient in according of private organism circadian rhythm is the main goal of chronotherapy approach. The aim of our study was to determine morpho-functional state (morphology characteristic of exocrine and endocrine part; morphometric parameters: areas of pancreatic islets, acini and acinar cell nucleus) of pancreas in rats with high-calorie (high fat) diet-induced obesity after melatonin administration in determined time of the day (evening and morning). Melatonin was administered daily by gavage for 7 weeks in dose 30 mg/kg 1 h before lights-off (ZT11, evening) or 1 h after lights-on (ZT01, morning) rats with high-calorie diet (HCD). Rats with HCD had morbid changes in pancreas cells morphology of exocrine and endocrine part, which manifested in presence of macrophage and leukocyte infiltration of islets, vacuolization and lipid droplets in acinocytes cytoplasm, while areas of islets, acini and acinar cell nucleus decreased. Obese rats with melatonin administration demonstrate amelioration of HCD-associated changes in pancreas. Namely, in rats with development obesity melatonin administrations increased area of pancreatic islets in comparison to HCD group, moreover pancreas acini area reach control values. Also were observed difference between time-of-day interventions of melatonin on acinar cell nucleus area parameters: evening administration showed more strong action in increased to control level direction. Together, is suggesting about melatonin ameliorative role on morpho-functional state of pancreas exocrine and endocrine part under HCD-induced obesity conditions, additionally evening administration 1 h before light-off displayed more beneficial influence compared to morning.

The impact of data feedback on continuous quality improvement projects in Rwanda: A mixed methods analysis.

BackgroundInjuries are a leading cause of death and disability globally. Over 90% of injury-related mortality happens in low- and middle- income countries (LMICs). Rwanda's pre-hospital emergency system – Service d'Aide Medicale Urgente (SAMU) – and their partners created an electronic pre-hospital registry and Continuous Quality Improvement (CQI) project in 2014. The CQI showed progress in quality of care, sparking interest in factors enabling the project's success. Healthcare workers (HCW) are critical pieces of this success, yet we found a void of information linking pre-hospital HCW motivation to CQI programs like SAMU's.MethodsOur mixed methods approach included a 40-question survey using questions regarding HCW motivation. We scored the surveys to compare SAMU staff motivation with other HCWs in LMICs, and used a Likert scale to elicit agreement or disagreement. A semi-structured interview based on employee motivation theory qualitatively explored SAMU staff motivation using constructivist grounded theory. To find interview themes, two researchers independently performed line-by-line analysis.ResultsSAMU staff received 5–21% higher motivation scores relative to other cohorts of HCWs in LMICs. Questions showing disagreement (five) asked about reprimand, damaged social standing, and ease of using the CQI technology. Three questions did not show consensus. Questions showing agreement (23) and strong agreement (nine) asked about organizational commitment, impact, and research improving patient care. Major themes were: improvements in quality of care, changes in job expectations, views on research, and positive experiences with data feedback.ConclusionsThe CQI project provides constant feedback vital to building and sustaining successful health systems. It encourages communication, collaboration, and personal investment, which increase organizational commitment. Continuous feedback provides opportunities for personal and professional development by uncovering gaps in knowledge, patient care, and technological understanding. Complete, personalized data input encouraged by the CQI improves resource allocation, building robust health systems that improve HCW agency and motivation.

Personalized geometry digitization technique of the vertebromotor segment L4–L5 in vivo

The article aim is to present a technique for digitizing personalized lumbar computed tomography data into a finite element geometric model of the vertebromotor segment L4–L5 in vivo. The computer tomography images set digitization of the lumbar spine without pathological changes took place using Mimics Materialise. A total of 34 people were selected in the study, including 20 men and 14 women. The young patients age ranged from 19 to 41 years. The article presents a technique for digitizing personalized data of computed tomography of the lumbar region into a finite element geometric model of the vertebromotor segment L4–L5 in vivo in Mimics Materialise. As an example, the technique application to obtain morphometric parameters of the vertebromotor segment L4–L5 in vivo on a finite element model is analyzed. The technique of digitizing personalized computed tomography data into a finite element geometric model in vivo can be used for any the spine segment.

Empowering learners with personalised learning approaches? Agency, equity and transparency in the context of learning analytics

The emergence of personalised data technologies such as learning analytics is framed as a solution to manage the needs of higher education student populations that are growing ever more diverse and larger in size. However, the current approach to learning analytics presents tensions between increasing student agency in making learning-related decisions and ‘datafying’ students in the process of collecting, analysing and interpreting data. This article presents a study that explores staff and student experience of agency, equity and transparency in existing data practices and expectations towards learning analytics in a UK university. The results show a number of intertwined factors that have contributed to the tensions between enhancing a learner’s control of their studies and, at the same time, diminishing their autonomy as an active agent in the process of learning analytics. This article argues that learner empowerment should not be automatically assumed to have taken place as part of the adoption of learning analytics. Instead, the interwoven power relationships in a complex educational system and the interactions between humans and machines need to be taken into consideration when presenting learning analytics as an equitable process to enhance student agency and educational equity.

An Overview of User-Interactions in Exploratory Search: Theoretical Foundations, Techniques, and Research Issues

In the 21st century, an individual is enclosed with data plethora, which carries insights and knowledge. Though, to seek relevant objects, a user with uncertain information needs to opportunistically adopt several strategies, e.g., analytical search, search by analogy, etc, to aggregate the knowledge. These exploratory conversations are driven by focused-search and exploratory-browsing. In this paper, a critical study on various aspects of user-interactions in exploratory search is conducted, to trace the trends and the viability of the existing techniques and eventually to uncover the inherent limitations. It is evident that, despite the recent developments, a search task is mainly constrained due to 'insufficient means to specify user-search', 'inability to understand search-intent evolutions' and 'limited support for navigation towards unexplored-data'. The article assert that, proactive modelling of search-intents for automatic data exploration and visualisation are pivotal to deal highlighted issues and be a prospective trend to design the personalised data exploration techniques.

An Interactive and Personalized Erasure Animation System for a Large Group of Participants

This paper introduces a system to realize interactive and personalized erasure animations by using mobile terminals, a shared display terminal, and a database server for a large group of participants. In the system, participants shake their mobile terminals with their hands. Their shaking data are captured by the database server. Then there are immersive and somatosensory erasure animations on the shared display terminal according to the participants’ shaking data in the database server. The system is implemented by a data preprocessing module and an interactive erasure animation module. The former is mainly responsible for the cleaning and semantic standardization of the personalized erasure shape data. The latter realizes the interactive erasure animation, which involves shaking the mobile terminal, visualizations of the erasure animation on the shared display terminal, and dynamic and personalized data editing. The experimental results show that the system can realize various styles of personalized erasure animation and can respond to more than 2000 shaking actions simultaneously and present the corresponding erasure animations on the shared display terminal in real time.

Patient-generated health data management and quality challenges in remote patient monitoring.

BackgroundPatient-Generated Health Data (PGHD) in remote monitoring programs is a promising source of precise, personalized data, encouraged by expanding growth in the health technologies market. However, PGHD utilization in clinical settings is low. One of the critical challenges that impedes confident clinical use of PGHD is that these data are not managed according to any recognized approach for data quality assurance.ObjectiveThis article aims to identify the PGHD management and quality challenges that such an approach must address, as these are expressed by key PGHD stakeholder groups.Materials and MethodsIn-depth interviews were conducted with 20 experts who have experience in the use of PGHD in remote patient monitoring, including: healthcare providers, health information professionals within clinical settings, and commercial providers of remote monitoring solutions. Participants were asked to describe PGHD management processes in the remote monitoring programs in which they are involved, and to express their perspectives on PGHD quality challenges during the data management stages.ResultsThe remote monitoring programs in the study did not follow clear PGHD management or quality assurance approach. Participants were not fully aware of all the considerations of PGHD quality. Digital health literacy, wearable accuracy, difficulty in data interpretation, and lack of PGHD integration with electronic medical record systems were among the key challenges identified that impact PGHD quality.ConclusionCo-development of PGHD quality guidelines with relevant stakeholders, including patients, is needed to ensure that quality remote monitoring data from wearables is available for use in more precise and personalized patient care.

Combination of sensor-embedded and secure server-distributed artificial intelligence for healthcare applications

Abstract The application of artificial intelligence (AI) in the areas of health, care and social participation offers great opportunities but also involves great challenges. Extensive regulatory, ethical and data-security related requirements exist for data recording, storage and processing of respective personalized and patient-related data. “Artificial Intelligence as a Service” (AIaaS) is pushed for consumer applications by global players, which implies data storage on external database server. However, the available solutions do not meet the requirements. Moreover, small and medium-sized enterprises (SMEs) in the field of healthcare fear the loss of data sovereignty and information outflow. In this paper, we propose a secure and resource-efficient approach by embedding AI directly close to the sensor in combination with secure and distributed data processing on local server or certified “Trusted Data Center”. For this purpose, we have developed the Artificial Intelligence for Embedded Systems (AIfES) platform-independent machine learning library in C programming language. It contains a fully configurable deep artificial neural network with feedforward structure. The library can be run directly on a microcontroller and even allows to train the neural network. Possible healthcare applications include direct (pre-) processing of sensor data, sensor calibration, pattern recognition and classification.

An apparatus for personalized atmospheric and flight data collection aboard high altitude weather balloons

A high altitude balloon (HAB) is a low cost platform capable of carrying a payload over 30,000 m above the Earth. HABs are often used for photography of the curvature of the Earth and experimentation in the lower stratosphere, offering the opportunity for affordable atmospheric and climate experimentation and research. While HABs offer the ability for original research, existing data loggers do not provide an opportunity for personalized data collection, as all options are closed source or require substantial modification of code and hardware. The apparatus presented in this paper is designed to foster customization by researchers through specially segmented and easily adaptable code, the use of the Arduino microcontroller, and by being comprised of affordable off-the-shelf components – allowing alteration without advanced knowledge of programming or electronics. Without modification, the presented apparatus collects equivalent data to commercial options while costing just 1/5 the price to produce. This paper features the steps taken by researchers to personalize the presented apparatus with a CO2 sensor and a field test in which student researchers customized the presented apparatus with a UV sensor for climate and ozone studies.

Fast Algorithms for Online Personalized Assortment Optimization in a Big Data Regime

We consider an online personalized assortment optimization problem where customers arrive sequentially and make their choices (e.g., click an ad, purchase a product) following the multinomial logit (MNL) model with unknown parameters. Utilizing customer's personal information, the firm makes an assortment decision tailored for the individual customer's preference. We develop two algorithms which make assortment recommendations to maximize expected total revenue while concurrently learning the demand. The first algorithm constructs upper-confidence bounds (UCB) of product utilities using estimated demand parameters and personalized data to balance exploration and exploitation. The second algorithm incorporates a fast online convex optimization procedure in the first algorithm, which significantly reduces the computational effort; thus it is particularly useful when solving online personalized assortment optimization problem in a big data regime. We show that the algorithms can be modified to solve high dimensional problem (i.e., when the dimension of customer's personal information data is high) through a dimension reduction method known as random projection. The theoretical performance for our algorithms in terms of regret are derived, and numerical experiments using synthetic and real data demonstrate that they perform very well in both low and high dimensional settings compared with several benchmarks.

Runners’ Perspectives on ‘Smart’ Wearable Technology and Its Use for Preventing Injury

ABSTRACTUnderstanding the user experience between runners and wearable technology is crucial for designing personalized and effective wearable technology features for injury prevention. Therefore, the overall objective of this study was to understand the attitudes and beliefs for competitive and recreational runners towards wearable technology as well as its potential use for preventing injury. Survey data were drawn from 663 respondents. Competitive runners preferred GPS running watches and were interested in tracking personalized data to optimize running efficiency, whereas recreational runners used mobile phones/apps and wristband activity trackers to increase motivation. All runners believed that basic metrics found in wearable technology were most important for injury prevention; however, more advanced metrics had little importance. This paper illustrates the importance of understanding different user experiences for recreational and competitive runners in relation to wearable technology, and encourages the human-computer interaction research community to identify methods in personalizing complex running-related wearable technology data.

The era of connectedness: How AI will help deliver the future of banking

How will the future model of financial services be delivered, and how can analytical tools leveraging artificial intelligence (AI) and machine learning create new forms of customer value? This paper begins by providing historical context around modern technological conveniences and explaining how this bring new forms of contextual interactions utilising personalised data and emerging technologies. Through examples from global technology firms, the authors explore how the absorption and optimisation of customer data lead to more pertinent advice centred around everyday life events, and where innovations in financial services could transform the banking industry. The paper uses pertinent industry use cases that demonstrate how financial institutions can build trust and empathy to create a deeper, more emotional connection between brand and customer. The paper reviews how modern applications of AI are collectively creating a more inclusive and equitable financial services ecosystem. These innovations will help deliver new value on top of evolving service platforms to create symbiotic relationships between health and wealth that could have significant multigenerational impacts. The paper concludes that there should be greater societal value derived from the financial services sector as it develops new algorithmic pathways towards broader and systematic financial security for the greater good.

Finite state machine implementation for left ventricle modeling and control

BackgroundSimulation of a left ventricle has become a critical facet of evaluating therapies and operations that interact with cardiac performance. The ability to simulate a wide range of possible conditions, changes in cardiac performance, and production of nuisances at transition points enables evaluation of precision medicine concepts that are designed to function through this spectrum. Ventricle models have historically been based on biomechanical analysis, with model architectures constituted of continuous states and not conducive to deterministic processing. Producing a finite-state machine governance of a left ventricle model would enable a broad range of applications: physiological controller development, experimental left ventricle control, and high throughput simulations of left ventricle function.MethodsA method for simulating left ventricular pressure-volume control utilizing a preload, afterload, and contractility sensitive computational model is shown. This approach uses a logic-based conditional finite state machine based on the four pressure-volume phases that describe left ventricular function. This was executed with a physical system hydraulic model using MathWorks’ Simulink® and Stateflow tools.ResultsThe approach developed is capable of simulating changes in preload, afterload, and contractility in time based on a patient’s preload analysis. Six pressure–volume loop simulations are presented to include a base-line, preload change only, afterload change only, contractility change only, a clinical control, and heart failure with normal ejection fraction. All simulations produced an error of less than 1 mmHg and 1 mL of the absolute difference between the desired and simulated pressure and volume set points. The acceptable performance of the fixed-timestep architecture in the finite state machine allows for deployment to deterministic systems, such as experimental systems for validation.ConclusionsThe proposed approach allows for personalized data, revealed through an individualized clinical pressure–volume analysis, to be simulated in silico. The computational model architecture enables this control structure to be executed on deterministic systems that govern experimental left ventricles. This provides a mock circulatory system with the ability to investigate the pathophysiology for a specific individual by replicating the exact pressure–volume relationship defined by their left ventricular functionality; as well as perform predictive analysis regarding changes in preload, afterload, and contractility in time.

Semantic lifting and reasoning on the personalised activity big data repository for healthcare research

Semantic lifting and reasoning on the personalised activity big data repository for healthcare research