AI and deep learning for processing the huge amount of patient-centric data that assist in clinical decisions

The area of clinical decision support systems (CDSS) is facing a boost in research and development with the increasing amount of data in clinical analysis together with new tools to support patient care. This creates a vibrant and challenging environment for the medical and technical staff. This chapter presents a discussion about the challenges and trends of CDSS considering big data and patient-centered constraints. Two case studies are presented in detail. The first presents the development of a big data and AI classification system for maternal and fetal ambulatory monitoring, composed by different solutions such as the implementation of an Internet of Things sensors and devices network, a fuzzy inference system for emergency alarms, a feature extraction model based on signal processing of the fetal and maternal data, and finally a deep learning classifier with six convolutional layers achieving an F1-score of 0.89 for the case of both maternal and fetal as harmful. The system was designed to support maternal–fetal ambulatory premises in developing countries, where the demand is extremely high and the number of medical specialists is very low. The second case study considered two artificial intelligence approaches to providing efficient prediction of infections for clinical decision support during the COVID-19 pandemic in Brazil. First, LSTM recurrent neural networks were considered with the model achieving R2=0.93 and MAE=40,604.4 in average, while the best, R2=0.9939, was achieved for the time series 3. Second, an open-source framework called H2O AutoML was considered with the "stacked ensemble” approach and presented the best performance followed by XGBoost. Brazil has been one of the most challenging environments during the pandemic and where efficient predictions may be the difference in saving lives. The presentation of such different approaches (ambulatory monitoring and epidemiology data) is important to illustrate the large spectrum of AI tools to support clinical decision-making. © 2022 Elsevier Inc. All rights reserved.

Towards a Deep Learning Pain-Level Detection Deployment at UAE for Patient-Centric-Pain Management and Diagnosis Support: Framework and Performance Evaluation.

The outbreak of the COVID-19 pandemic revealed the criticality of timely intervention in a situation exacerbated by a shortage in medical staff and equipment. Pain-level screening is the initial step toward identifying the severity of patient conditions. Automatic recognition of state and feelings help in identifying patient symptoms to take immediate adequate action and providing a patient-centric medical plan tailored to a patient's state. In this paper, we propose a framework for pain-level detection for deployment in the United Arab Emirates and assess its performance using the most used approaches in the literature. Our results show that a deployment of a pain-level deep learning detection framework is promising in identifying the pain level accurately.

Mobilizing the clinical trial ecosystem to drive adoption of master protocols.

Master protocol studies typically use an overarching protocol to answer several questions by guiding a variety of sub-studies. These sub-studies can incorporate multiple diseases, therapies, or both. Although this innovative approach offers many benefits, including the ability to deliver clinical research that is more patient-centric and efficient, several common barriers curtail widespread adoption. The Clinical Trials Transformation Initiative (CTTI) convened industry representatives, regulatory agencies, patient groups, and academic institutions to identify emerging best practices and develop resources designed to help sponsors and other stakeholders overcome these challenges. We first identify some broad changes needed in the clinical trials ecosystem to facilitate mainstream adoption of master protocol studies, and we subsequently summarize CTTI's resources designed to support this effort.

The COVID-19 pandemic as a catalyst for innovation: a regulatory framework to assess fit-for-purpose innovative approaches in clinical research.

The COVID-19 pandemic has had a devastating impact on individuals and multiple aspects of our society including healthcare and clinical research. The silver lining is that the pandemic also served as a catalyst for wider adoption of innovative approaches in clinical research, notably the use of mobile or remote services, and digital technologies. Regulators, clinical study investigators, clinical study participants, sponsors, and other stakeholders collaborated to adopt measures that ensured safe participation in clinical studies whilst maintaining study integrity. In this article, we propose a regulatory framework for assessing fit-for-purpose innovative approaches in clinical research based on Roche/Genentech's experience during the COVID-19 pandemic with the aim to inform and encourage broader implementation of patient-centric and sustainable innovation in clinical research. Our goal is to contribute to ongoing discussions on introducing innovative approaches in clinical trials and eventually the development of globally harmonised guidelines.

A Patient-Centric Interoperable, Quorum-based Healthcare System for Sharing Clinical Data

In the current Electronic Medical Record (EMR) systems, the healthcare organizations have the ownership of patient's EMR. Patients have only limited information of the EMR in the form of discharge summary and reports. This was viewed a problem in eHealth consultations during a pandemic like COVID-19, when doctors does not have access to patient data. Patient is the owner of the data and patient should have control over his medical data and should be able to share the data according to his requirement. So currently work is being undertaken to develop patient-centric EMR system. One major challenge here is to ensure the privacy and access management of data being accessed and shared. This paper aims to solve these challenges by using a permissioned blockchain network based FHIR solution for secure interoperability. The proposed system was evaluated by developing a prototype on Quorum Blockchain. The throughput and latency characteristics of the system was analyzed with different workloads and results was promising. © 2022 IEEE.

Artificial intelligence and the future of life sciences.

Over the past few decades, the number of health and 'omics-related data' generated and stored has grown exponentially. Patient information can be collected in real time and explored using various artificial intelligence (AI) tools in clinical trials; mobile devices can also be used to improve aspects of both the diagnosis and treatment of diseases. In addition, AI can be used in the development of new drugs or for drug repurposing, in faster diagnosis and more efficient treatment for various diseases, as well as to identify data-driven hypotheses for scientists. In this review, we discuss how AI is starting to revolutionize the life sciences sector.

Drug Information Association (DIA) 2021 Global Annual Meeting (June 26-July 1, 2021 - Virtual Meeting).

At the 57th Global Annual Meeting of the Drug Information Association (DIA), attendees met virtually for the second time to support the theme of 'Collaboration without Boundaries.' Sessions included presenters and speakers from regulatory agencies, patient advocacy and academia, with patients at the forefront of discussions. This report covers a number of presentations and panel discussions from the 4-day meeting that primarily focused on the COVID-19 global pandemic.

Progress, challenges and global approaches to rare diseases.

Rare diseases occur globally at every stage of life. Patients, families and caregivers have many unmet medical and social needs leading to extraordinary psychosocial and economic burdens. Efforts to improve diagnostic capabilities and to develop therapies for an estimated 7000 rare diseases have met with considerable success. In the United States, a rare disease or condition is one affecting fewer than 200,000 people. In the European Union (EU), a rare disease is any disease affecting fewer than 5 people in 10,000 (less than 1 in 2000 people). However, there are no effective treatments for 90 per cent of rare diseases. There is a need to expand awareness, advocacy and outreach to everyone including those with low incomes, poor literacy, minority ethnic status and living in underserved and marginalised populations in urban and rural areas as well as in developing nations throughout the world. The acceptance of patients as research partners complements the increased research emphasis and major regulatory initiatives leading to expedited review and approval programmes for products for serious or life-threatening conditions. The pipeline of new therapies provides hope to untreated patients. Advances in medical bioinformatics, artificial intelligence and machine learning with access to big data continue to identify novel therapeutics for screening and evaluation. Advanced analytics can identify the patterns of disease occurrence, predict disease progression, identify patient response to treatments, establish optimal care guidelines and generate research hypotheses with the narrowly identified research patient populations.

A Blockchain and Artificial Intelligence-Based, Patient-Centric Healthcare System for Combating the COVID-19 Pandemic: Opportunities and Applications.

The world is facing multiple healthcare challenges because of the emergence of the COVID-19 (coronavirus) pandemic. The pandemic has exposed the limitations of handling public healthcare emergencies using existing digital healthcare technologies. Thus, the COVID-19 situation has forced research institutes and countries to rethink healthcare delivery solutions to ensure continuity of services while people stay at home and practice social distancing. Recently, several researchers have focused on disruptive technologies, such as blockchain and artificial intelligence (AI), to improve the digital healthcare workflow during COVID-19. Blockchain could combat pandemics by enabling decentralized healthcare data sharing, protecting users' privacy, providing data empowerment, and ensuring reliable data management during outbreak tracking. In addition, AI provides intelligent computer-aided solutions by analyzing a patient's medical images and symptoms caused by coronavirus for efficient treatments, future outbreak prediction, and drug manufacturing. Integrating both blockchain and AI could transform the existing healthcare ecosystem by democratizing and optimizing clinical workflows. In this article, we begin with an overview of digital healthcare services and problems that have arisen during the COVID-19 pandemic. Next, we conceptually propose a decentralized, patient-centric healthcare framework based on blockchain and AI to mitigate COVID-19 challenges. Then, we explore the significant applications of integrated blockchain and AI technologies to augment existing public healthcare strategies for tackling COVID-19. Finally, we highlight the challenges and implications for future research within a patient-centric paradigm.

Lessons learned from the COVID-19 pandemic and its impact on bioanalysis and drug development.

The COVID-19 pandemic challenged pharmaceutical and bioanalytical communities at large, in the development of vaccines and therapeutics as well as supporting ongoing drug development efforts. Existing processes were challenged to manage loss of staffing at facilities along with added workloads for COVID-19-related study support including conducting preclinical testing, initiating clinical trials, conducting bioanalysis and interactions with regulatory agencies, all in an ultra-rapid timeframes. A key factor of success was creative rethinking of processes and removing barriers - some of which hitherto had been considered immovable. This article describes how bioanalysis was crippled at the onset of the pandemic but how innovative and highly collaborative efforts across teams within and outside of both pharma, bioanalytical labs and regulatory agencies worked together remarkably well.

How the COVID-19 pandemic is changing clinical trial conduct and driving innovation in bioanalysis.

Thousands of clinical trials all over the world were stopped, disrupted or delayed while countries grappled to contain the pandemic and research resources were redeployed. The long-term effects of the turbulence caused by the pandemic have yet to be fully understood, but it should already be clear that the increased focus on participant needs and on the logistical challenges of current models are not likely to fade away quickly. This disruption is opening doors for rethinking traditional approaches to clinical trial conduct - including decentralizing site visits, introducing new methods of sample collection, rethinking matrix selection, reducing sample volumes and collaborating on device development. These approaches reduce participant burden while improving critical trial data.

Telemedicine in the Western Cape Department of Health during the first peak of the COVID-19 pandemic: Leveraging data to save lives by activating a telemedicine response.

The pandemic caused by coronavirus disease 2019 (COVID-19) has put health systems across the globe under strain. There has been much suffering and loss, but a silver lining is emerging - a growing list of deeply contextualised, resource-light and patient-centric innovations that are showing the promise of reshaping health care delivery as we know it. Some of these innovations were lying latent in the system, waiting for the 'dots to be joined'. The Western Cape was the first province in South Africa to experience a COVID-19 wave from May 2020 to July 2020, with 60-70 deaths being reported daily. To bend the mortality curve during this crisis was not easy but was made possible using a rudimentary telehealth system. This project represents an exemplar of innovation, built out of necessity to save lives and may well become a staple component of the health service in a post-crisis era.

Patient-Led Research Collaborative: embedding patients in the Long COVID narrative.

A large subset of patients with coronavirus disease 2019 (COVID-19) are experiencing symptoms well beyond the claimed 2-week recovery period for mild cases. These long-term sequelae have come to be known as Long COVID. Originating out of a dedicated online support group, a team of patients formed the Patient-Led Research Collaborative and conducted the first research on Long COVID experience and symptoms. This article discusses the history and value of patient-centric and patient-led research; the formation of Patient-Led Research Collaborative as well as key findings to date; and calls for the following: the acknowledgement of Long COVID as an illness, an accurate estimate of the prevalence of Long COVID, publicly available basic symptom management, care, and research to not be limited to those with positive polymerase chain reaction and antibody tests, and aggressive research and investigation into the pathophysiology of symptoms.

Individualised Responsible Artificial Intelligence for Home-Based Rehabilitation.

Socioeconomic reasons post-COVID-19 demand unsupervised home-based rehabilitation and, specifically, artificial ambient intelligence with individualisation to support engagement and motivation. Artificial intelligence must also comply with accountability, responsibility, and transparency (ART) requirements for wider acceptability. This paper presents such a patient-centric individualised home-based rehabilitation support system. To this end, the Timed Up and Go (TUG) and Five Time Sit To Stand (FTSTS) tests evaluate daily living activity performance in the presence or development of comorbidities. We present a method for generating synthetic datasets complementing experimental observations and mitigating bias. We present an incremental hybrid machine learning algorithm combining ensemble learning and hybrid stacking using extreme gradient boosted decision trees and k-nearest neighbours to meet individualisation, interpretability, and ART design requirements while maintaining low computation footprint. The model reaches up to 100% accuracy for both FTSTS and TUG in predicting associated patient medical condition, and 100% or 83.13%, respectively, in predicting area of difficulty in the segments of the test. Our results show an improvement of 5% and 15% for FTSTS and TUG tests, respectively, over previous approaches that use intrusive means of monitoring such as cameras.

Land O'Lakes Workshop on Microsampling: Enabling Broader Adoption.

The microsampling workshop generated recommendations pertaining to blood sampling site (venous blood versus capillary blood), when to conduct a bridging study, statistical approaches to establish correlation/concordance and deciding on sample size, opportunities and challenges with patient-centric sampling, and how microsampling technology can enrich clinical drug development. Overall, the goal was to provide clarity and recommendations and enable the broader adoption of microsampling supporting patients' needs, convenience, and the transformation from clinic-centric to patient-centric drug development. The need and adoption of away-from-clinic sampling techniques has become critical to maintain patient safety during the current COVID-19 pandemic.

Have we got 'patient-centric sampling' right?

RA Koster currently works as Associate Director of Bioanalytical Science at the LC-MS/MS department at PRA Health Sciences in the Laboratory in Assen, The Netherlands. He is responsible for the LC-MS/MS analytical method development and leads a team of method development analysts and scientists. As global microsampling specialist within PRA he is interested in all developments regarding microsampling and aims to continuously improve microsampling techniques. He has been working in the field of bioanalysis for 19 years, in which he performed and supervised numerous analytical method developments using LC-MS/MS. He started his career in 2001 at Pharma Bio-Research (before it was acquired by PRA) as an LC-MS/MS analyst. In 2005, he moved to the University Medical Center Groningen where he focused on the development and validation of analytical methods for drugs and drugs of abuse in matrices like blood, plasma, hair, saliva, dried blood spots and volumetric absorptive microsampling with LC-MS/MS. In 2015 he obtained his PhD on the subject 'The influence of the sample matrix on LC-MS/MS method development and analytical performance'. In 2017, he started as Senior Scientist at PRA Health Sciences and in 2019, he accepted his current role of Associate Director of Bioanalytical Science. He is a (co-)author of more than 35 publications.

The development of patient-centric sampling as an enabling technology for clinical trials.

Accessing patient samples using a whenever/wherever paradigm is needed to enable a better understanding of human biology and disease. The technology for convenient self-collection of blood samples by patients at home is quickly becoming available. The potential benefits of patient-centric sampling far outweigh the short-term challenges associated with implementation of this disruptive approach. This is especially true given we are amid a global pandemic and enabling patients to sample at home would help not only clinical trials, but healthcare in general. This perspective article aims to convince the reader that patient-centric sampling is a reality and that we are on the cusp of an information revolution in clinical trials that will be enabled by patient-centric (e.g., at home) sampling.

Preparing for an Era of Episode-Based Care in Total Joint Arthroplasty.

With a history of steadily rising healthcare costs, the United States faces an unprecedented set of health and financial challenges. The COVID-19 pandemic will only exacerbate these challenges, and it is of paramount importance to reform and refine health systems to maximize the value of care delivered to the patient. Recent developments related to value improvement in total joint arthroplasty suggest that episode-based payment is likely to become standard practice given the current healthcare environment. Consequently, developing episode-based care models for total joint arthroplasty is in the best interests of surgeons, health systems, and patients. In this article, we review important developments related to value-based care in total joint arthroplasty and present an episode-based framework for delivering high-value, patient-centric care. We examine each phase of a total joint arthroplasty episode-preoperative, acute, post-acute, and follow up-and present several ideas with developing bodies of evidence that can improve the value of care delivered to the patient.

Evaluation of a novel blood microsampling device for clinical trial sample collection and protein biomarker analysis.

Aim: Evaluation of a novel microsampling device for its use in clinical sample collection and biomarker analysis. Methodology: Matching samples were collected from 16 healthy donors (ten females, six males; age 42 ± 20) via K2EDTA touch activated phlebotomy (TAP) device and phlebotomy. The protein profile differences between sampling groups was evaluated using aptamer-based proteomic assay SomaScan and selected ELISA. Conclusion: Somascan signal concordance between phlebotomy- and TAP-generated samples was studied and comparability of protein abundances between these blood sample collection methods was demonstrated. Statistically significant correlation in selected ELISA assays also confirmed the TAP device applicability to the quantitative analysis of protein biomarkers in clinical trials.