Pub Date : 2025-01-10DOI: 10.1016/j.slast.2025.100245
Xiujuan Wen, David G. McLaren
This mini-review provides an overview of recent developments in AEMS supporting hit identification in drug discovery, emphasizing its potential to enhance the quality and efficiency of label-free HTS. Future advancements that may further expand the role of AEMS in the drug discovery process will also be discussed.
{"title":"High-throughput hit identification with acoustic ejection mass spectrometry","authors":"Xiujuan Wen, David G. McLaren","doi":"10.1016/j.slast.2025.100245","DOIUrl":"10.1016/j.slast.2025.100245","url":null,"abstract":"<div><div>This mini-review provides an overview of recent developments in AEMS supporting hit identification in drug discovery, emphasizing its potential to enhance the quality and efficiency of label-free HTS. Future advancements that may further expand the role of AEMS in the drug discovery process will also be discussed.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"31 ","pages":"Article 100245"},"PeriodicalIF":2.5,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142973271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-09DOI: 10.1016/j.slast.2025.100243
Hongli Han
Chronic kidney disease (CKD) significantly increases the risk of CVD diseases, particularly among elderly patients. Understanding the interaction between several biomarkers and cardiovascular (CVD) risks is crucial for improving patient outcomes and tailoring personalized treatment strategies. There is much more to learn about the intricate relationship between biomarkers and CVD risks in elderly CKD patients. Research aims to harness natural language processing (NLP) strategies to investigate the interaction between biomarkers and CVD risks in elderly patients with CKD. This research examined how changes in baseline values of four novel and classic cardiac biomarkers relate to the danger of CVD, and all-cause death in a large cohort of patients with CKD. Initially, medical data were collected from EHR of elderly CKD patients. NLP technique, such as Named Entity Recognition (NER), is used to extract the relevant biomarkers and CVD risk factors from the data. Statistical techniques were applied to examine the associations between biomarkers and CVD risks. The predictive models, using a combination of structured and NLP-extracted features demonstrated improved accuracy in forecasting CVD outcomes compared to traditional methods. This investigation highlights the critical role of specific biomarkers like PTH and FGF-23 in predicting CVD outcomes, providing insights into the possibility of using EHR data for better patient management and enhancing predictive models for this high-risk population.
{"title":"Harnessing NLP to investigate biomarker interactions and CVD risks in elderly chronic kidney disease patients","authors":"Hongli Han","doi":"10.1016/j.slast.2025.100243","DOIUrl":"10.1016/j.slast.2025.100243","url":null,"abstract":"<div><div>Chronic kidney disease (CKD) significantly increases the risk of CVD diseases, particularly among elderly patients. Understanding the interaction between several biomarkers and cardiovascular (CVD) risks is crucial for improving patient outcomes and tailoring personalized treatment strategies. There is much more to learn about the intricate relationship between biomarkers and CVD risks in elderly CKD patients. Research aims to harness natural language processing (NLP) strategies to investigate the interaction between biomarkers and CVD risks in elderly patients with CKD. This research examined how changes in baseline values of four novel and classic cardiac biomarkers relate to the danger of CVD, and all-cause death in a large cohort of patients with CKD. Initially, medical data were collected from EHR of elderly CKD patients. NLP technique, such as Named Entity Recognition (NER), is used to extract the relevant biomarkers and CVD risk factors from the data. Statistical techniques were applied to examine the associations between biomarkers and CVD risks. The predictive models, using a combination of structured and NLP-extracted features demonstrated improved accuracy in forecasting CVD outcomes compared to traditional methods. This investigation highlights the critical role of specific biomarkers like PTH and FGF-23 in predicting CVD outcomes, providing insights into the possibility of using EHR data for better patient management and enhancing predictive models for this high-risk population.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"31 ","pages":"Article 100243"},"PeriodicalIF":2.5,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142973268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-09DOI: 10.1016/j.slast.2025.100246
Jie Ding, Kee Wee Tan, Xiaoyue Chen
Laboratory automation in the biopharmaceutical industry as a rule requires contracted service from highly professional automation solution provider, at times involving the purchase and development of specialized or customized hardware and software, which can be proprietary and expensive. Alternatively, with the availability of open-source software customized for automation, it is possible to automate existing laboratory instruments in a do-it-yourself (DIY), low-cost, and flexible fashion. In this work, we used an open-source scripting language, AutoIt, to integrate an existing microplate imager into an existing automation platform that is already equipped with a 4-axis robotic arm and an automated incubator, to achieve automation of the imaging procedure in our cell line development workflow. Furthermore, optimizations were performed using AutoIt to improve the overall automated imaging process, namely i) incorporating an automated scan profile selection step, ii) setting up automated handling of system errors, and iii) setting up remote handling of system errors. In summary, the use of AutoIt for DIY instrument integration proves to be cost-saving, versatile, and able to enhance the efficiency of automation workflows in the laboratory.
{"title":"Do-it-yourself instrument integration into an existing mammalian cell line development automation platform","authors":"Jie Ding, Kee Wee Tan, Xiaoyue Chen","doi":"10.1016/j.slast.2025.100246","DOIUrl":"10.1016/j.slast.2025.100246","url":null,"abstract":"<div><div>Laboratory automation in the biopharmaceutical industry as a rule requires contracted service from highly professional automation solution provider, at times involving the purchase and development of specialized or customized hardware and software, which can be proprietary and expensive. Alternatively, with the availability of open-source software customized for automation, it is possible to automate existing laboratory instruments in a do-it-yourself (DIY), low-cost, and flexible fashion. In this work, we used an open-source scripting language, AutoIt, to integrate an existing microplate imager into an existing automation platform that is already equipped with a 4-axis robotic arm and an automated incubator, to achieve automation of the imaging procedure in our cell line development workflow. Furthermore, optimizations were performed using AutoIt to improve the overall automated imaging process, namely i) incorporating an automated scan profile selection step, ii) setting up automated handling of system errors, and iii) setting up remote handling of system errors. In summary, the use of AutoIt for DIY instrument integration proves to be cost-saving, versatile, and able to enhance the efficiency of automation workflows in the laboratory.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"31 ","pages":"Article 100246"},"PeriodicalIF":2.5,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142973275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-30DOI: 10.1016/j.slast.2024.100236
Sarah A Alzakari, Asma Aldrees, Muhammad Umer, Lucia Cascone, Nisreen Innab, Imran Ashraf
{"title":"Corrigendum to \"Artificial intelligence-driven predictive framework for early detection of still birth\" [SLAS Technology Volume 29, Issue 6, 100203, December 2024].","authors":"Sarah A Alzakari, Asma Aldrees, Muhammad Umer, Lucia Cascone, Nisreen Innab, Imran Ashraf","doi":"10.1016/j.slast.2024.100236","DOIUrl":"https://doi.org/10.1016/j.slast.2024.100236","url":null,"abstract":"","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":" ","pages":"100236"},"PeriodicalIF":2.5,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-25DOI: 10.1016/j.slast.2024.100241
Santhi Raveendran , Asma Saeed , Mahesh Kumar Reddy Kalikiri , Harshitha Shobha Manjunath , Alia Al Massih , Muna Al Hashmi , Iman Al Azwani , Basirudeen Syed Ahamed Kabeer , Rebecca Mathew , Sara Tomei
Quantitative PCR (qPCR) is a technique commonly employed in laboratories and core facilities. In our previous study, we had shown the possibility to automate steps in a panel-specific gene expression workflow by pairing Mosquito HV with BioMark HD. Here we aimed to automate the full workflow and explore miniaturization capabilities. Each step of the gene expression workflow was scripted on Mosquito HV genomics software. We performed three different automated runs: i. Replicates of a Reference RNA sample (obtained by pooling RNA isolated from 10 healthy individuals) were run on an immunology gene expression panel. We tested the full reaction (FR) and three miniaturization conditions, namely: 1.5x, 2.5x and 5x; the data obtained from the automated FR replicates was compared to the data obtained from the manual processing; ii. Biological RNA samples (isolated from n = 45 individuals) were run as FR and 1.5x on the immunology gene expression panel; iii. Biological RNA samples (isolated from n = 45 individuals) were run as FR and 1.5x on a pregnancy gene expression panel. The expression of each gene was calculated using the 2(-delta Ct) method.
Successful amplification was observed for the reference samples when using FR and 1.5x conditions. The 2.5x condition exhibited suboptimal amplification with a lower success rate while the 5x condition retrieved no amplification. The 2.5x and 5x miniaturization conditions were excluded from further runs. A strong significant positive correlation was observed between the manual and automated workflows for the reference RNA sample, underscoring the robustness of the gene expression assay. The automation of the immunology and pregnancy gene expression panels on the 45 individual samples retrieved a success rate >70 % for both the FR and the 1.5x miniaturization conditions. A significant positive correlation was also observed between the FR and 1.5x miniaturization conditions for both panels.
Our results show that the adoption and the 1.5x miniaturization capabilities of Mosquito HV system for automating the gene expression workflow did not interfere with data quality and reproducibility.
{"title":"Automation and miniaturization of high-throughput qPCR for gene expression profiling","authors":"Santhi Raveendran , Asma Saeed , Mahesh Kumar Reddy Kalikiri , Harshitha Shobha Manjunath , Alia Al Massih , Muna Al Hashmi , Iman Al Azwani , Basirudeen Syed Ahamed Kabeer , Rebecca Mathew , Sara Tomei","doi":"10.1016/j.slast.2024.100241","DOIUrl":"10.1016/j.slast.2024.100241","url":null,"abstract":"<div><div>Quantitative PCR (qPCR) is a technique commonly employed in laboratories and core facilities. In our previous study, we had shown the possibility to automate steps in a panel-specific gene expression workflow by pairing Mosquito HV with BioMark HD. Here we aimed to automate the full workflow and explore miniaturization capabilities. Each step of the gene expression workflow was scripted on Mosquito HV genomics software. We performed three different automated runs: i. Replicates of a Reference RNA sample (obtained by pooling RNA isolated from 10 healthy individuals) were run on an immunology gene expression panel. We tested the full reaction (FR) and three miniaturization conditions, namely: 1.5x, 2.5x and 5x; the data obtained from the automated FR replicates was compared to the data obtained from the manual processing; ii. Biological RNA samples (isolated from <em>n</em> = 45 individuals) were run as FR and 1.5x on the immunology gene expression panel; iii. Biological RNA samples (isolated from <em>n</em> = 45 individuals) were run as FR and 1.5x on a pregnancy gene expression panel. The expression of each gene was calculated using the 2<sup>(-delta Ct)</sup> method.</div><div>Successful amplification was observed for the reference samples when using FR and 1.5x conditions. The 2.5x condition exhibited suboptimal amplification with a lower success rate while the 5x condition retrieved no amplification. The 2.5x and 5x miniaturization conditions were excluded from further runs. A strong significant positive correlation was observed between the manual and automated workflows for the reference RNA sample, underscoring the robustness of the gene expression assay. The automation of the immunology and pregnancy gene expression panels on the 45 individual samples retrieved a success rate >70 % for both the FR and the 1.5x miniaturization conditions. A significant positive correlation was also observed between the FR and 1.5x miniaturization conditions for both panels.</div><div>Our results show that the adoption and the 1.5x miniaturization capabilities of Mosquito HV system for automating the gene expression workflow did not interfere with data quality and reproducibility.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"31 ","pages":"Article 100241"},"PeriodicalIF":2.5,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142899425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-24DOI: 10.1016/j.slast.2024.100238
Nagalakshmi R , Surbhi Bhatia Khan , Ananthoju Vijay kumar , Mahesh T R , Mohammad Alojail , Saurabh Raj Sangwan , Mo Saraee
This study delves into the transformative potential of Machine Learning (ML) and Natural Language Processing (NLP) within the pharmaceutical industry, spotlighting their significant impact on enhancing medical research methodologies and optimizing healthcare service delivery. Utilizing a vast dataset sourced from a well-established online pharmacy, this research employs sophisticated ML algorithms and cutting-edge NLP techniques to critically analyze medical descriptions and optimize recommendation systems for drug prescriptions and patient care management. Key technological integrations include BERT embeddings, which provide nuanced contextual understanding of complex medical texts, and cosine similarity measures coupled with TF-IDF vectorization to significantly enhance the precision and reliability of text-based medical recommendations. By meticulously adjusting the cosine similarity thresholds from 0.2 to 0.5, our tailored models have consistently achieved a remarkable accuracy rate of 97 %, illustrating their effectiveness in predicting suitable medical treatments and interventions. These results not only highlight the revolutionary capabilities of NLP and ML in harnessing data-driven insights for healthcare but also lay a robust groundwork for future advancements in personalized medicine and bespoke treatment pathways. Comprehensive analysis demonstrates the scalability and adaptability of these technologies in real-world healthcare settings, potentially leading to substantial improvements in patient outcomes and operational efficiencies within the healthcare system.
{"title":"Enhancing drug discovery and patient care through advanced analytics with the power of NLP and machine learning in pharmaceutical data interpretation","authors":"Nagalakshmi R , Surbhi Bhatia Khan , Ananthoju Vijay kumar , Mahesh T R , Mohammad Alojail , Saurabh Raj Sangwan , Mo Saraee","doi":"10.1016/j.slast.2024.100238","DOIUrl":"10.1016/j.slast.2024.100238","url":null,"abstract":"<div><div>This study delves into the transformative potential of Machine Learning (ML) and Natural Language Processing (NLP) within the pharmaceutical industry, spotlighting their significant impact on enhancing medical research methodologies and optimizing healthcare service delivery. Utilizing a vast dataset sourced from a well-established online pharmacy, this research employs sophisticated ML algorithms and cutting-edge NLP techniques to critically analyze medical descriptions and optimize recommendation systems for drug prescriptions and patient care management. Key technological integrations include BERT embeddings, which provide nuanced contextual understanding of complex medical texts, and cosine similarity measures coupled with TF-IDF vectorization to significantly enhance the precision and reliability of text-based medical recommendations. By meticulously adjusting the cosine similarity thresholds from 0.2 to 0.5, our tailored models have consistently achieved a remarkable accuracy rate of 97 %, illustrating their effectiveness in predicting suitable medical treatments and interventions. These results not only highlight the revolutionary capabilities of NLP and ML in harnessing data-driven insights for healthcare but also lay a robust groundwork for future advancements in personalized medicine and bespoke treatment pathways. Comprehensive analysis demonstrates the scalability and adaptability of these technologies in real-world healthcare settings, potentially leading to substantial improvements in patient outcomes and operational efficiencies within the healthcare system.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"31 ","pages":"Article 100238"},"PeriodicalIF":2.5,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142899724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.slast.2024.100232
Tove Selvin , Malin Berglund , Anders Åkerström , Marco Zia , Jakob Rudfeldt , Malin Jarvius , Rolf Larsson , Claes R Andersson , Mårten Fryknäs
To facilitate the translation of immunotherapies from bench to bedside, predictive preclinical models are essential. We developed the in vivo immuno-oncology Hollow Fiber Assay (HFA) to bridge the gap between simpler cell-based in vitro assays and more complex mouse models for immuno-oncology drug evaluation. The assay involves co-culturing human cancer cell lines or primary patient-derived cancer cells with human immune cells inside semipermeable hollow fibers. Implanted intraperitoneally in mice, the fibers captured treatment-induced immune cell-mediated cancer cell killing following treatments with aCD3 and/or IL-2, demonstrating the feasibility of the assay. Traditional models require lengthy observation periods to monitor tumor growth and treatment response. The immuno-oncology HFA enables a rapid initial in vivo evaluation of immunological agents on cancer and immune cells of human origin, addressing two of the 3Rs — reduction and refinement — in animal research.
{"title":"Exploratory insights from the immuno-oncology hollow fiber assay: A pilot approach bridging In Vitro and In Vivo models","authors":"Tove Selvin , Malin Berglund , Anders Åkerström , Marco Zia , Jakob Rudfeldt , Malin Jarvius , Rolf Larsson , Claes R Andersson , Mårten Fryknäs","doi":"10.1016/j.slast.2024.100232","DOIUrl":"10.1016/j.slast.2024.100232","url":null,"abstract":"<div><div>To facilitate the translation of immunotherapies from bench to bedside, predictive preclinical models are essential. We developed the in vivo immuno-oncology Hollow Fiber Assay (HFA) to bridge the gap between simpler cell-based in vitro assays and more complex mouse models for immuno-oncology drug evaluation. The assay involves co-culturing human cancer cell lines or primary patient-derived cancer cells with human immune cells inside semipermeable hollow fibers. Implanted intraperitoneally in mice, the fibers captured treatment-induced immune cell-mediated cancer cell killing following treatments with aCD3 and/or IL-2, demonstrating the feasibility of the assay. Traditional models require lengthy observation periods to monitor tumor growth and treatment response. The immuno-oncology HFA enables a rapid initial in vivo evaluation of immunological agents on cancer and immune cells of human origin, addressing two of the 3Rs — reduction and refinement — in animal research.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"29 6","pages":"Article 100232"},"PeriodicalIF":2.5,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142787295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.slast.2024.100233
Buyun Tang, Becky Lam, Stephanie Holley, Martha Torres, Theresa Kuntzweiler, Tatiana Gladysheva, Paul Lang
Pharmaceutical and biotechnology companies are increasingly being challenged to shorten the cycle time between design, make, test, and analyze (DMTA) compounds. Automation of multiplex assays to obtain multiparameter data on the same robotic run is instrumental in reducing cycle time. Consequently, an increasing need in automated systems to streamline laboratory workflows with the goal to expedite assay cycle time and enhance productivity has grown in industrial and academic institutions in the past decades. Herein, we present a customized robotic platform with operational modularity and flexibility, designed to automate entire assay workflows involving multistep reagent dispensing, mixing, lidding/de-lidding, incubation, centrifugation, and final readout steps by linking spinnaker robot with various peripheral instruments. Compared to manual workflows, the system can seamlessly execute processes with high efficiency, evaluated by standard assay validation protocols for robustness and reproducibility. Furthermore, the system can perform multiple, independent protocols in parallel, and has high-throughput capacity. In this publication, we demonstrate that the modular robotic platform can fully automate multiplex assay workflows through ‘one-click-and-run’ solution with tremendous benefits in liberating manual intervention, boosting productivity while producing high-quality data combined with reduced cycle time (>20 %), as well as expanding the capacity for higher throughput.
{"title":"Automation of multiplex biochemical assays to enhance productivity and reduce cycle time using a modular robotic platform","authors":"Buyun Tang, Becky Lam, Stephanie Holley, Martha Torres, Theresa Kuntzweiler, Tatiana Gladysheva, Paul Lang","doi":"10.1016/j.slast.2024.100233","DOIUrl":"10.1016/j.slast.2024.100233","url":null,"abstract":"<div><div>Pharmaceutical and biotechnology companies are increasingly being challenged to shorten the cycle time between design, make, test, and analyze (DMTA) compounds. Automation of multiplex assays to obtain multiparameter data on the same robotic run is instrumental in reducing cycle time. Consequently, an increasing need in automated systems to streamline laboratory workflows with the goal to expedite assay cycle time and enhance productivity has grown in industrial and academic institutions in the past decades. Herein, we present a customized robotic platform with operational modularity and flexibility, designed to automate entire assay workflows involving multistep reagent dispensing, mixing, lidding/de-lidding, incubation, centrifugation, and final readout steps by linking spinnaker robot with various peripheral instruments. Compared to manual workflows, the system can seamlessly execute processes with high efficiency, evaluated by standard assay validation protocols for robustness and reproducibility. Furthermore, the system can perform multiple, independent protocols in parallel, and has high-throughput capacity. In this publication, we demonstrate that the modular robotic platform can fully automate multiplex assay workflows through ‘one-click-and-run’ solution with tremendous benefits in liberating manual intervention, boosting productivity while producing high-quality data combined with reduced cycle time (>20 %), as well as expanding the capacity for higher throughput.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"29 6","pages":"Article 100233"},"PeriodicalIF":2.5,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142786946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.slast.2024.100226
Yi Sun
Dentists often suggest dental implants to replace missing teeth; nevertheless, mechanical issues can develop with these implants, which could lead to prosthesis replacement or repairs. When investigating implant systems' mechanical characteristics and stress distribution, finite element analysis (FEA) is a popular computational tool. In biomechanical investigations, this strategy is widely used. However, traditional FEA methods can be tedious and require expert expertise for accurate simulation and translation of results. To automate and simplify the process of mending oral implant prostheses, the article suggests a new framework called AI-FEA. The three primary parts that make up the suggested AI-FEA framework are 1. An AI-powered model creation module that utilizes data from medical imaging to autonomously construct 3D finite element designs that are unique to each patient. Utilizing deep learning approaches, this module segments and reconstructs three-dimensional geometries from computed tomography (CT) or cone-beam CT data using material properties and boundary conditions. 2. A FEA solver that runs simulations to test the way the implant system handles different loads. This component uses state-of-the-art numerical methods to model the implant and bone interface and determine stress distributions. 3. An AI-based decision support system that takes all that data and recommends the best way to fix the prosthesis. Combining FEA findings with patient-specific variables, this decision support system uses machine learning algorithms educated on an extensive dataset of implant failure instances and repair results to provide the optimal repair strategy. For patients experiencing issues with oral implants, the suggested AI-FEA framework might mean huge time and skill savings in prosthesis repair planning, leading to better, more individualized care.
{"title":"Prosthesis repair of oral implants based on artificial intelligenc`e finite element analysis","authors":"Yi Sun","doi":"10.1016/j.slast.2024.100226","DOIUrl":"10.1016/j.slast.2024.100226","url":null,"abstract":"<div><div>Dentists often suggest dental implants to replace missing teeth; nevertheless, mechanical issues can develop with these implants, which could lead to prosthesis replacement or repairs. When investigating implant systems' mechanical characteristics and stress distribution, finite element analysis (FEA) is a popular computational tool. In biomechanical investigations, this strategy is widely used. However, traditional FEA methods can be tedious and require expert expertise for accurate simulation and translation of results. To automate and simplify the process of mending oral implant prostheses, the article suggests a new framework called AI-FEA. The three primary parts that make up the suggested AI-FEA framework are 1. An AI-powered model creation module that utilizes data from medical imaging to autonomously construct 3D finite element designs that are unique to each patient. Utilizing deep learning approaches, this module segments and reconstructs three-dimensional geometries from computed tomography (CT) or cone-beam CT data using material properties and boundary conditions. 2. A FEA solver that runs simulations to test the way the implant system handles different loads. This component uses state-of-the-art numerical methods to model the implant and bone interface and determine stress distributions. 3. An AI-based decision support system that takes all that data and recommends the best way to fix the prosthesis. Combining FEA findings with patient-specific variables, this decision support system uses machine learning algorithms educated on an extensive dataset of implant failure instances and repair results to provide the optimal repair strategy. For patients experiencing issues with oral implants, the suggested AI-FEA framework might mean huge time and skill savings in prosthesis repair planning, leading to better, more individualized care.</div></div>","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"29 6","pages":"Article 100226"},"PeriodicalIF":2.5,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142787505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-01DOI: 10.1016/j.slast.2024.100234
Meghav Verma , Nate Hoxie , John Janiszewski , Charles Bonney , Matthew D. Hall , Sam Michael , Tom Covey , Jonathan H. Shrimp
{"title":"Notes on AEMS methods development for high throughput experimentation in drug discovery","authors":"Meghav Verma , Nate Hoxie , John Janiszewski , Charles Bonney , Matthew D. Hall , Sam Michael , Tom Covey , Jonathan H. Shrimp","doi":"10.1016/j.slast.2024.100234","DOIUrl":"10.1016/j.slast.2024.100234","url":null,"abstract":"","PeriodicalId":54248,"journal":{"name":"SLAS Technology","volume":"29 6","pages":"Article 100234"},"PeriodicalIF":2.5,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142787248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号