Lean Model Research Articles

Computational analysis of the functional impact of MHC-II-expressing triple-negative breast cancer.

The tumor microenvironment (TME) plays a crucial role in tumor progression and immunoregulation. Major histocompatibility complex class II (MHC-II) is essential for immune surveillance within the TME. While MHC-II genes are typically expressed by professional antigen-presenting cells, they are also expressed in tumor cells, potentially facilitating antitumor immune responses. To understand the role of MHC-II-expressing tumor cells, we analyzed triple-negative breast cancer (TNBC), an aggressive subtype with poor prognosis and limited treatment options, using public bulk RNA-seq, single-cell RNA-seq, and spatial transcriptomics datasets. Our analysis revealed a distinct tumor subpopulation that upregulates MHC-II genes and actively interacts with immune cells. We implicated that this subpopulation is preferentially present in proximity to regions in immune infiltration of TNBC patient cohorts with a better prognosis, suggesting the functional importance of MHC-II-expressing tumor cells in modulating the immune landscape and influencing patient survival outcomes. Remarkably, we identified a prognostic signature comprising 40 significant genes in the MHC-II-expressing tumors in which machine leaning models with the signature successfully predicted patient survival outcomes and the degree of immune infiltration. This study advances our understanding of the immunological basis of cancer progression and suggests promising new directions for therapeutic strategies.

Research on Lean Construction Management Mode of EPC Project Based on BIM

In view of the low production efficiency, backward information level and rough project management of the traditional construction industry, it is necessary to introduce a construction model that can efficiently achieve the project construction goals. Taking EPC projects as the research object, building information modeling (BIM) as the technical means, and lean construction (LC) as the management model, this paper constructs a lean construction management model for EPC projects based on BIM, the "BIM-LC" model. From the perspective of the general contractor, the lean construction implementation mechanism of EPC projects using BIM technology is proposed, and the research is combined with EPC project examples. The results show that through the practical application of this model, the characteristics of BIM technology and lean construction refined management can be brought into play, the EPC project management process can be simplified, and the efficiency of project management can be improved.

Automatic classification of fungal-fungal interactions using deep leaning models

Fungi provide valuable solutions for diverse biotechnological applications, such as enzymes in the food industry, bioactive metabolites for healthcare, and biocontrol organisms in agriculture. Current workflows for identifying new biocontrol fungi often rely on subjective visual observations of strains’ performance in microbe-microbe interaction studies, making the process time-consuming and difficult to reproduce. To overcome these challenges, we developed an AI-automated image classification approach using machine learning algorithm based on deep neural network. Our method focuses on analyzing standardized images of 96-well microtiter plates with solid medium for fungal-fungal challenge experiments. We used our model to categorize the outcome of interactions between the plant pathogen Fusarium graminearum and individual isolates from a collection of 38,400 fungal strains. The authors trained multiple deep learning architectures and evaluated their performance. The results strongly support our approach, achieving a peak accuracy of 95.0 % with the DenseNet121 model and a maximum macro-averaged F1-Score of 93.1 across five folds. To the best of our knowledge, this paper introduces the first automated method for classifying fungal–fungal interactions using deep learning, which can easily be adapted for other fungal species.

Artificial intelligence derived electrocardiograms: a comparative study of network architectures predicting sex and left ventricular dysfunction

Abstract Background Within cardiovascular medicine, AI-driven electrocardiogram (ECG) analysis has emerged as a powerful tool, capable of predicting clinically significant abnormalities. The increasing growth of wearable technologies for ECG monitoring underscores the importance of advancing AI methodologies. While Convolutional Neural Networks (CNNs) have traditionally been the go-to choice for ECG analysis, the rise of Vision Transformers (ViTs), a novel computer vision paradigm, raises the question of their potential superiority. Purpose To compare the performance of CNNs and ViTs in ECG analysis, and to assess the efficiency of lean models using truncated ECG recordings. Methods We trained a model using 12-lead ECGs as input for the binary classification of two outputs: Sex (Male or Female) and Left ventricular dysfunction (LVD, defined as below 35%), determined by echocardiography within 2 weeks of the ECG. Models were developed using full standard ECGs, single lead and truncated recordings (1,2 and 4 10 seconds). We compared CNNs (PyTorch) and ViTs (HuggingFace) performance. We analyzed the explainability of our findings, representing the AI model's focus of interest on ECGs from normal cases versus those with reduced ejection fraction, thereby validating its diagnostic discernment (Fig 1) Results We identified 150,691 and 29,422 patients with valid ECG tests for the Sex and LVD prediction models, respectively. For the Sex outcome, the AUROCs were 0.911 (95% CI: 0.908-0.914) and 0.898 (95% CI: 0.894-0.901) for the CNN-based model and the ViT-based models, respectively, with the difference statistically significant (P-Value < 0.001). For the LVD outcome, the AUROCs were comparable at 0.878 (95% CI: 0.864-0.892) and 0.866 (95% CI: 0.853-0.879) for the CNN-based model and the ViT-based models, respectively, (P-Value = 0.056). Furthermore, we found that 98.8% for the maximal predictive power of the models was achieved within a 2 second time frame of a 12 lead ECG. Similarly, a single lead based model achieved a relatively high AUC for the prediction of LVD. Conclusions AI-ECG models developed with ViT architecture did not surpass CNN-based models in sex classification and LVD identification. Our study highlights the significance of lean models allowing for rapid prediction within 2-second tracings or using a single lead, demonstrates the potential for streamlined AI-ECG applications in clinical practice.

Lean metabolic dysfunction-associated steatotic disease is reversed by betulinic acid, a therapeutic triterpene from birch bark

The prevalence of metabolic dysfunction-associated steatotic disease (MASLD) in lean individuals has continued to increase. Despite the benefits of betulinic acid in obesity, its role in lean MASLD has not been verified. We investigated whether betulinic acid recovered lean MASLD by rescuing lipid homeostasis in vivo. Lean MASLD disease mice model was established using atherogenic diets on C57BL/6 male mice. Betulinic acid (5, 15, and 25 mg/kg bw) or positive control was provided ad libitum for 12 weeks. Betulinic acid reduced body adiposity (p < 0.01) without affecting lean mass. Betulinic acid improved hepatic lipid accumulation (p < 0.01). Blood lipid profiles, including triglyceride, total cholesterol, LDL-cholesterol, and non-esterified fatty acids (p < 0.001 and p < 0.05), were decreased by betulinic acid. RNA transcriptomes and immunoblotting revealed that betulinic acid markedly reduced hepatic de novo lipogenesis by inhibiting Srebp1/Acc/Fas (p < 0.05). Betulinic acid increased fatty acid utilization (p < 0.05) in skeletal muscle by stimulating Ampk/Acc1/Cpt1. These findings imply that betulinic acid is a potent bioactive compound that prevents lean MASLD and dyslipidemia.

Patient-centered lean healthcare management from a humanistic perspective

BackgroundHealthcare organizations are under pressure to improve services because of an aging population and increasing healthcare demands. Lean healthcare management focuses on improving service quality and efficiency under the condition of limited resources, but it may overlook patients’ emotional needs and experiences, especially in developing countries. This study advocates integrating medical humanities with lean healthcare to develop a patient-centered service model.MethodsThe study employs literature review to discuss the critical role of medical humanities in lean healthcare frameworks, both theoretical and practical. Additionally, it conducts a qualitative study through semi-structured interviews to explore strategies for developing a humanistic lean healthcare model. The study conducts semi - structured interviews with eight management staff members and doctors in a tertiary hospital in China that actively adopts this approach.ResultsEight managers and doctors (five female and three male) were interviewed between January and March 2024 at their chosen locations. Firstly, the study identifies key benefits of integrating medical humanities into lean healthcare, which are as follows: (1) Enhancing the personalization and comprehensiveness of services. (2) Building trust in doctor-patient relationships. (3) Boosting the satisfaction of healthcare teams. Secondly, it highlights strategies for a humanistic approach, namely: (1) Conducting comprehensive patient assessments and providing personalized treatments. (2) Enhancing doctor - patient communication for emotional resonance. (3) Optimizing the medical environment for humanized services. (4) Developing humanistic qualities among healthcare professionals. (5) Using information technology effectively. Additionally, the study also addresses potential issues regarding lean healthcare’s focus on profitability and proposes preventive measures: (1) Implementing a scientific evaluation and incentive mechanism. (2) Enhancing transparency and oversight in healthcare. (3) Cultivating a patient - centric medical culture.ConclusionsThis research proposes a patient-centered lean healthcare model integrating medical humanities, providing a novel framework for improving service quality and efficiency while ensuring compassionate care. This management framework can support the reform of public hospitals in China and also serve as a reference for other countries.

Lean Manufacturing and Process Optimization : Enhancing Efficiency in Modern Production

This comprehensive article explores the transformative impact of lean manufacturing and process optimization in modern industrial settings. It delves into these methodologies' principles, tools, and benefits, highlighting their crucial role in enhancing operational efficiency, reducing costs, and improving product quality. The article presents key statistics and case studies, including Japanese automotive manufacturer's benchmark lean manufacturing model, to demonstrate the significant improvements in productivity, quality, and cost-effectiveness achieved through these approaches. It also discusses the implementation strategies for lean and process optimization, emphasizing the importance of leadership commitment, employee training, and technology integration. Integrating Industry 4.0 technologies with lean principles, termed Lean 4.0, is introduced as the next frontier in operational excellence.

Development and validation of machine-learning models for monitoring individual behaviors in group-housed broiler chickens

Animals' individual behavior is commonly monitored by live or video observation by a person. This can be labor intensive and inconsistent. An alternative is the use of machine learning-based computer vision systems. The objectives of this study were to 1) develop and optimize machine learning model frameworks for detecting, tracking and classifying individual behaviors of group-housed broiler chickens in continuous video recordings; and 2) use an independent dataset to evaluate the performance of the developed machine leaning model framework for individual poultry behaviors differentiation. Forty-two video recordings from 4 different pens (total video duration = 1,620 min) were used to develop and train multiple models for detecting and tracking individual birds and classifying 4 behaviors: feeding, drinking, active, and inactive. The optimal model framework was used to continuously analyze an external set of 11 videos (duration = 326 min), and the second-by-second behavior of each individual broiler was extracted for the comparison of human observation. After comparison of model performance, the YOLOv5l, out of 5 detection models, was selected for detecting individual broilers in a pen; the osnet_x0_25_msmt17, out of 4 tracking algorithms, was selected to track each detected bird in continuous frames; and the Gradient Boosting Classifier, out of 12 machine learning classifiers, was selected to classify the 4 behaviors. Most of the models were able to keep previously assigned individual identifications of the chickens in limited amounts of time, but lost the identities throughout an examination period (≥4 min). The final framework was able to accurately predict feeding (accuracy = 0.895) and drinking time (accuracy = 0.9) but subpar for active (accuracy = 0.545) and inactive time (accuracy = 0.505). The algorithms employed by the machine learning models were able to accurately detect feeding and drinking behavior but still need to be improved for maintaining individual identities of the chickens and identifying active and inactive behaviors.

Organization Culture and Lean Implementation: A Study in Micro, Small and Medium Engineering Enterprise

This study investigates the organizational culture and lean readiness using the Organiza tional Culture Assessment Instrument (OCAI) and Lean Culture Assessment Model (LCAM) to implement lean for improving productivity in one of the Indian Micro, Small, and Medium Enterprises (MSMEs). The OCAI study results found that the organization has a family-style corporate culture and horizontal leadership. LCAM results showed that the company’s score on lean readiness is very low. Further, study through interaction with key organizational personnel revealed that the day-to-day operations were cluttered and lacked direction. The diagnostic study helped identify the cultural issues and problems of the company. The imple mentation of lean was undertaken for 15 months, resulting in a reduced workforce and timely delivery of orders. It also generated cash through the liquidation of scraps and non-productive assets. A refreshed culture further led to sustained and improved motivation among staff with a sense of achievement.

An Economic Perspective on the Implementation of Artificial Intelligence in the Restaurant Sector

Technology is evolving and being implemented across nearly every sector of society, including health, nutrition, and sustainability. Specifically, artificial intelligence (AI) has become an essential tool in gastronomy, not only facilitating chefs’ work but also fostering business innovation through cost reduction. However, for a gastronomic business to be profitable, it is crucial to understand its strategic elements. In this study, three groups associated with gastronomy—chefs, entrepreneurs, and gastronomic experts—were surveyed to gather their opinions on the application of artificial intelligence in the restaurant sector in Spain. Additionally, the Business Model Canvas and Lean Model Canvas were developed, specifically adapted for the restaurant sector. These models, as novel approaches, allowed for the identification of key success factors based on the respondents’ experiences, considering that the Business Model Canvas focuses on the market and the company, while the Lean Model Canvas prioritizes the market and the product. This distinction is essential for mitigating the high failure rate in the restaurant industry in Spain. The results from the Canvas models and SWOT analysis have allowed us to understand the participants’ views. They largely see the use of AI in gastronomy as beneficial due to innovation in recipes and cost savings. However, concerns were raised about the potential loss of human touch in dish preparation and increased unemployment due to the automation of some cooking processes. These findings could be highly relevant for future restaurant entrepreneurs.

FP8.10 - Sustainability in Hand Surgery

Abstract Aims Carpal tunnel release surgery (CTR) is a widely performed procedure in the NHS with significant contributions to waste and carbon emissions within surgery. 36,704 CTRs were preformed from 2022-2023 with an average carbon footprint of 12.0 kg CO2e. The aim of this quality improvement project is to reduce the carbon footprint of CTR through a lean and green model, and examine the rates of infection with this model compared to standard practice. Methods Retrospective data was collected for CTRs performed at the Royal Cornwall Hospital between 31/05/2022 and 01/02/2023 for the first audit cycle using standard set up and equipment. The primary outcome was rates of infection post-CTR. The lean and green model included reducing the number of instruments in the handset (36 items to 14 items), use of a smaller drape, and no gown for the procedure. The second cycle will be examining rates of infection following this intervention. Results Out of 100 patients in the first cycle, 1 patient was treated with antibiotics via a General Practitioner telephone consultation. These eco-changes were well received by staff members, with significant waste reduction this far (over 50 gowns and 25 aperture drapes). Data collection for the second cycle is currently underway. Conclusions CTR surgery is a commonly performed procedure with significant contributions to waste and carbon footprint within surgery. Through simple and low-cost changes to current practice we can promote sustainability in surgery and have a lasting positive impact on the environment.

From Traditional to Advanced Models: A Comparative Study between Time Series and Machine Leaning Models in Agriculture

From Traditional to Advanced Models: A Comparative Study between Time Series and Machine Leaning Models in Agriculture

Predicting Patient No-Shows: Situated Machine Learning with Imperfect Data.

Patients who do not show up for scheduled appointments are a considerable cost and concern in healthcare. In this study, we predict patient no-shows for outpatient surgery at the endoscopy ward of a hospital in Denmark. The predictions are made by training machine leaning (ML) models on available data, which have been recorded for purposes other than ML, and by doing situated work in the hospital setting to understand local data practices and fine-tune the models. The best performing model (XGBoost with oversampling) predicts no-shows at sensitivity = 0.97, specificity = 0.66, and accuracy = 0.95. Importantly, the situated work engaged local hospital staff in the design process and led to substantial quantitative improvements in the performance of the models. We consider the results promising but acknowledge that they are from a single ward. To transfer the no-show models to other wards and hospitals, the situated work must be redone.

An integrated Building Information Modelling, Integrated Project Delivery and Lean Construction Maturity Model

ABSTRACT Construction scholars and professionals have recognized the integration of Building Information Modelling (BIM), Integrated Project Delivery (IPD), and Lean Construction (LC) as an effective way to increase collaboration and deliver construction projects. However, construction organizations cannot identify the transitional management steps required to achieve BIM-IPD-LC (BIL) implementation maturity. This paper presents a roadmap, introducing a BIL Maturity Model (MM) through iterative rounds of semi-structured interviews, model validation through a survey, and model implementation. The research defined the maturity characteristics of construction organizations applying BIL across five levels, namely: ad hoc (individual), repeatable (project), defined (organization and project), quantitatively managed (full organization awareness), and optimizing (cross-organization integration) encompassing five major attributes including, ‘Customer Focus’, ‘Culture & People’, ‘Workplace Standardization’, ‘Waste Minimization’, and ‘Continuous improvement’ as well as 23 sub-attributes. The proposed integrated BIL MM will attract and assist industry practitioners and relevant stakeholders in identifying their position in BIL implementation maturity. The identified interdependencies between BIM, IPD, and LC will also serve as the basis for future academic studies respecting the collaboration of these three in an integrated manner.

Geographic information systems adoption model: A partial least square-structural equation modeling analysis approach

The ability of Geographic Information System (GIS) to organize, analyze, visualize and integrate spatial data has been at the top of its primary uses among professional industries. However, considering the extensive adoption of Information System (IS) throughout history for government organizations’ or citizens' disaster response, the implementation of geographical elements is still minimal. Previous GIS models and framework studies, particularly in developing countries, were affected by pandemic pressure, competitiveness pressure, change management, and security factors. Thus, this study aims to develop a model for the successful adoption of GIS using the Technology Acceptance Model (TAM), and De Lone and Mc Lean Information Success Model and analyze the applicability of the existing factors to enhance the performance of Public Sector Organizations (PSOs). From the study, a new conceptual framework was proposed to examine the effects of factors on GIS adoption that impact performance among PSOs from the perspective of Saudi Arabia. Quantitative methods were used to collect data through a questionnaire distributed to 350 respondents from PSO, and only 272 were found to be valid. Partial Least Square Structural Equation Modeling (PLS-SEM) validated the GIS model. The finding revealed that system quality, service quality, change management, competitiveness pressure, perceived ease of use, perceived usefulness, and security factors significantly and positively affected GIS adoption. The study also showed that GIS adoption substantially affected PSO performance. The proposed model provides insight into how GIS adoption can eventually enhance performance among PSOs. In essence, the study contributes to the running of PSO and the decisions taken by policymakers.

Development and validation of a deep learning-based model for diabetes diagnosis

Diabetes is a systemic disease caused by hyperglycemia, and the number of people with diabetes worldwide may reach 1.31 billion by 2050. The traditional diagnosis of early diabetes is difficult and inaccurate. Computer-aided automatic method has been widely applied in diabetes diagnosis at early stage. In order to realize automatic diagnosis of diabetes, this study proposed a deep neural network-based model for diabetes diagnosis, and its performance was compared with those of other classical machine leaning models. After data cleaning, Synthetic Minority Over-sampling Technique (SMOTE) sampling and feature selecting of the diabetes dataset, multiple models were applied to the features such as Body Mass Index (BMI), Age and other features for prediction. The results showed that Deep Neural Network (DNN) is the best diagnostic solution for diabetes with excellent performance with an accuracy of 99.5%. More specific features will be considered to ensure the accuracy and credibility of clinical diagnosis of diabetes.

Integrated serum metabolomics, 16S rRNA sequencing and bile acid profiling to reveal the potential mechanism of gentiopicroside against nonalcoholic steatohepatitis in lean mice

Ethnopharmacological relevanceLean nonalcoholic steatohepatitis (NASH) poses a serious threat to public health worldwide. Herbs of the genus Gentiana have been used for centuries to treat hepatic disease or have been consumed for hepatic protection efficiency. Gentiopicroside (GPS), the main bioactive component of Gentiana herbs, has been shown to be beneficial for protecting the liver, improving intestinal disorders, modulating bile acid profiles, ameliorating alcoholic hepatosteatosis, and so on. It is plausible to speculate that GPS may hold potential as a therapeutic strategy for lean NASH. However, no related studies have been conducted thus far. Aim of the studyThe present work aimed to investigate the benefit of GPS on NASH in a lean mouse model. Materials and methodsNASH in a lean mouse model was successfully established via a published method. GPS of 50 and 100 mg/kg were orally administered to verify the effect. Untargeted metabolomics, 16S rDNA sequencing and bile acid (BA) profiling, as well as qPCR and Western blotting analysis were employed to investigate the mechanism underlying the alleviating effect. ResultsGPS significantly reduced the increase in serum biochemicals and liver index, and attenuated the accumulation of fat in the livers of lean mice with NASH. Forty-two potential biomarkers were identified by metabolomics analysis, leading to abnormal metabolic pathways of primary bile acid biosynthesis and fatty acid biosynthesis, which were subsequently rebalanced by GPS. A decreased Firmicutes/Bacteroidetes (F/B) ratio and disturbed BA related GM profiles were revealed in lean mice with NASH but were partially recovered by GPS. Furthermore, serum profiling of 23 BAs confirmed that serum BA levels were elevated in the lean model but downregulated by GPS treatment. Pearson correlation analysis validated associations between BA profiles, serum biochemical indices and related GM. qPCR and Western blotting analysis further elucidated the regulation of genes associated with liver lipid synthesis and bile acid metabolism. ConclusionsGPS may ameliorate steatosis in lean mice with NASH, regulating the metabolomic profile, BA metabolism, fatty acid biosynthesis, and BA-related GM. All these factors may contribute to its beneficial effect.

Exploring Fibrosis Pathophysiology in Lean and Obese Metabolic-Associated Fatty Liver Disease: An In-Depth Comparison.

While obesity-related nonalcoholic fatty liver disease (NAFLD) is linked with metabolic dysfunctions such as insulin resistance and adipose tissue inflammation, lean NAFLD more often progresses to liver fibrosis even in the absence of metabolic syndrome. This review aims to summarize the current knowledge regarding the mechanisms of liver fibrosis in lean NAFLD. The most commonly used lean NAFLD models include a methionine/choline-deficient (MCD) diet, a high-fat diet with carbon tetrachloride (CCl4), and a high-fructose and high-cholesterol diet. The major pro-fibrogenic mechanisms in lean NAFLD models include increased activation of the extracellular signal-regulated kinase (ERK) pathway, elevated expression of α-smooth muscle actin (α-SMA), collagen type I, and TGF-β, and modulation of fibrogenic markers such as tenascin-X and metalloproteinase inhibitors. Additionally, activation of macrophage signaling pathways promoting hepatic stellate cell (HSC) activation further contributes to fibrosis development. Animal models cannot cover all clinical features that are evident in patients with lean or obese NAFLD, implicating the need for novel models, as well as for deeper comparisons of clinical and experimental studies. Having in mind the prevalence of fibrosis in lean NAFLD patients, by addressing specific pathways, clinical studies can reveal new targeted therapies along with novel biomarkers for early detection and enhancement of clinical management for lean NAFLD patients.

Enhanced deep leaning model for detection and grading of lumbar disc herniation from MRI.

Lumbar disc herniation is one of the most prevalent orthopedic issues in clinical practice. The lumbar spine is a crucial joint for movement and weight-bearing, so back pain can significantly impact the everyday lives of patients and is prone to recurring. The pathogenesis of lumbar disc herniation is complex and diverse, making it difficult to identify and assess after it has occurred. Magnetic resonance imaging (MRI) is the most effective method for detecting injuries, requiring continuous examination by medical experts to determine the extent of the injury. However, the continuous examination process is time-consuming and susceptible to errors. This study proposes an enhanced model, BE-YOLOv5, for hierarchical detection of lumbar disc herniation from MRI images. To tailor the training of the model to the job requirements, a specialized dataset was created. The data was cleaned and improved before the final calibration. A final training set of 2083 data points and a test set of 100 data points were obtained. The YOLOv5 model was enhanced by integrating the attention mechanism module, ECAnet, with a 3 × 3 convolutional kernel size, substituting its feature extraction network with a BiFPN, and implementing structural system pruning. The model achieved an 89.7% mean average precision (mAP) and 48.7 frames per second (FPS) on the test set. In comparison to Faster R-CNN, original YOLOv5, and the latest YOLOv8, this model performs better in terms of both accuracy and speed for the detection and grading of lumbar disc herniation from MRI, validating the effectiveness of multiple enhancement methods. The proposed model is expected to be used for diagnosing lumbar disc herniation from MRI images and to demonstrate efficient and high-precision performance.

Improving Customer Service Efficiency Using Demand Forecasting with Leagile and Lean Six Sigma Concepts: A Case Study

Background and Objectives: The coffee industry is a highly competitive business, especially for coffee shops that provide fresh coffee. Prolonged service times in such establishments can significantly impact activity-based costing. Although previous research has addressed issues related to extended waiting times, there is a gap in understanding how demand forecasting, combined with Leagile and Lean Six Sigma methodologies, can improve service processes in small coffee shops. This study seeks to identify the maximum increase in beverage demand periods through demand forecasting and implement Leagile and Lean Six Sigma strategies to enhance customer service, decrease activity-based costs, and improve overall efficiency. Methodology: The data on product sales throughout the year 2022 during operating hours were collected from January 1st to December 31st. Python and Autoregressive Integrated Moving Average (ARIMA) were employed for sales forecasting to find the maximum increasing period of demand, and the accuracy of predictions was evaluated using metrics such as Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), Mean Absolute Error (MAE). The in-depth interviews were conducted with key informants. The application of Leagile and Lean Six Sigma concepts, with various tools such as service blueprint, process flow chart, activity value analysis, and Cause-and-effect diagram, took place over the period from March 1st to April 31st, 2023 to improve the customer service process. Results: The main findings of the study revealed that peak demand occurred during two specific periods: 07:45-08:00 a.m. and 12:45-01:00 p.m., with increases of 73.2% and 76.8%, respectively. The research identified and addressed five non-value-added activities in the service process which are queuing for ordering, writing down the order on paper, asking for the customer’s name and writing it down on the receipt, folding the tissue paper onto the cup, and choosing the proper straw. Decreasing those processes resulted in a notable 20.71% reduction in lead time (equivalent to 87 seconds per cup). Additionally, four out of five activities (80%) that cause idle time, consist of writing down the order on paper, asking for the customer’s name and writing it down on the receipt, folding the tissue paper onto the cup, and choosing the proper straw, were successfully eliminated. These improvements contributed to an estimated daily reduction of 2,350 baht in activity-based costs, translating to a monthly saving of 61,110 baht. Discussions: Entrepreneurs should consider using demand forecasting to identify peak times of demand, aiming to enhance the efficiency of customer service processes in conjunction with the Leagile and Lean Six Sigma concepts. This involves collecting and analyzing data, identifying the root causes of problems, selecting an appropriate decoupling point to modify the workflow, and utilizing forecast-driven principles in the Lean model. The workflow is then transformed using order-driven principles in the Agile model. Eliminating non-value-added activities is a crucial method to enhance the efficiency of customer service processes, reducing customer waiting times and minimizing unnecessary business activity-based costs. Conclusions: Integrating demand forecasting with Leagile and Lean Six Sigma principles proves beneficial for fresh coffee shops, enhancing operational efficiency and reducing unnecessary activity costs.