Machine learning virtual SEM metrology and SEM-based OPC model methodology

Machine learning provides a flexible technique to predict the survival of patients who are admitted to hospital as emergency admissions. Mortality prediction is a central component of emergency patient quality of care and this can act as an indicator of severity to determine who needs prioritized care. Machine learning-based models, as opposed to human-crafted severity score systems, allow for much more complex and updateable models to be developed based on a larger set of input data attributes. While various studies of machine learning-based predictive models for predicting inpatient mortality have been carried out there is little literature on performance maintenance of these models. Determining the performance maintenance of these models over time determines how reliably they can be utilized into the future and for how long. The best performing model in this study achieve’s an AUC of 0.86 upon training and is able to maintain a similarly high AUC of 0.845 as of the end of the period of performance maintenance evaluation nine months later. This is the first paper that the authors are aware of to consider and measure relative performance maintenance of machine learning-based models for emergency admission mortality prediction.

Commercial quadrupole mass spectrometer (QMS) residual gas analyzers became available in the late 1960s and have been popular in R&D laboratories, but have found limited use in semiconductor manufacturing. To sample at pressures above 10−5 Torr with ppm sensitivity or better (relative to the total process pressure), differential pumping is usually required. The newly available, small, high-pressure QMS sensors can operate as high as 10–20 mTorr without differential pumping, but provide somewhat lower mass resolution and partial pressure sensitivity than a standard QMS. Applications in semiconductor manufacturing include equipment monitoring, process monitoring, and effluent analysis. Equipment monitoring can include qualification after preventative maintenance, rate-of-rise tests, and leak identification and detection. Usually the burning question is, Why won’t the vacuum chamber pump down? Other uses that are not usually considered include the qualification of replaceable parts: sputter cathodes, electrodes, lamps, shields, etc. In process monitoring, the key question is, Is this process running normally? A manufacturing monitor can be useful simply by providing a comparison between a well-behaved high-yield process and a marginal or failing process. Examples are given for physical vapor deposition (sputtering) processes, chemical vapor deposition, and plasma etching. The effluent from chemical vapor deposition and plasma etch processes can be analyzed to measure the efficiency of process gas utilization or to monitor the efficacy of abatement methods used for the removal of global warming gases.

BackgroundA brief gonadotropin-releasing hormone analogues (GnRHa) stimulation test which solely focused on LH 30-minute post-stimulation was considered to identify girls with central precocious puberty (CPP). However, it was tested using traditional statistical methods. With advanced computer science, we aimed to develop a machine learning-based diagnostic model that processed baseline CPP-related variables and a brief GnRHa stimulation test for CPP diagnosis.MethodsWe recruited girls suspected of precocious puberty and underwent a GnRHa stimulation test at Children Hospital 2, Vietnam, and Cathay General Hospital, Taiwan. Clinical data, bone age measurement, and 30-min post-stimulation blood test were used to build up the predictive model. The candidate model was developed by different machine learning algorithms that were mainly evaluated by sensitivity, specificity, the area under the receiver operator characteristic curve (AUC), and F1-score in internal and external validation data to classify girls as CPP and non-CPP at different time-points (0-min, 30-min, 60-min, and 120-min post-stimulation).ResultsAmong the 614 girls diagnosed with PP, 524 (85.3%) had CPP. The random forest algorithm yielded the highest value of F1-score (0.976), specificity (0.893), positive predicted value (0.987), and relatively high value of AUC (0.972) that contributed to high probability to identify CPP. The performance metrics of the 30-min post-stimulation diagnostic model including sensitivity and specificity surpassed those of the 0-minute model (0-min) and were equivalent to those of the model obtained 60-min and 120-min post-stimulation. Hence, our machine learning-based model helps shorten the stimulation test to 30 minutes after GnRHa injection, in general, it requires 120 minutes for a completed GnRHa stimulation test.ConclusionsWe developed a diagnostic model based on clinical features and a single sample 30-minute post-stimulation to identify CPP in girls that can reduce distress for children caused by multiple blood samplings.

Performance evaluation of machine learning techniques in predicting cumulative absolute velocity

Background: Although transplantation of patch-shaped autologous skeletal muscle-derived cells has been introduced to ischemic cardiomyopathy (ICM) or non-ICM patients, we found responders or non-responders to this treatment exist and how to predict the responsiveness to this treatment is crucial for the improvement of the effectiveness. In this study, we revealed the clinical features associated with the responders using a machine learning based-model, which was discriminated between the responder and the non-responders in this treatment. Methods and Results: We used the retrospective databases of 23 ICM patients and 23 non-ICM patients undergoing autologous myoblast patch transplantation to develop machine learning models to discriminate 3-year VAD free survival. Sixty-nine pre-transplantation clinical futures were selected to train the models. In ICM models, there were 4 VADs or deaths, and in non-ICM models, there were 10 VADs or deaths during the 3-year follow-up periods. Using these databases, we trained multiple machine learning models and evaluated the models with the leave-one-out method. In ICM, k nearest neighbor demonstrated the best performance, showing the accuracy was 95.7%, and the AUC was 0.95. The features associated with 3-year VAD free survival in ICM were NYHA classification, cardiac index, and left ventricular ejection fraction. In non-ICM, k nearest neighbor demonstrated the best performance among the trained classifiers, demonstrating the accuracy was 95.7%, and the AUC was 0.93. The features associated with 3-year VAD free survival in non-ICM were pulmonary capillary wedge pressure, pulmonary vascular resistance, and albumin. Conclusion: We found the features associated with 3-year VAD free survival in autologous myoblast patch transplantation in ICM and non-ICM. Focusing on these features may facilitate optimal candidate selection in ICM and non-ICM for regenerative therapy.

As High Numerical Aperture Extreme Ultraviolet Lithography (0.55NA EUVL) gets ready to step in the integrated circuit manufacturing world, advanced materials and patterning becomes very critical in terms of resolution, roughness, defectivity and process window. Among various combinations of mask absorber materials, mask tones and processes, bright field masks with utilization of negative-tone metal oxide resists (MORs) have emerged as one of the most promising candidates for 0.55NA EUVL patterning. Therefore, in this paper, we investigate the optical proximity correction (OPC) model accuracy of the dry resist process using a bright field low-n attenuated phase-shift mask. The use case is conducted on imec N2 (pitch 28nm) metal design, with wafer exposure performed using the imec NXE:3400 scanner. Thousands of OPC-relevant features are selected, and all the SEM images (both after develop inspection and after etch inspection) are acquired using a HITACHI CDSEM. The capability and accuracy of machine learning-based OPC models for resist (N2R) and etch (N2E) are studied.

In this paper, a Virtual Metrology (VM) model is proposed to predict etch rate which is one of the most important etching profile in etch process. Error Back Propagation (EBP) neural network is used to make the VM for etch rate prediction.

Background Patients classified as high bleeding risk (HBR) undergoing percutaneous coronary intervention (PCI) face a significantly higher incidence of net adverse clinical events (NACE) compared to non-HBR patients. Existing risk assessment models, such as the CRUSADE and TIMI scores, do not adequately address the unique risks faced by the HBR population. There is an urgent need for a precise and comprehensive predictive model tailored to PCI-HBR patients to guide clinical decision-making and improve patient outcomes. Methods This study aimed to develop a machine learning-based predictive model for long-term NACE in PCI-HBR patients. We utilized data from the Prognostic Analysis and an Appropriate Antiplatelet Strategy for Patients with Percutaneous Coronary Intervention and High Bleeding Risk (PPP-PCI) registry database. Feature selection and interpretation were performed using a SHAP (SHapley Additive exPlanations) model based on Recursive Feature Elimination (RFE). Model construction and evaluation were conducted using four algorithms: logistic regression, random forest, gradient boosting, and XGBoost. Results A total of 1512 PCI-HBR patients were included in the study. The XGBoost model demonstrated the highest predictive performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.85. The SHAP model identified 24 significant variables contributing to the prediction of NACE, including clinical parameters, laboratory findings, and echocardiographic data. Conclusions Our machine learning-based model offers a promising tool for predicting long-term NACE in PCI-HBR patients. The model’s high predictive accuracy and interpretability have the potential to enhance clinical decision-making and improve patient care. Further validation in larger, diverse populations is warranted to confirm these findings.SHAP summary plot. AUC plot.

Background: Spontaneous coronary artery dissection (SCAD) remains a poorly understood differential diagnosis of acute coronary syndrome (ACS). We aimed to develop a machine learning-based risk score model to predict in-hospital mortality in patients with SCAD. Methods: The National Inpatient Sample (NIS) 2016-2020 database was used to identify all adult patients (≥18 years of age) with SCAD, identified using ICD-10 code I25.42. Relevant clinical characteristics and outcomes were extracted. The primary endpoint was in-hospital all-cause mortality. The dataset was randomly split into 3 subsets: training, validation, and testing, with a ratio of 0.7, 0.2, and 0.1, respectively. The risk score was generated using R software’s Autoscore package, which is a machine learning-based automatic clinical score generator, and performance was evaluated using the area under receiver-operative characteristics curve (AUC) with 95% confidence intervals (95%CI). Results: Among the 8,260 SCAD patients identified [age 60.9±14.4 years, female 4,708 (57%)], there were 480 (5.8%) primary outcome events. Out of the top 20 covariates seen in the Parsimony plot, we used six for our risk score (0–100): age, comorbidity burden, cardiogenic shock, balloon pump, extracorporeal membrane oxygenation, and race (Figure 1A). The AUC for the derivation and validation cohorts was 0.862 (0.817–0.907) and 0.833 (0.788–0.879), respectively (Figures 1B and 1C). Conclusion: We developed and internally validated a machine learning-based risk score model to predict outcomes in patients with SCAD with a high AUC of 0.833 (0.788–0.879). Risk score models guide decision-making, and future studies are needed for external validation of our findings.

IntroductionInternational guidelines recommend single or hypo-fraction for palliative radiotherapy (PRT). However, due to the inherent difficulty in accurately predicting life expectancy, the customization of end-of-life care for individual patients poses a significant challenge. This study aims to develop a machine learning-based mortality prediction model for PRT tailored to life expectancy.MethodsA retrospective analysis encompassed 318 patients who expired after receiving PRT for advanced cancer from March 2013 to July 2023. Various model algorithms employing 22 variables were used to predict mortality within 30 days from initiation of PRT: extra trees, random forest, light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost). We evaluated each model's performance using accuracy, precision, recall, specificity, and F1 score.ResultsA total of 302 patients were analyzed after excluding those with missing data. The <30-day mortality group had significantly worse Eastern Cooperative Oncology Group (ECOG) status, lower albumin, higher neutrophil‑to‑lymphocyte ratio, and lower lymphocyte count (all p<0.05). No significant multicollinearity was observed. Among all models, LightGBM showed the best performance (accuracy: 0.725, F1-score: 0.720). A minimal variable model (MVM) using the top eight features plus sex achieved comparable performance to the full variable model (FVM), with improved recall and reduced complexity.ConclusionWe developed a machine learning-based mortality prediction model for tailoring PRT to life expectancy. The model identified clinically meaningful predictors that reflect patient condition and tumor burden. The MVM demonstrated a comparable performance to the FVM, suggesting its potential utility as an interpretable and practical clinical decision support tool for individualized end-of-life care planning.

Background: A mechanism to predict graft failure before the actual kidney transplantation occurs is crucial to clinical management of chronic kidney disease patients. Several kidney graft outcome prediction models, developed using machine learning methods, are available in the literature. However, most of those models used small datasets and none of the machine learning-based prediction models available in the medical literature modelled time-to-event (survival) information, but instead used the binary outcome of failure or not. The objective of this study is to develop two separate machine learning-based predictive models to predict graft failure following live and deceased donor kidney transplant, using time-to-event data in a large national dataset from Australia. Methods: The dataset provided by the Australia and New Zealand Dialysis and Transplant Registry will be used for the analysis. This retrospective dataset contains the cohort of patients who underwent a kidney transplant in Australia from January 1 st, 2007, to December 31 st, 2017. This included 3,758 live donor transplants and 7,365 deceased donor transplants. Three machine learning methods (survival tree, random survival forest and survival support vector machine) and one traditional regression method, Cox proportional regression, will be used to develop the two predictive models. The best predictive model will be selected based on the model's performance. Discussion: This protocol describes the development of two separate machine learning-based predictive models to predict graft failure following live and deceased donor kidney transplant, using a large national dataset from Australia. Furthermore, these two models will be the most comprehensive kidney graft failure predictive models that have used survival data to model using machine learning techniques. Thus, these models are expected to provide valuable insight into the complex interactions between graft failure and donor and recipient characteristics.

To propose a machine learning-based method for predicting the trajectories during manual acupuncture manipulation (MAM), aiming to improve the precision and consistency of acupuncture practitioner' operation and provide the real-time suggestions on MAM error correction. Computer vision technology was used to analyze the hand micromotion when holding needle during acupuncture, and provide a three-dimensional coordinate description method of the index finger joints of the holding hand. Focusing on the 4 typical motions of MAM, a machine learning-based MAM trajectory predictive model was designed. By integrating the changes of phalangeal joint angle and hand skeletal information of acupuncture practitioner, the motion trajectory of the index finger joint was predicted accurately. Besides, the roles of machine learning-based MAM trajectory predictive model in the skill transmission of acupuncture manipulation were verified by stratified randomized controlled trial. The performance of MAM trajectory predictive model, based on the long short-term memory network (LSTM), obtained the highest stability and precision, up to 98%. The learning effect was improved when the model applied to the skill transmission of acupuncture manipulation. The machine learning-based MAM predictive model provides acupuncture practitioner with precise action prediction and feedback. It is valuable and significant for the inheritance and error correction of manual operation of acupuncture.

Background and study aims The aim of this study was to develop a machine learning-based model to classify bowel cleansing quality and to test this model in comparison to a pixel analysis model and assessments by four colon capsule endoscopy (CCE) readers.Methods A pixel analysis and a machine learning-based model with four cleanliness classes (unacceptable, poor, fair and good) were developed to classify CCE videos. Cleansing assessments by four CCE readers in 41 videos from a previous study were compared to the results both models yielded in this pilot study.Results The machine learning-based model classified 47 % of the videos in agreement with the averaged classification by CCE readers, as compared to 32 % by the pixel analysis model. A difference of more than one class was detected in 12 % of the videos by the machine learning-based model and in 32 % by the pixel analysis model, as the latter tended to overestimate cleansing quality. A specific analysis of unacceptable videos found that the pixel analysis model classified almost all of them as fair or good, whereas the machine learning-based model identified five out of 11 videos in agreement with at least one CCE reader as unacceptable.Conclusions The machine learning-based model was superior to the pixel analysis in classifying bowel cleansing quality, due to a higher sensitivity to unacceptable and poor cleansing quality. The machine learning-based model can be further improved by coming to a consensus on how to classify cleanliness of a complete CCE video, by means of an expert panel.

In semiconductor manufacturing, accurate measurement of shapes and sizes of fabricated features is required. These measurements are carried out using critical dimension scanning electron microscope (CD-SEM). Positions of edges are often unclear because of charging. Depending on the SEM setup and the pattern under measurement, the effect of charging varies. The influence of measurement conditions can be simulated and optimized. A Monte Carlo electron beam simulation tool was developed, which takes into account electron scattering and charging. CD-SEM imaging of silicon dioxide lines on silicon was studied. In the experiment, changes in the beam voltage were found to result in contrast tone reversal. The same effect was also found in simulations considering charging. The time dependence of contrast variation was studied. A good agreement between simulation and measurement was found. The simulation software proved reliable in predicting SEM images, which makes it an important instrument to optimize settings of electron beam systems.

With the development of offshore wind power industry, the reliability and maintenance of wind turbines have become critical issues. Bolts, as connecting components in key parts of wind turbines, directly affect operational safety through their fatigue life. However, the complex marine environment makes predicting bolt fatigue life particularly challenging. To address this, this paper proposes a machine learning-based prediction model for offshore wind turbine bolt fatigue life. The model collects diverse data from different operational phases of bolts, including loading conditions, environmental factors (wind speed, humidity, salt mist concentration), and material characteristics. Through preprocessing steps such as data cleaning and feature extraction, the quality of collected data is significantly improved to enhance model input validity. By comparing various machine learning algorithms, this paper selected the most effective one for bolt fatigue prediction and established the predictive model. Cross-validation and practical case studies verified the model's performance, demonstrating that the proposed machine learning-based prediction model can accurately forecast bolt fatigue life with acceptable error margins. This model provides valuable insights for optimizing offshore wind turbine O&M, effectively reducing O&M costs while improving operational reliability.