a EHR: electronic health record.
b HbA 1c : glycated hemoglobin.
c GP: general practitioner.
d DETECT: Dynamic Electronic Health Record Detection.
e KOA: knee osteoarthritis.
f APOL1-HR: apolipoprotein L1 high-risk.
g eGFR: estimated glomerular filtration rate.
The EHRs of patients used in the included studies were originally recorded in hospitals or primary care centers. Especially for the detection of mental and behavioral disorders, EHRs were often extracted from military health records [ 32 , 36 ], and for neurodevelopmental and cardiovascular disorders, EHRs were mostly extracted from general practices [ 33 , 37 ]. Most studies (16/20, 80%) used structured EHRs [ 29 - 33 , 35 , 38 - 43 , 45 - 48 ], sometimes combined with unstructured data [ 34 , 36 , 37 , 44 ], to estimate the risk of a disease or medical event. Demographic information (statically used), symptoms, laboratory (blood) test results, diagnoses, medications, BMI, and clinical notes were commonly used data from EHRs. In addition, the EHR length and hospital admission and visit history were frequently added to the model. Lifestyle data were included for cardiovascular diseases. Clinical and social signs were more frequently used for self-harm and mental, behavioral, and neurodevelopmental disorders. For the prediction of kidney and diabetes outcomes, laboratory test results were frequently extracted. If EHRs were unstructured, natural language processing methods were conducted as a precursor to analyze clinical notes. The central techniques were a basic recurrent neural network (RNN) or long short-term memory (LSTM) [ 29 , 31 , 34 , 35 , 39 , 44 , 45 , 49 ], often compared with logistic regression, support vector machine, or random forest. When techniques were used that could not handle temporal data, a temporal aspect was created in the data. Although not extensively specified, a slope and intercept of variables [ 31 , 36 ]; a mean [ 30 ]; minimum, maximum, median, and SD measures [ 42 ]; the addition of a time-weight (eg, 0.9 × days from reference point+decay) [ 43 ]; different time stamps [ 42 ]; or dividing the data into time blocks [ 33 , 46 ] were used. Multimedia Appendix 3 [ 29 - 48 ] provides an overview of the EHR data used and the techniques applied.
Disease detection and prevention can be supported by using ML or DL on longitudinal EHRs. First, the development and training of such models on EHRs can generate new medical insights (1-4). Second, when those models are applied (eg, for additional analyses or to “new” data in clinical practice), the following clinical benefits may be achieved (5 and 6). These insights will be summarized in the following sections.
The use of ML and DL models on EHRs could support the detection of diseases with a high diagnostic accuracy. Performance metrics such as the area under the receiver operating characteristic curve (AUROC), sensitivity (recall), specificity, accuracy, precision, and the area under the precision-recall curve evaluated the detecting ability of the model. The AUROC was by far the most frequently reported metric because it illustrates the diagnostic ability for a binary classification (disease or nondisease) by using the sensitivity versus the specificity. Although it is not our intention to identify the best-performing model, it was observed that the AUROC of central models varied between 0.73 and 0.97. In 40% (8/20) of the studies, the optimal model had a “good” detection (AUROC between 0.7 and 0.8), 35% (7/20) of the studies succeeded in having a “very good” detection (AUROC between 0.8 and 0.9), and 15% (3/20) of the studies reached an “excellent” detecting performance (AUROC between 0.9 and 1.0) [ 36 , 41 , 46 ] according to the classification of diagnostic accuracy by Simundic [ 50 ]. For the best disease detection, multiple models were compared within the study, or the central model was compared with existing detection tools. The authors of 30% (6/20) of the studies claimed that their model produced a (slightly) higher performance than “conventional” or “traditional” models or ML models in the literature [ 29 , 34 , 37 , 38 , 44 , 45 ]. In 15% (3/20) of the studies, the central model performed better compared with currently used approaches such as a validated clinical model [ 42 ], a surveillance tool on which current health indexes are based [ 47 ], and a gold standard in routine clinical practice according to the American College of Cardiology and the American Heart Association [ 40 ]. In one study, the prediction scores of the model were validated by experts who agreed 100% through manual record reviewing [ 36 ]. The diagnostic accuracy of the included models was not dependent on disease categories but relied on the EHR data given to the model. Many studies (7/20, 35%) mentioned that diseases could be detected more accurately (ie, the predictive performance was increased) when the EHRs were closer to the date of diagnosis [ 32 , 33 , 46 ] and with an increase in the number of predictors [ 37 , 40 , 43 , 48 ]. Overall, the ability of the included models to classify nonhealthy and healthy individuals was close to the registered diagnoses in the EHRs.
In 45% (9/20) of the studies, ML and DL models observed all available EHR data to classify patients as a case or control (ie, ML vs human detection) [ 30 , 33 , 34 , 36 , 38 , 39 , 42 , 43 , 45 ]. However, in the other studies (10/20, 50%), models were able to detect diseases earlier than the moment they were diagnosed by clinicians in EHRs (ie, prediction) [ 29 , 31 , 32 , 35 , 37 , 40 , 41 , 44 , 46 - 48 ]. By dividing the participants’ EHRs into 2 pieces, X years were observed (observation period), and based on these data, it was possible to predict the risk of developing a disease or medical event in the future (prediction period). In other words, the prediction was made at an earlier time (x=0) than when it was diagnosed in practice (end of black bars). In some studies (5/20, 25%), it was part of the research to identify what time frame encompasses enough predictive information and, therefore, how much earlier an (accurate) detection was possible [ 32 , 33 , 37 , 43 , 46 ]. For example, Walsh et al [ 46 ] used 2 years of EHRs and extended their prediction window more and more to find the earliest moment of an accurate prediction. Raket et al [ 35 ] predicted whether a psychosis would occur 1 year before its onset, whereas Zhao et al [ 40 ] used 7 years of EHRs to predict the occurrence of cardiovascular events in the following 10 years. Figure 2 [ 29 - 48 ] illustrates the different time frames of longitudinal EHRs and their results according to a possible earlier detection. How much earlier a disease can be detected has a varying clinical meaning and, therefore, needs its own interpretation.
Another way to support disease detection and prevention was by generating insights into factors, topics, predictors, or indicators contributing to disease prediction [ 30 , 31 , 33 , 35 - 41 , 43 - 46 ]. In unstructured clinical notes, relevant topics, related words, and medical concepts were found that contributed to disease detection [ 36 , 44 ]. These words concerned daily living, behavior, and medical history. ML and DL models using structured EHRs generated the most contributing factors and their individual contribution to the outcome [ 30 , 31 , 33 , 35 , 37 - 41 , 43 , 45 , 46 ]. The most contributing predictors reported among all disease categories were (related to) age, blood pressure, BMI, cholesterol, smoking, and specific medication. Concerning mental, behavioral, and neurodevelopmental disorders, additional predictors were related to depression, personal difficulties, and personality changes. Some of these identified predictors were new for their discipline (eg, specific medication) [ 35 , 41 , 44 ] or not yet incorporated into gold standards for clinical diagnostic guidelines (eg, genetic information) [ 40 ]. In addition to this, insights into the importance of (known) predictors were generated. For example, Raket et al [ 35 ] identified what factors were responsible for the biggest positive and negative change in risk estimation (eg, differential white blood cells) and, therefore, indicated the most effective targets for preventive interventions. Other models found that the contribution of some predictors was not as high as assumed (eg, stress on diabetes) [ 31 ]; factors that seemed individually irrelevant turned out to have cumulative important predictive value [ 35 ], and the instability of factors, not the factor itself, was a predictor for one disease [ 40 ]. The aforementioned factors were identified during model development, but applying such a model to new EHRs would generate responsible factors for that individual.
In total, 10% (2/20) of the studies used EHRs not to predict the risk of a disease but to create other health indicators. Hung et al [ 47 ] developed a health index based on 3 DL predictions of impactful and costly health indicators (mortality, hospitalization, and cancer). This health index also generated insights into the population’s health and was found to be close to the “true risk” and, therefore, a better indicator than baseline models. Another study claimed to forecast what disease an individual would have at the next hospital visit [ 48 ]. Their results showed that the developed model generated well-performing results in forecasting medical diagnoses aggregated in 3- and 4-digit International Classification of Diseases, 9th and 10 th Revision codes.
Clinical benefit 5: preliminary screening.
In 25% (5/20) of the studies, ML models were used to support (preliminary) screening on longitudinal EHRs [ 29 , 35 , 36 , 42 , 46 ]. After developing ML and DL models, risk classes could be generated as a precursor for physical screening. Approximately 90% of the diagnosed cases were concentrated in the highest (10%) risk class. Other studies assessed the utility of ML and DL models by thresholds for the proportion needed to be screened versus the detection possibility [ 29 , 42 ]. For example, to detect 90% of all validated patients with hepatocellular carcinoma, the highest 66% of risk scores (predicted by a DL model) needed to be screened, whereas to detect 80% of all cases, screening from only the highest 51% of risk scores was required [ 29 ]. Chauhan et al [ 42 ] reasoned the other way around and focused on efficiency. From the 10% highest risk scores for kidney failure, the positive predictive value was 68%. Moreover, the cost benefits for screening options using DL on EHRs were investigated [ 35 ]. Disease detection using a DL model was associated with a positive net benefit–to–cost benefit ratio for a single-point risk assessment (1:3) and continuous-time risk assessment (1:16). Reasons for preliminary screening in EHRs were to prioritize those with the highest risk for disciplines with long waiting lists [ 29 , 42 ], before costly or more invasive examinations (eg, image or biomechanical retrieval) [ 35 , 41 ], or to detect cases that might be missed by the current pathway and go undetected [ 35 , 36 , 46 ].
Only 10% (2/20) of the included studies were validated using an external data set, but none of the models have been implemented in clinical practice (yet). Consequently, the benefits for health were not evaluated. However, the authors interpreted their findings and suggested opportunities and possible health care benefits for clinical practice. The authors of 35% (7/20) of the studies mentioned that, if their models were applied in clinical practice, this may improve personalized health care [ 34 - 36 , 42 , 45 - 47 ]. Personalized health care was related to a personalized risk prediction, an individual-level index or output, a tailored care plan, and targeted care and screening. The authors of 60% (12/20) of the studies claimed that prevention could be improved by using their ML and DL models [ 31 - 38 , 42 , 44 , 45 , 47 ]. Early and timely detection and interventions before disease manifestation were often mentioned. In one case, the use of DL on EHRs could not directly prevent the targeted outcome, but by better preparing health care in an appropriate setting, indirect health outcomes could be prevented [ 44 ]. Additional suggestions to improve health care were focused on policies. It was suggested to base health policies on risk classes at a nationwide level [ 39 , 42 ]. Moreover, (predicted) future health conditions may be a better base for health care policies than traditional surveillance models reflecting health conditions from years before [ 47 ]. In addition to this, DL support can reduce the clinical workload. Even if the positive predictive value to select a screening population is low, a model with an excellent sensitivity can reduce the clinician’s workload by 70% [ 44 ]. All studies assumed EHR data to be valuable information to improve health care. The author of one study suggested that even imperfect data can be used as a silver standard to develop risk models [ 36 ].
The first research question in this study sought to determine which diseases have been detected in longitudinal EHRs using ML techniques. Results showed that a variety of diseases could be detected or predicted, particularly diabetes; kidney diseases; diseases of the circulatory system; and mental, behavioral, and neurodevelopmental disorders [ 22 ]. Comparing our findings with those of prior work, only a third of EHR prediction models predict diseases; meanwhile, mortality and hospitalization remain the most prevalent outcomes [ 51 ]. Among the studies that have predicted diseases, cancer is the most frequently predicted disease based on EHRs. Another systematic review used clinical notes to identify chronic diseases [ 52 ]. It also found diseases of the circulatory system as the most prevalent and explained this by the structure of the data. Not only the structure but also the length of the EHR horizon before diagnosis may explain the diseases that can be detected or predicted. As we determined the scope of diseases that may be prevented, the length of historic data before the diagnosis (in existence of early signs) reflects the “preventive stage” before the onset of the disease. The literature confirms that the longest EHR time horizon (8-10 years) has been found for diabetes and cardiovascular and kidney diseases [ 51 ], which were also prevalent diseases in our scoping review. In the end, the diseases that can be detected rely on available EHR data and, therefore, previous medical visits.
The second research question determined the scope of what EHR data have been used by ML techniques for the early detection and prevention of diseases. This scoping review found that age, sex, BMI, symptoms, procedures, laboratory test results, diagnoses, medications, and clinical notes are frequently used. Diseases that could be detected earlier than when they are currently diagnosed did not use other EHR variables. In addition, the most important predictors found in multiple studies were age, blood pressure, BMI, cholesterol, smoking, and medication. The consistency in the used and most important EHR variables underlines the importance of establishing generalized regulation and standardization of these variables across electronic health software, especially for variables overlapping in various health disciplines [ 53 ]. This would also address well-known challenges and limitations with EHR data, which will be discussed later in this section. According to the literature on the use of EHR data, it seems that a larger variable set improves disease prediction [ 51 ]. Their systematic review concluded that studies must leverage the full breadth of EHR data by using longitudinal data. In addition, we found that large longitudinal EHR data can successfully be analyzed via RNN and, derived from it, LSTM. These are both neural network architectures that are able to find patterns while incorporating temporality, making them effective for time-series predictions. Other types of neural networks (eg, convolutional neural networks) are well-known for their performance on images [ 15 ]. Similar results for techniques were identified in a review on the same topic from a technical perspective [ 2 ]. They concluded that RNN (specifically LSTM) was the most prominent technique to capture complex time-varying EHRs. Another review on AI techniques to facilitate earlier diagnoses of cancer also stated that neural networks were the dominant technique applied to EHRs [ 54 ]. Our results showed that there was no consistent way to process EHR variables temporally when techniques other than LSTM and RNN were used. Therefore, we can conclude that a basic RNN and LSTM are the most suitable techniques to analyze multivariable, longitudinal EHRs.
The third research question of this review was to determine the scope of medical insights that could be generated. Our results showed that, with the development and training of ML and DL models on EHRs, (1) a high diagnostic accuracy was reached, (2) the most responsible predictors could be identified, (3) diseases could be detected earlier than when they are currently diagnosed, and (4) additional health care indicators were created. The most prominent medical insight was the detection performance of the models. However, how good the performance should be is ambiguous. For example, DL models used to facilitate earlier cancer diagnoses had AUROC values ranging from 0.55 to 0.99 [ 54 ], indicating performance from almost random guessing to near-perfect detection. Looking into a more mature domain, the diagnostic accuracy of sepsis predictions ranged from between 0.68 and 0.99 in the intensive care unit to between 0.96 and 0.98 in hospital and between 0.87 and 0.97 in the emergency department [ 55 ]. This metric is ideally as high as possible because it induces a high sensitivity (true positives) and specificity (true negatives). For comparison, the diagnostic accuracy of a gut feeling (meta-analysis on cancer diagnosis) had a sensitivity of only 0.40 and a specificity of 0.85 [ 56 ]. The diagnostic accuracy of physical examination (for the detection of cirrhosis) had a sensitivity between 0.15 and 0.68 and a specificity between 0.75 and 0.98 [ 57 ]. If ML can increase both the sensitivity and specificity of disease detection, nonhealthy persons can be found, and delayed diagnoses can be reduced without overtreating healthy persons misdiagnosed as cases [ 58 ]. If the developed model is further evaluated in false-negative and false-positive groups, it may be possible that the model detects even more (true) cases than those registered by clinicians. This is already the case for many DL techniques on imaging data [ 59 ]. For now, an even more important finding is the ability of some models to detect disease manifestation earlier than the moment of diagnosis registration in EHRs. These examples of earlier detection are aligned with a study on the onset of diseases [ 60 ] that concluded that “slowly progressive diseases are often misperceived as relatively new” (ie, the onset could have been detected earlier). They found that, in 31% of diagnosed cases, the onset of their disease had started >1 year before their diagnosis. When disease predictions are early and accurate enough, it can facilitate disease prevention [ 23 ]. Especially with the addition of personally responsible factors and the biggest changers in risk prediction, prevention interventions may be more effective because they are more targeted to the individual. When medical prevention and interventions become based on the unique profile of each individual, personalized health care is delivered [ 61 ]. After all, the aforementioned medical insights only show the bright side of ML and DL models.
Our final research question sought the (possible) clinical benefits that could be obtained from using ML on EHRs. We found that preliminary screening was a clinical benefit of applying such models on longitudinal EHRs. Patients were accurately classified into risk classes to prioritize those with the highest risk, and a positive net benefit was found. In addition, the authors of the studies stated that their results (although they were not clinically evaluated) may contribute to a more personalized health care, prevention possibilities, and health care policies and reduce the clinicians’ workload. These benefits are perfectly aligned with the near-future vision, strategies, and action foci set by the World Health Organization [ 62 , 63 ]. In particular, the emerging clinical staff shortage makes the future health care system more dependent on technical innovations and the health care system will be forced to be digitally assisted [ 64 ]. However, to be adopted in medical practice, ML and DL models require external validation, the absence of bias and drift, and transparency for clinicians. In prior work, benefits have rarely been clinically evaluated either. Even in a more mature health domain regarding ML, the intensive care unit, only 2% of the AI applications are clinically evaluated [ 65 ]. In their systematic review, the clinical readiness of AI was explored, but no AI model was found to be integrated into routine clinical practice at the time of writing. The limited amount of publications evaluating the clinical benefits of the application of ML on EHRs indicates the research gap in the literature. Future studies should explore the follow-up of these AI attempts and the reasons for success or failure in practice.
Up until now, we have only discussed possible beneficial results of using ML and DL on EHRs. However, we cannot ignore the possible risks, obstacles, challenges, or issues. Multiple (systematic) reviews have summarized these well-known issues, challenges, and limitations regarding the application of ML and DL on EHRs [ 2 , 51 , 66 , 67 ]. Viewed generally across all studies, practical obstacles influence the scientific and clinical implementation process: ethical considerations, privacy guidelines, legal procedures, equity, and data protection and security [ 68 ]. Beyond these obstacles, existing predictions face limitations due to their reliance on the data. First, key issues of using EHRs are irregularity, heterogeneity, sparsity (eg, missing data), temporality, the lack of gold-standard labels, and the volume and quality of data [ 2 , 51 , 66 , 67 ]. Second, ML and DL models have limited transparency and interpretability, face domain complexity (vs engineering expertise), may include biases, and often lack external validation. It is not possible to assign specific issues to specific studies; they all suffer more or less from the aforementioned issues. Our point is to become aware of the downside as well. Therefore, all our principal findings must be interpreted with this last discussion point in mind. In our opinion, a consistent, reliable, and valid way of EHR registration will improve the (use of) data and could be the first step toward a data-based health care system. This need for movement and improvement is important not only for research but also for practical convenience for clinicians and, consequently, to succeed in improving health outcomes.
A limitation of this scoping review is the time between the search and the publication. As ML and DL have become a popular topic and the amount of research has grown drastically over the last years, new research could have been published between the literature search and the publishing of this scoping review. Consequently, some of our findings may have been overtaken by the progress in research.
Another limitation was the data synthesis regarding the performance outcomes per technique. Due to a wide variety of internal analyses, outcomes were not directly comparable, and therefore, the data extraction and data synthesis were difficult. Some studies just noted the optimal performance value achieved by the central model, while other studies compared a variety of techniques and noted various performance values for different subgroups, different metrics, and different time windows and with the addition of various technical improvements. A few authors discussed their ultimate results and mentioned that their model was better than literature, that is, “traditional” or “conventional,” attempts, which were not always clearly defined. We have attempted to follow the authors’ description to avoid incorrect comparisons. However, some comparisons may have become vague or skewed during data synthesis. Nevertheless, we scoped the optimal AUROC for each study at the meta level.
As we used a broad definition of EHR, we included a greater range of data. This means that the results are not based solely on data directly extracted from clinical record systems but also on data extracted by an intermediate organization, such as insurance companies. Therefore, readers must interpret the results of ML and DL models with this in mind.
Longitudinal EHRs have valuable potential to support the early detection of a variety of diseases. For various diseases, EHR data concerning diagnoses, procedures, vital signs, medication, laboratory tests, BMI, and (early) symptoms have a high predictive value. To analyze multivariable, longitudinal EHRs, a basic RNN and LSTM are the most suitable techniques. For the detection of diseases, using ML (including DL) on EHRs proved to be highly accurate. When the detection occurs at the same moment as the diagnosis of clinicians, it seems not directly relevant for the prevention of diseases. However, the detection of diseases offers the clinical benefits of preliminary screening to prioritize patients from the highest risk class. The prevention of diseases can be supported by ML models that are able to predict or detect diseases earlier than the current clinical practice. The additional information about the most important predictors of the individual and the biggest risk changers allow targeted prevention interventions and, therefore, personalized care. Improved health care policies and workload reduction are frequently cited benefits but have not yet been evaluated in clinical practice. Both ML and DL attempts for disease detection and prevention still remain in the testing and prototyping phase and have a long way to go to be clinically applied.
The first author conducted this study as part of her PhD trajectory. Her PhD trajectory was funded by the Centre of Expertise Prevention in Care and Wellbeing from Inholland University of Applied Sciences. JS acknowledges financial support from Regieorgaan SIA RAAK, part of the Netherlands Organisation for Scientific Research (grant HBOPD.2018.05.016). The remaining authors declare no other external sources of funding for this scoping review.
All the authors made substantial contributions to the conception and design, acquisition of data, or analysis and interpretation of data. LS and FCB screened, extracted, analyzed, and interpreted the data. KAZ designed the search strategy and ran, exported, and deduplicated the search results. All authors revised the paper critically and have granted final approval for the version to be published.
None declared.
Search strategy.
Data extraction instrument.
Electronic health record data and applied techniques.
PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist.
artificial intelligence |
area under the receiver operating characteristic curve |
deep learning |
electronic health record |
long short-term memory |
machine learning |
Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews |
recurrent neural network |
Edited by T de Azevedo Cardoso, S Ma; submitted 19.04.23; peer-reviewed by J Zeng, V Rajan, D Chrimes; comments to author 11.07.23; revised version received 29.09.23; accepted 29.04.24; published 20.08.24.
©Laura Swinckels, Frank C Bennis, Kirsten A Ziesemer, Janneke F M Scheerman, Harmen Bijwaard, Ander de Keijzer, Josef Jan Bruers. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 20.08.2024.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research (ISSN 1438-8871), is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included.
Development of a finite element model for prediction of cutting forces in turning of aisi 1040, user preference based network selection management in a heterogeneous network, integration of global navigation satellite system and ultra-wide band for improvement of outdoor robot positioning range and precision, contribution of climate variability and land use change to streamflow variations in thika dam watershed, information.
Published by: Jomo Kenyatta University of Agriculture & Technology
Advertisement
Cancer Discov 2024;XX:1–13
Ju-Fang Chang , Jack H. Landmann , Tien-Ching Chang , Mehmet Emrah Selli , Yangdon Tenzin , John M. Warrington , Julie Ritchey , Yu-Sung Hsu , Michael Slade , Deepesh Kumar Gupta , John F. DiPersio , Alex S. Holehouse , Nathan Singh; Rational Protein Engineering to Enhance MHC-Independent T-cell Receptors. Cancer Discov 2024; https://doi.org/10.1158/2159-8290.CD-23-1393
Download citation file:
Chimeric antigen receptor (CAR)–based therapies have pioneered synthetic cellular immunity but remain limited in their long-term efficacy. Emerging data suggest that dysregulated CAR-driven T-cell activation causes T-cell dysfunction and therapeutic failure. To re-engage the precision of the endogenous T-cell response, we designed MHC-independent T-cell receptors (miTCR) by linking antibody variable domains to T-cell receptor constant chains. Using predictive modeling, we observed that this standard “cut and paste” approach to synthetic protein design resulted in myriad biochemical conflicts at the hybrid variable–constant domain interface. Through iterative modeling and sequence modifications, we developed structure-enhanced miTCRs which significantly improved receptor-driven T-cell function across multiple tumor models. We found that 41BB costimulation specifically prolonged miTCR T-cell persistence and enabled improved leukemic control in vivo compared with classic CAR T cells. Collectively, we have identified core features of hybrid receptor structure responsible for regulating function.
Significance: Improving the durability of engineered T-cell immunotherapies is critical to enhancing efficacy. We used a structure-informed design to evolve improved miTCR function across several models. This work underscores the central role of synthetic receptor structure in T-cell function and provides a framework for improved receptor engineering.
Citing articles via, email alerts.
Sign In or Create an Account
Volume 17, Issue 4
First findings on the dietary pattern of the eastern water bat myotis petax (hollister, 1812) feeding near lake baikal (using coproscopy data).
Rights and permissions
Editorial policies
© Pleiades Publishing, Ltd.
IMAGES
COMMENTS
Journal of Engineering Research (JER) is an international, peer reviewed journal which publishes full length original research papers, reviews and case studies related to all areas of Engineering such as: Civil, Mechanical, Industrial, Electrical, Computer, Chemical, Petroleum, Aerospace, Architectural, etc. JER is intended to serve a wide range of educationists, scientists, specialists ...
The Engineering Research Journal was established in 1985 by the Faculty of Engineering-Mataria-Helwan University. It is a Journal devoted to the publication of Research and scientific papers in all fields of Engineering related subjects in both English and Arabic languages. Articles are refereed before publication.
Engineering Research Express. ISSN: 2631-8695. SUPPORTS OPEN ACCESS. Engineering Research Express (ERX) is a broad, multidisciplinary journal devoted to publishing new experimental and theoretical research covering topics extending across all areas of engineering science including interdisciplinary fields.
Read the latest articles of Journal of Engineering Research at ScienceDirect.com, Elsevier's leading platform of peer-reviewed scholarly literature.
Effects of variations in speed and cutting blade projection on performance and conformity of slice thickness to the adjustment of the cutting blade projection of motorised cassava slicer. Kodwo A. Budu, Emmanuel Y.H. Bobobee, Kojo A. Aikins, Albert K. Arkoh. In Press, Corrected Proof, Available online 19 July 2024.
Sage publishes over 50 engineering journals. The collection includes the 18 journals of the Institution for Mechanical Engineers as well other research in robotics, computing and textiles. The collection also features the leading open access journal in its field, Advances in Mechanical Engineering. Download new special issues, collections, and ...
Overview. Engineering Research / Forschung im Ingenieurwesen publishes current research across all disciplines of engineering and technology. Provides an interdisciplinary overview of engineering science. Encourages exchange of ideas between research and development. Submissions are subject to regular peer review by independent experts.
International Scientific Journal & Country Ranking. SCImago Institutions Rankings SCImago Media Rankings SCImago Iber SCImago Research Centers Ranking SCImago Graphica Ediciones Profesionales de la Información
Journal of Engineering Research (JER) is an international, peer reviewed journal which publishes full length original research papers, reviews, case studies related to all areas of Engineering such as: Civil, Mechanical, Industrial, Electrical, Computer, Chemical, Petroleum, Aerospace, Architectural, etc. JER is intended to serve a wide range ...
Engineering Research Journal. Current Issue: Volume 47, Issue 3, July 2024, Pages 325-457 ( (issued on 1/7/2024 in 4 Parts: Part (1): Electrical Engineering, Part (2) Mechanical Engineering, Part (3): Civil Engineering, Part (4): Architectural Engineering.)
Building Services Engineering Research & Technology is one of the foremost, international peer reviewed journals that publishes the highest quality original research relevant to today's Built Environment. Published in conjunction with CIBSE, this impressive journal reports on the latest research providing you with an invaluable guide to recent developments in the field.
One of the oldest and most respected periodicals in the field, the Journal of Structural Engineering has a history of reporting on fundamental knowledge that advances the state-of-the-art and state-of-the-practice in structural engineering. Authors discuss the art and science of structural modeling and design; develop, apply and interpret the results of novel analytical, computational and ...
Engineering Research Journal (DOI: 10.46654/ERJ, ISSN: 2782-8212) is a journal that offers monthly publication of research articles in Engineering discipline. The journal aims to represent and publish research in trending areas of global concern carried out by scholars and practitioners in the relevant fields. These include studies and reviews ...
412.45. Port Said Engineering Research Journal (PSERJ) is an international peer-reviewed open access journal managed and published by the Faculty of Engineering, Port Said University with print ISSN: (1110-6603) and Online ISSN: (2536-9377). The journal aims to be a leading forum for the publication of high-quality research articles and reviews ...
Journal of Engineering Research (JER) is an international, peer reviewed journal which publishes full length original research papers, reviews, case studies related to all areas of Engineering such as: Civil, Mechanical, Industrial, Electrical, Computer, Chemical, Petroleum, Aerospace, Architectural, etc.. JER is intended to serve a wide range of educationists, scientists, specialists ...
About. Global Journals of Research in Engineering welcomes original research papers and articles on traditional and emerging domains of engineering. It is a double-blind, peer reviewed, international journal encouraging studies in fields but not limited to mechanical and automotive engineering, aerospace, robotics, civil engineering and ...
The Journal of Engineering Research (JER) is an international blind peer-reviewed journal published by the Faculty of Engineering, Tanta University. JER publishes four issues of new developments and original contributions in the various Engineering disciplines of Mathematics, Chemistry, Physics, Civil, Geotechnical engineering, Computer Science ...
International Journal of Aerospace Engineering. Volume 2024, Issue 1 1263459. Research Article. Open Access. ... Anhui Undergrowth Crop Intelligent Equipment Engineering Research Center , Lu'an , 237012 , China. Search for more papers by this author. Tan Zhang, Tan Zhang.
The official journal of the Chinese Academy of Engineering and Higher Education Press. Engineering is an international open-access journal that was launched by the Chinese Academy of Engineering (CAE) in 2015. Its aims are to provide a high-level platform where cutting-edge advancements in engineering R&D, current major research outputs, and key achievements can be disseminated and shared; to ...
Explore Elsevier's Mechanical engineering journals and stay up-to-date with the latest research and insights from top authors in the field. Subscribe today ... The journal covers research based on new experimental results or new experimental techniques pertaining to any of the three main research areas or their combination. In addition, the ...
Ionic liquids (ILs) have garnered significant research interest due to their wide-range applications in separation, catalysis, and synthesis. However, the combination of an extensive quantity of diverse anions and cations makes it a grand challenge for traditional methods (theoretical calculations and experiments) to analyze the properties of unexplored ILs. The emerging machine learning (ML ...
High Voltage is an open access power engineering journal publishing original and review articles on high-voltage power engineering and high voltage applications.
Literature Review of Nanotechnology in the Enhanced Oil Recovery. "Journal of Engineering Research", the scientific publication of the College of Engineering of Kuwait University. It is an international, peer-reviewed journal and deals with the latest research and studies in the broad disciplinary streams of Scienc.
Training future engineers, who will need to solve professional problems with the aid of modern technology and with an eye toward the country's innovation-focused path to development is a major comp...
Abstract The article examines the influence of structural, institutional, and spatial factors on business performance in Novosibirsk oblast, Russia, based on information about enterprises in the region for 2019-2020 available in the SPARK-Interfax database. An empirical analysis was carried out using regression models; an approach based on an extended production function was used, within ...
From 1986 to 1997 the Director of the Institute of Thermophysics was academician V.E. Nakoryakov, a famous scientist in the field of thermophysics, mechanics and power engineering. From 1997 the Director of the Institute is Corresponding Member of RAS S.V. Alekseenko. About 450 employees work at the Institute.
Although ML has become well developed, studies mainly focus on engineering but lack medical outcomes. Objective: This study aims for a scoping review of the evidence on how the use of ML on longitudinal EHRs can support the early detection and prevention of disease. ... Journal of Medical Internet Research 8622 articles JMIR Research Protocols ...
Vol. 8 No. 2 (2024): JOURNAL OF SUSTAINABLE RESEARCH IN ENGINEERING Vol. 8 No. 2 (2024): JOURNAL OF SUSTAINABLE RESEARCH IN ENGINEERING Published: 2024-08-19 Articles Development of a finite element model for prediction of cutting forces in turning of AISI 1040 Rodgers Nyamweya Bosire, Onesmus Mutuku Muvengei, James Mutua, James Kuria Kimotho ...
Abstract. Chimeric antigen receptor (CAR)-based therapies have pioneered synthetic cellular immunity but remain limited in their long-term efficacy. Emerging data suggest that dysregulated CAR-driven T-cell activation causes T-cell dysfunction and therapeutic failure. To re-engage the precision of the endogenous T-cell response, we designed MHC-independent T-cell receptors (miTCR) by linking ...
Contemporary Problems of Ecology is a multidisciplinary peer-reviewed journal focusing on various aspects of modern environmental science. Covers theoretical and methodical issues, regional aspects, ecological disasters, ecosystems, and anthropogenic transformations of ecosystems. Features articles related to global changes in biodiversity at ...