• Digital Twins in Health

Caso de uso aplicado para un ejemplo real en el que CTN se ha basado para capacitarse en la implementación de algoritmos de minería de procesos sobre un conjunto de datos real del sector sanitario. Concretamente, nos centramos en las diferentes fases por las que atraviesa un paciente cuando realiza una consulta médica, de modo que el conjunto de datos se conforma de un listado de 100 pacientes con sus correspondientes citas médicas con los respectivos doctores y las diferentes pruebas a las que se someten. Estos datos se han recopilado para el proyecto MINEPRAFDT - Mining process & analysis for Digital Twin - Aplicación del Process Mining al modelado y análisis de proceso industriales con una alta componente manual para la creación de su Gemelo Digital, financiado por el Instituto de Fomento de la Región de Murcia con el apoyo de los Fondos FEDER. {"references": ["https://medium.com/@c3_62722/process-mining-with-python-tutorial-a-healthcare-application-part-1-ae02027a050", "https://medium.com/@c3_62722/process-mining-with-python-tutorial-a-healthcare-application-part-3-cc9af986c122", "https://pm4py.fit.fraunhofer.de/", "https://www.futurelearn.com/courses/process-mining-healthcare"]}

Overview This repository contains a comprehensive dataset to assess cognitive states, workload, situational awareness, stress, and performance in human-in-the-loop process control rooms. The dataset includes objective and subjective measures from various data collection tools such as NASA-TLX, SART, eye tracking, EEG, Health Monitoring Watch, surveys, and think-aloud situational awareness assessments. It is based on an experimental study of a formaldehyde production plant based on participants' interactions in a controlled control room experimental setting. Purpose The study compared three different setups of human system interfaces in four human-in-the-loop (HITL) configurations, incorporating two alarm design formats (Prioritised vs non-prioritised) and three procedural guidance setups (e.g. one presenting paper procedures, one offering digitised screen-based procedures, and lastly an AI-based procedural guidance system). Key Features Subject Area: Chemical Engineering, Control and Safety Engineering, Human Factors and Ergonomics, Human-Computer Interaction, and Artificial Intelligence Data Format: Raw, Analyzed, Filtered Type of Data: CSV File (.csv), Matlab File (.mat), Excel (.xlsx), Table Data Collection: The dataset contains behavioural, cognitive, and performance data from 92 participants, including system data under each participant from three scenarios, each simulating a typical control room monitoring, alarm handling, planning, and intervention tasks and subtasks. The participants consented to participate on the test day, after which the researchers trained them. They performed tasks under three scenarios, each lasting 15 - 18 minutes. During these tests, the participant wore a watch for health monitoring, including an eye tracker. They were asked situational awareness questions based on the SPAM methodology at specific periods within 15 minutes, especially at the 6th, 8th, and 12th minutes. These questions assessed the three levels of situational awareness: perception, comprehension, and projection. This feedback collection process on situational awareness differed for one of the groups that used an AI-based decision support system. The question for this group was asked right after specific actions. Therefore, for the overall study, the following performance-shaping factors are considered: type of decision support system (alarm display design, procedure format, AI support, interface design), communication, situational awareness, cognitive workload, experience/training, task complexity, and stress. In both cases, communication was excluded as a factor considered in the first and second scenarios based on this absence. The data collected was normalized using the Min-Max normalization. Potential Applications The dataset provides an opportunity for various applications, including: Developing human performance models and process safety models Developing a digital twin simulating human-machine interaction in process control rooms Optimizing human-AI interaction in safety-critical industries Qualifying and quantifying the performance and effectiveness of AI-enhanced decision support systems incorporating Deep Reinforcement Learning (DRL) using a Specialized Reinforcement Learning Agent (SRLA) framework Validating proposed solutions for the industry Usage The dataset is instrumental for researchers, decision-makers, system engineers, human factor engineers, and teams developing guidelines and standards. It is also applicable for validating proposed solutions for the industry and for researchers in similar or close domains. Data Structure The concatenated Excel file for the dataset may include the following detailed data: Demographic and Educational Background Data: Participant Identifier: A unique alphanumeric code assigned to each participant for anonymity and tracking purposes. Age: The age of each participant at the time of the experiment. Gender: The gender of each participant, typically categorized as male, female, or other. Educational Background: Details of participants' academic qualifications, including degree type (e.g., Masters, PhD), year of study, and field of study (e.g., Chemical Engineering, IT). Dominant Hand: Information on whether participants are right or left-handed, which could influence their interaction with the simulation interface. Familiarity with Industry and Control Room: Self-reported familiarity levels with the industry in general and control room environments specifically, on a scale from 1 to 5. SPAM Metrics: Participant Identifier: Unique codes for participants (e.g., P04, P06), maintaining anonymity while allowing for individual analysis. Group Assignment: Indicates the experimental group (e.g., G4, G3, G2, G1) to which participants belonged, reflecting different levels of decision support in the simulation. Scenario Engagement: Identifies the specific scenarios (e.g., S1, S2, S3) each participant encountered, representing diverse challenges within the control room simulation. SPAM Metrics: Participant ratings across three dimensions of the SPAM questionnaire - Perception, Understanding, and Projection, on a scale typically from 1 to 5. SPAM Index: Composite scores derived from the SPAM, indicating overall situation awareness levels experienced by participants. Calculated as the average of the score on perception, understanding and projection. NASA-TLX Responses: Participant Identifier: A unique alphanumeric code assigned to each participant for anonymity and tracking purposes. Group Assignment: Indicates the experimental group (e.g., G1) to which participants were assigned, reflecting different levels of decision support in the simulation. TLX Ratings: Participants' responses utilizing the NASA Task Load Index (NASA TLX) questionnaire, providing insights into the cognitive, physical, and emotional workload experienced by operators in simulated control room scenarios. TLX Index: Composite scores derived from the NASA TLX, representing the overall workload experienced by the participant, calculated as an average of the ratings across the six dimensions. SART Data: Participant Identifier: Unique codes for participants (e.g., P04, P06), maintaining anonymity while allowing for individual analysis. Group Assignment: Indicates the experimental group (e.g., G1) to which participants belonged, reflecting different levels of decision support in the simulation. SART Metrics: Participants' responses to the Situation Awareness Rating Technique (SART) questionnaire, capturing metrics reflecting the participants' situation awareness. It is calculated using the equation U - (D - S). Situation Understanding (U) comprises Information Quantity, Information Quality, and Familiarity. Situation demand (D) includes the situation's Instability, Complexity, and Variability. At the same time, the Supply of attentional resources (S) comprises Arousal, Concentration, Division of Attention, and Spare Capacity. AI Decision Support System Feedback: Participant Identifier: A unique alphanumeric code assigned to each participant for anonymity and tracking purposes. AI System Ratings: Participants' feedback and ratings across different aspects of the AI decision support system, such as support, explainability, and trust, providing insights into the system's perceived strengths and areas for improvement. Workload Impact Data: Information on the workload impact and the balance between AI benefits and additional workload, offering valuable perspectives on the practicality and efficiency of integrating AI systems in control room operations. DRL (Deep Reinforcement Learning) Role: Emphasis on the importance of validating AI recommendations and the role of Deep Reinforcement Learning (DRL) in enhancing trust. Performance Metrics: Participant Identifier: A unique alphanumeric code assigned to each participant for anonymity and tracking purposes. Scenario Engagement: Details of the specific scenario (e.g., S1, S2, S3) each participant encountered, representing various challenges in the control room environment. Task-Specific Performance Measures: Data capturing the participants' experiences and performance across different scenarios in a control room simulation, including task-specific performance measures and outcomes related to decision-making processes in safety- critical environments. This detailed breakdown provides a comprehensive view of the specific data elements that could be included in the concatenated Excel file, allowing for thorough analysis and exploration of the participants' experiences, cognitive states, workload, and decision-making processes in control room environments. Citation Please cite this article and dataset if you use this dataset in your research or publication. Amazu, C. W., Mietkiewicz, J., Abbas, A. N., Briwa, H., Perez, A. A., Baldissone, G., ... & Leva, M. C. (2024). Experiment Data: Human-in-the-loop Decision Support in Process Control Rooms. Data in Brief, 110170.

Abstract Background Mitotic rate is routinely assessed in breast cancer cases and based on the assessment of 10 high power fields (HPF), a non-standard sample area, as per the College of American Pathologists cancer checklist. The effect of sample area variation has not been assessed. Methods A computer model making use of the binomial distribution was developed to calculate the misclassification rate in 1,000,000 simulated breast specimens using the extremes of field diameter (FD) and mitotic density cutoffs (3 and 8 mitoses/mm2), and for a sample area of 5 mm2. Mitotic counts were assumed to be a random sampling problem using a mitotic rate distribution derived from an experimental study (range 0–16.4 mitoses/mm2). The cellular density was 2500 cell/mm2. Results For the smallest microscopes (FD = 0.40 mm, area 1.26 mm2) 16% of cases were misclassified, compared to 9% of the largest (FD 0.69 mm, area 3.74 mm2), versus 8% for 5 mm2. An excess of 27% of score 2 cases were misclassified as 1 or 3 for the lower FD. Conclusion Mitotic scores based on ten HPFs of a small field area microscope are less reliable measures of the mitotic density than in a bigger field area microscope; therefore, the sample area should be standardized. When mitotic counts are close to the cut-offs the score is less reproducible. These cases could benefit from using larger sample areas. A measure of mitotic density variation due to sampling may assist in the interpretation of the mitotic score.

Additional file 17. GWAS enrichment results and results from pathway analysis of those GWAS genes, for lesional and non-lesional DEGs and URs, in AD, UC, and CD.

End-stage renal disease (ESRD) is a major and growing healthcare problem associated with substantial costs. By the end of 2010 the global patient population requiring chronic renal replacement therapy (RRT) exceeds 2 million, of which approximately 90% relies on hemodialysis (HD). The number of patients dependent on RRT are expected to annually increase with 8%. Based on this figure, it is expected that in 2030, 7.3 million ESRD patients need HD treatment. To facilitate adequate HD therapy a reliable vascular access (VA) is mandatory and can be provided by either creation of an autologous arteriovenous fistula (AVF), a prosthetic arteriovenous graft (AVG) or a central venous catheter (CVC). Guidelines by the National Kidney Foundation (NKF K/DOQI Guidelines), the Vascular Access Society (Good Nephrological Practice Guidelines) and the European Dialysis and Transplant Association (European Best Practice Guidelines on vascular access) advocate the implementation of an all-autologous fistula policy to maximize the use of AVF over AVG and CVC because AVF have the best long-term patency, fewer complications and require less interventions once fully maturated. Although the implementation of preoperative ultrasonography examination for vessel assessment has reduced the number of early AVF failure by improving the selection of the most suitable vessels and site for AVF creation, short- and long-term AVF dysfunction remains the major cause of morbidity and hospitalisation in HD patients, and is therefore the major limitation for HD treatment. This dysfunction is usually associated with non-maturation of the newly created AVF or the formation of neo-intimal hyperplasia (NIH) which potentially results in decreased access flow and eventual fistula thrombosis in up to 50% of AVFs. On the other hand, the low resistance vascular traject via the AVF may lead to impeded perfusion of the extremity distally of the AV anastomosis resulting in hand ischemia (HAIDI = Hemodialysis Access Induced Distal Ischemia), while an abundant AVF flow may lead to the development of left ventricular hypertrophy, both with potentially severe consequences. These high-flow complications occur in approximately 20% of fistulae. Numerous studies have investigated alternative preoperative mapping tools and criteria for reduction of AVF related complications. However, current clinical use of these individual tools and parameters does not take into account their potential interplay at a systemic level. Therefore one might consider that multiple prognostic parameters within a single patient are likely more valuable to improve outcome and therefore it is obvious to tailor the type of AVF to the individual patient. A possible solution to deal with multiple independent prognostic factors is implementation of a predictive patient-specific computational tool that relates geometrical, mechanical and hemodynamical parameters by means of physical laws. As a result, the computational tool takes the complex interplay between different prognostic parameters into consideration and accounts for individual differences in anatomy, physiology, demography and hemodynamics. Such an innovative computational tool opens new opportunities. By predicting postoperative flow abovementioned deleterious events can possibly be prevented. High-flow (>1500ml/min) and low-flow (<600ml/min) vascular access can then be predicted and consequently be rejected and a more suitable AVF-configuration chosen. Consequently, simulation of outcome after AVF creation is at hand. Recently, the feasibility of VA computational simulation has been investigated and proven in the ARCH FP7 ICT-224390 project (ARCH; patient-specific image-based computational modeling for improvement of short- and long- term outcome of vascular access in patients on hemodialysis therapy). Within this technological and clinical study, longitudinal collection of cardiovascular data was performed with the intention to develop, calibrate and validate patient-specific modelling tools for surgical planning and assistance in the management of complications arising from AVF creation. Given the difficult and heterogeneous patient population, the study protocol was designed in such way that pre- and postoperative imaging could be performed strictly, aiming at complete datasets of structural, functional and demographical data. Although the computational simulation model has been validated in a small patient group, larger randomized observational patient studies, aiming at evaluating the potential beneficial effect of the use of computational tools in reducing AVF-related clinical problems, are needed. Patients suffering from end-stage renal disease (ESRD) are dependent on renal replacement therapy (dialysis). The majority of dialysis is facilitated by hemodialysis. For hemodialysis a vascular access is necessary, preferable an arteriovenous fistula (AVF) in which a vein is directly anastomosed to an artery. In order to use the AVF for hemodialysis three criteria have to be met; the minimal flow over the AVF is 600 mL/min, the diameter is at least 6 mm, and the AVF is located less than 6 mm under the skin. Unfortunately, approximately half of the patients (50%) are confronted with an AVF that does not meet these criteria; the so called non-maturation or primary failure. In case of non-maturation the AVF is not only unusable for dialysis, but also requires reinterventions on short- and long-term. Firstly to mature the AVF, and secondly, when the AVF is matured, to keep the vascular access. Using a computational simulation postoperative flow can be predicted. Based on patient-specific duplex measurements, the model can calculate the flow that can be expected following vascular access surgery for all AVF configurations; fore- or upper arm. These calculations lead to an advice which configuration is indicated; a flow that exceeds 600 mL/min, leading to maturation. Potentially the aforementioned 50% of non-maturation can be reduced. The patient then has an adequate vascular access and reinterventions are adverted, resulting in a decrease of costs, hospital demand, and an increase of the patients' quality of life. When the expected reduction of non-maturation is confirmed, the computational tool can be offered to other hospitals.

Additional file 3. GNU octave computer code â get_sample_mitotic_score.mâ .

We use three MeSH branches as representations of Health-demand, Informatics-supply, and Technological applications (hereafter, H-I-T model) and use their co-occurrences to measure the digital medical innovation process in China. The detailed definition of HIT is as follows：1) H: The entire “Diseases [C]” branch as well as two subbranches, i.e., “Health [N01.400]” and “Public Health [N06.850]” are regarded as a representation of health demand for HIT innovations. “Health [N01.400]” and “Public Health [N06.850]” are under the branches “Population Characteristics [N01]” and “Environmental and Public Health [N06]”, respectively—with the top root “Health Care [N]”. So, we use two MeSH terms “health” and “public health” to represent the population health demand, and the "diseases category" MeSH terms to indicate the individual health demand (specific diseases management).2) I: The “Information Science [L]” branch as a representation of the supply side in terms of informatics concepts and techniques.3) T: The “Analytic, Diagnostic, and Therapeutic Techniques and Equipment [E]” branch is a representation of the state of the art of technological applications, namely the functions to be realized by informatics, e.g., diagnosis, therapeutics, surgical procedures, investigative techniques, equipment and supplies.In the H-I-T model, every related article can be classified as Health demand (H), Informatics-supply (I), Technological applications (T), or a combination of these three using its MeSH terms and HIT score. MeSH terms are arranged in an alphabetical and hierarchical structure from the most general level to the narrowest level. Table 1 shows the branches of MeSH terms used in distinguishing the H-I-T classification. Note that since the MeSH term “Public Health” has another tree number H02.403.720 (Branch of medicine concerned with the prevention and control of disease and disability, and the promotion of physical and mental health of the population on the international, national, state, or municipal level), terms under this branch are also included in health-demand (H) category. These terms include Epidemiology, Molecular Epidemiology, Pharmacoepidemiology, Preventive Medicine, Environmental Medicine, Occupational Medicine, Preventive Psychiatry.To calculate the HIT score, the MeSH list and the MeSH terms contained in each article are required:The MeSH 2020 stored in file: MeSH_trees.csvThe UK/US/CHINA/WORLD's medical informatics publications and HIT scores stored in files: redo_cn_HIT_pall.csv redo_UK_HIT_pall.csv redo_UK_HIT_pall.csv redo_WORLD_HIT_pall.csvAll files contain publication id(pubid),publish year(year),mesh terms(mesh),H score(H),I score(I),T score(T)

The face is a fundamental structure of our body that expresses all our emotions and forms an important part of our identity. Injuries to the face are among the most devastating for patients, both medically and psychologically. Despite its importance, many facial injuries cannot be repaired surgically due to extensive damage or other irreparable conditions. In difficult scenarios like these, plastic surgeons have grown new tissues with the patient���s cells to cover up those defects, instead of trying to perform complicated plastic and reconstructive surgeries. The increased complexity of microcirculation and the necessity to promote regeneration in tissues that have suffered from traumatic injury or a pathological process led to an increase in interest in the development of regenerative medicine. The practice of using a patient's cells to promote healing falls within the ambit of Regenerative Medicine. This relatively new field includes the use of stem cells, tissue scaffolds, and growth factors. The fundamental factors necessary are a source of viable cells, a robust scaffold, an effective method of combining cells with scaffold, and a constellation of growth factors to support the growth of newly regenerative tissues. Regenerative medicine and tissue engineering research is a highly complex field traversing through multiple disciplines. Effective coordination between different scientists, clinicians, and departments is necessary to achieve a properly functioning regenerative science program. Simultaneously, there has been a rapid surge in the development of new biomaterials, tissue engineering approaches, and cell-based therapies. A wide range of biomaterials has been used for tissue engineering applications such as scaffolds for skin replacement, trachea replacements, cartilage grafts, vascular grafts, and ligament reconstruction, etc. The use of these biomaterials has simplified clinical practice to a great extent and benefitted the patients. Tissue Engineering is an area of research that uses living cells to replace or repair damaged tissues. The process involves taking a patient���s cells, growing them in the lab, and implanting them back into the patient. This approach helps overcome problems with transplant rejection and the need for anti-rejection drugs. The process of cellular tissue engineering involves the use of scaffolding to grow cells. Scientists have been using tissue scaffolds for years, and they have developed several methods to grow a variety of tissues, such as skin, bone, ligaments, and cartilage. For example, to develop skin that can be used to treat severe burns or replace lost skin due to trauma or cancer, they have implanted autologous tissue-derived cells (and not just stem cells) onto a tissue scaffold. A sufficient number of cells are necessary for the synthesis of a new tissue matrix. Tissue scaffolds, biomolecules, and a supportive microenvironment provide a vital stimulus for the proliferation, orientation, and differentiation of the cells. For this newly regenerated matrix to be durable, it must go through three stages: growth, induction, and maintenance of maturation. Autologous (from the same person) cells are preferred due to their lack of evoking any immunogenic reaction. Other than that, cells can also be sourced from the same species (allogenic) or different species (xenogenic). Furthermore, cells may also be classified based on their unique capabilities for further differentiation and multiplication. Stem cells are found in embryos and umbilical cords, as well as in bone marrow and adipose tissue (body fat). Usually, the stem cells in embryos are pluripotent, while those in an adult bone marrow are multipotent. Adult somatic cells have fully developed functions. They cannot divide and grow as fast as stem cells, which makes them less useful for tissue engineering. Progenitor cells are cells that can become a more specialized cell type than their originating cell type. Progenitor cells are more differentiated than stem cells and are therefore called multipotent rather than pluripotent. Tissue Scaffolds are a necessary component of any regenerative medicine and tissue engineering strategy. A suitable framework for cell growth and development provides cells with the structure they need to migrate, multiply and differentiate. It also provides cells with the ability to reorganize and form a functional 3D network. There are two main classifications of tissue scaffolds: natural and synthetic. The development of biologic scaffolds can be done in vitro through a bioreactor or in vivo by implanting the construct into the body. Functionalized and intelligent biomaterials containing biomolecular properties on their surface aim to orchestrate and optimize cell attachment to the surfaces. This allows for more vigorous growth and synthesis of new tissues. Advances in biomanufacturing technologies engineering, materials science, and tissue engineering have allowed the design and development of more complex self-organization of regenerative tissues, along with further advancements through computer modeling, bioprinting and nanotechnology. The size of the tissue scaffolds is largely limited by the lack of effective vascularization. The most successful research in this field focuses on understanding the components of native tissues and their micro-architecture. A good understanding is fundamental to creating an accurate reproduction of functional tissues. The desirable properties necessary in a tissue scaffold includes: ��� Biocompatibility. ��� Mechanical stability. ��� Efficient pore size that would enable sufficient vascularization while fulfilling the metabolic needs of the cells. ��� Non-immunogenic. ��� 3D architecture that allows for cell growth and migration. ��� Microenvironments conducive to migration, maturation, and reproduction of cells. ��� Suitability for sterilization to allow clinical use. ��� Easy to be mass-produced by the industry. Regenerative medicine with newly engineered tissues has the potential to change reconstructive plastic surgery. For this approach to work, scientists must be able to create new tissues in a lab that is similar to natural tissue in function and appearance. Basic scientific research in cell and gene therapies has led to the development of a variety of cell and gene therapy products. However, this has not yet resulted in plenty of commercial products that are available for clinical use. To translate newly regenerated tissue constructs from the laboratory into actual clinical practice, an effective multidisciplinary approach is required. Ethical considerations and regulatory issues add to the challenges of these translational activities. Conclusion: Regenerative medicine offers great potential to reduce patient morbidity and mortality, but a coordinated and lasting link between physicians, scientists, and the industry is needed to change from potential to reality.

Additional file 8. Prioritization of all identified URs. The z score indicates the activation state of an upstream regulator. The farther the activation z score is from zero, the more likely it is that the direction of differential expression of the target genes is consistent with the regulator being in either an “activated” or an “inhibited” state. The URs (columns) are presented in ranked order, from left to rights (decreasing), based on the number of cell types that each UR is predicted to regulate at different time points (|z-score| ≥ 2 and P-value < 0.05). The data is illustrated in Fig. 7D.