Hierarchical Classification Research Articles

Hybrid Data Augmentation for Enhanced Crack Detection in Building Construction

Quality management in construction projects necessitates early defect detection, traditionally conducted manually by supervisors, resulting in inefficiencies and human errors. Addressing this challenge, research has delved into automating defect detection using computer vision technology, yet progress has been impeded by data limitations. Numerous studies have explored generating virtual images to tackle this issue. However, these endeavors have fallen short in providing image data adaptable to detecting defects amidst evolving on-site construction conditions. This study aims to surmount this obstacle by constructing a hybrid dataset that amalgamates virtual image data with real-world data, thereby enhancing the accuracy of deep learning models. Virtual images and mask images for the model are concurrently generated through a 3D virtual environment and automatic rendering algorithm. Virtual image data are built by employing a developed annotation system to automatically annotate through mask images. This method improved efficiency by automating the process from virtual image creation to annotation. Furthermore, this research has employed a hierarchical classification system in generating virtual image datasets to reflect the different types of defects that can occur. Experimental findings demonstrate that the hybrid datasets enhanced the F1-Score by 4.4%, from 0.4154 to 0.4329, compared to virtual images alone, and by 10%, from 0.4499 to 0.4990, compared to sole reliance on real image augmentation, underscoring its superiority. This investigation contributes to unmanned, automated quality inspection aligning with smart construction management, potentially bolstering productivity in the construction industry.

Hierarchical segmentation of surgical scenes in laparoscopy.

Segmentation of surgical scenes may provide valuable information for real-time guidance and post-operative analysis. However, in some surgical video frames there is unavoidable ambiguity, leading to incorrect predictions of class or missed detections. In this work, we propose a novel method that alleviates this problem by introducing a hierarchy and associated hierarchical inference scheme that allows broad anatomical structures to be predicted when fine-grained structures cannot be reliably distinguished. First, we formulate a multi-label segmentation loss informed by a hierarchy of anatomical classes and then train a network using this. Subsequently, we use a novel leaf-to-root inference scheme ("Hiera-Mix") to determine the trade-off between label confidence and granularity. This method can be applied to any segmentation model. We evaluate our method using a large laparoscopic cholecystectomy dataset with 65,000 labelled frames. We observed an increase in per-structure detection F1 score for the critical structures, when evaluated across their sub-hierarchies, compared to the baseline method: 6.0% for the cystic artery and 2.9% for the cystic duct, driven primarily by increases in precision of 11.3% and 4.7%, respectively. This corresponded to visibly improved segmentation outputs, with better characterisation of the undissected area containing the critical structures and fewer inter-class confusions. For other anatomical classes, which did not stand to benefit from the hierarchy, performance was unimpaired. Our proposed hierarchical approach improves surgical scene segmentation in frames with ambiguity, by more suitably reflecting the model's parsing of the scene. This may be beneficial in applications of surgical scene segmentation, including recent advancements towards computer-assisted intra-operative guidance.

What do Contemporary Publications Report about the Generation of Urban Solid Waste (MSW) and/or Consumption from the Perspective of Chemistry Teaching?

The present study aimed to highlight the research on the topics of urban solid waste generation and consumerism from the perspective of Chemistry teaching between the years 2018 and 2023. To this end, a State-of-the-Art research, according to Romanowski and Ens (2006), in Periódicos Capes database on the aforementioned themes was realized. The methodology used was qualitative. The forms of analysis applied were both mediated by the IRAMuTeQ software and processed by the content analysis of Bardin (2002). In relation to the survey in Periódicos Capes, a textual corpus was obtained with 15 article summaries. Still as results, for textual statistics, the emergence of 82 text segments (ST) was observed, with the use of 65 ST (79.3%) and six classes in the Descending Hierarchical Classification (DHC). This is a satisfactory use and allows us to classify this analysis as consistent and consequently move on to content analysis based on the DHC. The mottos Waste and Generation were the highlights of the similarity analysis, preceded by the mottos Technology, Environmental, Student and Consumerism. In relation to content analysis, two very important categories emerged that communicate well with this object of study. As a consideration, it appears that in the contemporaneity of the last five years, there are strong signs of gaps regarding the use of these themes in the teaching of Chemistry, making it important for researchers to invest more time in the development of the area.

Semantic Hierarchical Classification Applied to Anomaly Detection Using System Logs with a BERT Model

Semantic Hierarchical Classification Applied to Anomaly Detection Using System Logs with a BERT Model

Cross-Temporal Hierarchical Forecast Reconciliation of Natural Gas Demand

Local natural gas distribution companies (LDCs) require accurate demand forecasts across various time periods, geographic regions, and customer class hierarchies. Achieving coherent forecasts across these hierarchies is challenging but crucial for optimal decision making, resource allocation, and operational efficiency. This work introduces a method that structures the gas distribution system into cross-temporal hierarchies to produce accurate and coherent forecasts. We apply our method to a case study involving three operational regions, forecasting at different geographical levels and analyzing both hourly and daily frequencies. Trained on five years of data and tested on one year, our model achieves a 10% reduction in hourly mean absolute scaled error and a 3% reduction in daily mean absolute scaled error.

Hierarchy-Aware and Label Balanced Model for Hierarchical Text Classification

Hierarchical text classification, where labels can be modeled as a hierarchical structure, is a special multi-label text classification sub-task. Current methods mainly improve model performance by modeling label dependencies. The model HGCLR with excellent performance obtains hierarchy-aware text representations through contrastive learning, but the degree of hierarchical awareness is insufficient. To address this problem, a new multi-label negative supervision method is proposed to drive text representations of samples with more different labels farther away. In addition, to tackle the problem of label imbalance in hierarchical text classification, asymmetric loss is employed to compute the classification loss, so that the model focuses on learning from difficult samples and the contributions of positive and negative labels to the loss function tend to be balanced. In summary, based on HGCLR, by adding multi-label negative supervision and replacing the classification loss with asymmetric loss, we propose a hierarchy-aware and label balanced model (HALB) for hierarchical text classification. Experimental results demonstrate that HALB outperforms several classical models for hierarchical text classification. HALB achieves the best results on both Micro-F1 and Macro-F1 and obtains average improvements of 0.51% and 1.28% respectively on four datasets compared with the strongest baseline model HGCLR.

Two-step hierarchical binary classification of cancerous skin lesions using transfer learning and the random forest algorithm

Skin lesion classification plays a crucial role in the early detection and diagnosis of various skin conditions. Recent advances in computer-aided diagnostic techniques have been instrumental in timely intervention, thereby improving patient outcomes, particularly in rural communities lacking specialized expertise. Despite the widespread adoption of convolutional neural networks (CNNs) in skin disease detection, their effectiveness has been hindered by the limited size and data imbalance of publicly accessible skin lesion datasets. In this context, a two-step hierarchical binary classification approach is proposed utilizing hybrid machine and deep learning (DL) techniques. Experiments conducted on the International Skin Imaging Collaboration (ISIC 2017) dataset demonstrate the effectiveness of the hierarchical approach in handling large class imbalances. Specifically, employing DenseNet121 (DNET) as a feature extractor and random forest (RF) as a classifier yielded the most promising results, achieving a balanced multiclass accuracy (BMA) of 91.07% compared to the pure deep-learning model (end-to-end DNET) with a BMA of 88.66%. The RF ensemble exhibited significantly greater efficiency than other machine-learning classifiers in aiding DL to address the challenge of learning with limited data. Furthermore, the implemented predictive hybrid hierarchical model demonstrated enhanced performance while significantly reducing computational time, indicating its potential efficiency in real-world applications for the classification of skin lesions.

A rapid evaluation method of the seismic damage to buildings based on UAV images

With the widespread application of UAVs in post-disaster damage evaluation, feature extraction and analysis based on drone images has become the main trend in seismic assessment. In this research, a fast assessment method that integrates object-oriented 2D classification and 3D assessment is proposed in the paper. Firstly, to segment the regional orthoimage, a multi-scale feature segmentation method is developed to segment the orthoimage of the region and the features are selected based on the attributes of ground objects. Meanwhile, a two-stage object-oriented hierarchical classification method is put forward to establish partition rules at different levels. The classification method takes the overall attributes of the object into account which reduces the amount of data correspondingly resulting in much higher efficiency and accuracy of feature extraction than the pixel-based method. In addition, the integrity of building’s top texture after classification is used as the first criterion to assess building seismic damage. Besides, a 3D elevation analysis method based on regional normalized digital surface model (nDSM) is developed by comparing digital surface model with digital elevation model to serve as the second criterion for determining the vertical changes in building. The proposed method is validated by a field test at the Beichuan earthquake site with an accuracy rate of 86.95 %. The experimental results show that the proposed method can meet the accuracy requirement of seismic assessment and has a high application value in the field of regional disaster evaluation.

A Pipeline Intrusion Detection Method Based on Temporal Modeling and Hierarchical Classification in Optical Fiber Sensing

A Pipeline Intrusion Detection Method Based on Temporal Modeling and Hierarchical Classification in Optical Fiber Sensing

Identification and Discrimination of Petrol Sources by Nuclear Magnetic Resonance Spectroscopy and Machine Learning in Fire Debris Analysis

Petrol is considered the most common fire accelerant. However, the identification and classification of petrol sources through the years has proven to be a challenging field in the investigation of fire debris analysis. This research explored the possibility of identifying petrol sources by high-field NMR methods accompanied by ML (machine learning). The automated identification and classification of petrol brands were achieved for first time based on the ML classification model developed in this research. A hierarchical classification model was constructed using local classifiers to categorize neat or weathered petrol into its sources.

Social representations of health-disease-care, security, and food sovereignty of indigenous students from Insikiran

The social representations of Insikiran Indigenous students regarding health-illness, care, security, insecurity, and food sovereignty were analyzed, aiming for a contextualized understanding of these topics, which are scarcely explored in the literature. This case study employed an exploratory, descriptive, and qualitative approach and was conducted at the Insikiran Institute of Indigenous Higher Education. The methodology included processing the textual corpus formed by the responses of 22 Indigenous students, using SPSS and IRaMuTeQ software. The analyses encompassed descriptive statistics, lexical analysis, descending hierarchical classification, similarity analysis, and word cloud generation. The results highlighted significant thematic diversity, emphasizing the importance of traditional health practices, concerns with chronic diseases, and the relevance of food sovereignty. The social representations were organized into three main thematic groups, demonstrating the intersections between traditional and academic knowledge. This study underscores the importance of adopting interdisciplinary and culturally adapted approaches to promote health and well-being in Indigenous communities.

Attribute reduction for hierarchical classification based on improved fuzzy rough set

Attribute reduction plays a critical role in extracting valuable information from high-dimensional datasets. Compared to Pawlak rough set, fuzzy rough set can preserve more data information, making it a prominent focus in the research of attribute reduction. However, current fuzzy rough set-based attribute reduction focuses on flat classification, neglecting distinguishable stability information in hierarchical classification, which leads to insufficient data utilization and reduces the accuracy of attribute reduction. To address these issues, this paper presents two types of fuzzy rough set, named IFRS-I and IFRS-II. Especially, IFRS-I is an improved fuzzy rough set for flat classification, while IFRS-II is constructed based on IFRS-I for hierarchical classification. Unlike traditional fuzzy rough set, IFRS-II has the following two advantages: (1) a stability factor is designed to measure the stability difference among decision classes, (2) a tolerance index is designed to represent the tolerance distance between decision classes based on the approximate information of different decision classes in hierarchical classification. Finally, a stable and effective attribute reduction based on IFRS-II (ARIFRS-II) is designed for hierarchical classification. Experiments demonstrate that compared with the existing related algorithms, ARIFRS-II obtains a higher classification accuracy and stability, while maintaining a suitable number of subsets after reduction.

Risk-based maintenance strategy for oil transfer pipelines using an intuitionistic fuzzy computational approach

The safety and reliability of oil transfer pipelines are crucial, as pipeline failures can severely affect the environment. As pipeline risk management is dynamic and uncertain, traditional maintenance approaches often fall short. This research paper proposes an Intuitive Fuzzy Computational Approach (IFCA) for oil transfer pipeline maintenance (RBM). To develop a targeted and nuanced maintenance plan, Failure Modes and Effects Analysis (FMEA) is employed. Pipeline equipment is hierarchically organised according to their failure mode criticality, which guides maintenance design. This paper leverages the context of an Interval Valued Intuitionistic Fuzzy (IVIF) environment to streamline the hierarchical classification of oil transmission pipeline instruments. The objectives are threefold: (1) to develop an intuitionistic fuzzy risk assessment model, (2) to design a modified algorithm for maintenance prioritisation, and (3) to develop a decision support system. Additionally, the research incorporates the IVIF-SWARA method to enable flexible adjustments in the alignment of the pipeline instruments. By addressing the specific challenges of oil transfer pipelines, this research aims to contribute to advancing the field of pipeline maintenance and risk management. The proposed RBM strategy, underpinned by the IFCA framework, is expected to enhance pipeline reliability and mitigate the risks associated with pipeline failures. Abbreviations: RBM: Risk-Based Maintenance; IFCA: Intuitionistic Fuzzy Computational Approach; FMEA: Failure Modes and Effects Analysis; IVIF: Interval Valued Intuitionistic Fuzzy; SWARA: Stepwise Weight Assessment Ratio Analysis; RCM: Reliability-Centered Maintenance; RBI: Risk-Based Inspection; CBM: Condition-Based Maintenance; IFS: Intuitionistic Fuzzy Set; HFPR: Hesitant Fuzzy Preference Relation; IVIFPHA: Interval-Valued Intuitionistic Fuzzy Power Heronian Aggregation; MCDM: Multi-Criteria Decision-Making; S C O i : Accuracy Function of Occurrence; S C S i : Accuracy Function of Severity; K ( a ~ ) : Failure Probability Index; L W D : Minimum Allowable Weight of The Failure Detection Index; WS, WO, WD: Weight Assigned to The Failure Outcome; RP V j : Relative Priority Value; OREDA: The Offshore Reliable Data Handbook; IVIFPWHA: Interval-Valued Intuitionistic Fuzzy Power Weight Heronian Aggregation

Challenges and prospects for teaching ocean literacy in Brazilian schools

This study took as a case study the perspective of teachers working in the State of Rio de Janeiro by 53 interviews to investigate the challenges and prospects of including content about the ocean in Brazilian school classrooms. The data were subjected to content analysis and explored quantitatively using Descending Hierarchical Classification (DHC) and Factor Correspondence Analysis (FCA) of word and terms used by teachers in their discourse. The main difficulties reported in including themes related to the ocean and marine environments in classes were the absence of OL in the school curriculum and university education, as well as the limited time to work on these subjects in classes, which is in line with the challenges faced by teachers from other countries. On the other hand, Brazilian teachers cited particular problems of Brazilian formal education, such as the need for professional development, support for an education with an interdisciplinary emphasis, and provision of financial resources for schools. However, DHC analysis also indicates strong connection of the teachers with the ocean due to sea fascination (24% of the answers in the textual corpus), spiritual and emotional connection (26.7%), leisure (22.7%) and professional interest (26.7%). Furthermore, the textual corpus also identified that teachers recognize the importance of teaching marine topics due to: students live in coastal areas (32.2%), the provision of ecosystem services (19.9%), preservation issues (34.2%), and limited student knowledge on these themes (13.7%). These data can help formulate educational policies to mitigate OL teaching barriers in Brazilian schools.

A data decomposition-based hierarchical classification method for multi-label classification of contractual obligations for the purpose of their governance

Contract governance ensures that the agreed outcomes between customers and vendors are fulfilled. Information Technology (IT) outsourcing organizations enter thousands of contractual relationships each month leading to a high volume of business-critical contractual text that must be reviewed and deciphered for effective governance. The key to effective governance of contracts is a model that facilitates assigning ownership of the obligations to the right departments in an organization and allocating their accountability to the right stakeholders. For this, the contractual obligations need to be identified and classified so that details such as actions to be taken by departments in an organization and their ownership as per a given clause are brought out for the purpose of governance. In this paper, we present our work on automated extraction and classification of obligations present in Software Engineering (SE) contracts for the purpose of contracts governance. We propose a novel data decomposition-based hierarchical classification method for a multi-label classification of contractual obligations. We conducted experiments for a fine-grained automated classification of more than 55,000 statements from 50 large real-life SE contract documents received from a large vendor organization into 152 governance-specific classes. The results indicate that the proposed method can bring about a 7–8% improvement in accuracies when compared to state-of-the-art classification baselines such as BERT, RoBERTa, and generative models such as GPT-2.

Towards ultrasonic guided wave fine-grained damage detection on hierarchical multi-label classification network

This study advocates the hierarchical multi-label classification (HMC) network for fine-grained damage detection using ultrasonic guided wave. Existing deep learning methods only focus on one aspect of the damage type or the degree of damage progression, and both are important for the long-term safe operation of the structure. To address this limitation, an ultrasonic guided wave HMC network (GHmcNet) and its lightweight version (L-GHmcNet) are developed. The essential designs of the proposed methods are derived from two motivations: (1) achieving robust fine-grained damage classification; (2) designing a lightweight network. The hierarchical labels (defect type-depth-size) are constructed on guided wave data. Inspired by the work of image classification, residual connections are introduced to transfer and fuse features between parent and children categories. The GHmcNet has three output channels and a weighted cross-entropy loss function is imposed on each channel. The weights of the corresponding loss are automatically adjusted during training. To reduce the parameters, we improve the structure of GHmcNet by applying different numbers of convolutional layers and channels at different levels based on the number of classes in each level, proposing the lightweight model L-GHmcNet. Both numerical and experimental studies are carried out, in which the dataset contains signals of different damage types, depths and sizes. The results show the superiority of the proposed methods in terms of accuracy at three levels compared to state-of-the-art methods. Moreover, the high accuracy classification results of L-GHmcNet demonstrate that the proposed lightweight network is a successful attempt.

A clustering machine learning approach for improving concrete compressive strength prediction

AbstractThis study investigates the application of clustering techniques to enhance the accuracy of hierarchical classification and regression (HCR) models for predicting concrete compressive strength (CCS). Following the hypothesis that integrating clustering at the initial levels of model hierarchy reduces classification errors and prevents their propagation to subsequent levels, HCR models were developed utilizing both the unweighted pair group method with arithmetic mean (UPGMA) and hard clustering (HC) methods. Findings demonstrate that models using UPGMA significantly outperform those based on HC. Furthermore, it was demonstrated that further hierarchical clustering allows for multilayered HCR models that improve predictive performance by further leveraging parent–child relationships within data clusters. Overall, this study demonstrates that the proposed methodology can be introduced in the model development pipeline to enhance the prediction accuracy of CCS models.

Racial and gender disparities in utilization of outpatient total shoulder arthroplasties

Utilization in outpatient total shoulder arthroplasties (TSAs) has increased significantly in recent years. It remains largely unknown whether utilization of outpatient TSA differs across gender and racial groups. This study aimed to quantify racial and gender disparities both nationally and by geographic regions. 168,504 TSAs were identified using Medicare fee-for-service inpatient and outpatient claims data and beneficiary enrollment data from 2020 to 2022Q4. The percentage of outpatient cases, defined as cases discharged on the same day of surgery, was evaluated by racial and gender groups and by different census divisions. A multivariate logistics regression model controlling for patient sociodemographic information (White vs. non-White race, age, gender, and dual eligibility for both Medicare and Medicaid), hierarchical condition category (HCC) score, hospital characteristics, year fixed effects, and patient residency state fixed effects was performed. The TSA volume per 1000 beneficiaries was 2.3 for the White population compared with 0.8, 0.6, and 0.3 for the Black, Hispanic, and Asian population, respectively. A higher percentage of outpatient TSAs were in White patients (25.6%) compared with Black patients (20.4%) (P<.001). The Black TSA patients were also younger, more likely to be female, more likely to be dually eligible for Medicaid, and had higher HCC risk scores. After controlling for patient sociodemographic characteristics and hospital characteristics, the odds of receiving outpatient TSAs were 30% less for Black than the White group (odds ratio 0.70). Variations were observed across different census divisions, with South Atlantic (0.67, P<.01), East North Central (0.56, P<.001), and Middle Atlantic (0.36, P<.01) being the 4 regions observed with significant racial disparities. Statistically significant gender disparities were also found nationally and across regions, with an overall odds ratio of 0.75 (P<.001). Statistically significant racial and gender disparities were found nationally in outpatient TSAs, with Black patients having 30% (P<.001) fewer odds of receiving outpatient TSAs than White patients, and female patients with 25% (P<.001) fewer odds than male patients. Racial and gender disparities continue to be an issue for shoulder arthroplasties after the adoption of outpatient TSAs.

Use of CAR T cell vs non-CAR T cell therapy in the treatment of patients (pts) with multiple myeloma (MM) in the Medicare population.

e23310 Background: Chimeric antigen receptor T-cell therapy (CAR T) is FDA-approved in pts with triple-class exposed (TCE) relapsed/refractory (RR) MM after four or more prior lines of therapy (LOTs). Real-world access to CAR T remains challenging due to manufacturing capacity, financial barriers, and pt fitness. Pts with certain pre-existing comorbidities (e.g., central nervous system disease, heart disease, secondary malignancies) are commonly excluded from clinical trials, including those investigating CAR T. The objective of this study was to identify the factors associated with the use of CAR T in pts with TCE RRMM to better understand the unmet need in this population. Methods: We conducted an observational cohort study using Medicare fee-for-service data; each pt in the CAR T intention-to-treat (ITT) population between 2021 and 2023 was matched to three non-CAR T pts, without replacement. Pts were eligible if they had an initial MM diagnosis, were continuously enrolled, were TCE, and did not receive treatment in a clinical trial. The index date was the ITT date. Baseline characteristics included age, sex, race/ethnicity, census region, three comorbidity indexes (Charlson, Elixhauser, CMS hierarchical condition categories [HCCs]), a claims-based frailty index (CFI), and dual enrollment in Medicare and Medicaid (as a proxy to social economic status [SES]). Logistic regression was used to derive odds ratios (ORs) and 95% confidence intervals (CIs) comparing the characteristics of CAR T vs non-CAR T pts. Results: Seventy-three ITT CAR T pts (nine underwent apheresis but did not receive CAR T) were matched to 219 non-CAR T pts by LOT and index year. Matched pts were treated with varied standard regimens (daratumumab-containing: 63%). Median prior LOTs were similar in the two cohorts (8; range 2–13). Median time from MM diagnosis to index date was 44.6 and 51.9 months for CAR T and non-CAR T pts, respectively. Compared with non-CAR T pts, pts in the CAR T population were younger (aged &lt; 75 years: 59% CAR T vs 36% non-CAR T), less frail (mean CFI: 0.18 vs 0.20) and had higher SES (without dual enrollment in Medicare and Medicaid: 96% vs 81%), but were similar in terms of sex, region, and race/ethnicity. Variation in individual comorbidity prevalence was observed between CAR T and non-CAR T pts. In a multivariable regression analysis, factors strongly associated with lower odds of CAR T use included age ≥75 years (OR 0.29; 95% CI 0.16–0.53), comorbidities (lung/other severe cancers [OR 0.39; 95% CI 0.20–0.74] and chronic obstructive pulmonary disease [OR 0.32; 95% CI 0.10–0.99] defined by HCCs), and SES (OR 0.09; 95% CI 0.02–0.37). Conclusions: Older age, certain comorbidities, and lower SES are associated with lower odds of receiving CAR T in real-world pts with TCE RRMM, demonstrating an unmet need for more accessible and effective treatment options with acceptable safety profiles for these pts.

A Preoperative Risk Assessment Tool for Predicting Adverse Outcomes among Total Shoulder Arthroplasty Patients

With the increased utilization of Total Shoulder Arthroplasty (TSA) in the outpatient setting, understanding the risk factors associated with complications and hospital readmissions becomes a more significant consideration. Prior developed assessment metrics in the literature either consisted of hard-to-implement tools or relied on postoperative data to guide decision-making. This study aimed to develop a preoperative risk assessment tool to help predict the risk of hospital readmission and other postoperative adverse outcomes. We retrospectively evaluated the 2019-2022(Q2) Medicare fee-for-service inpatient and outpatient claims data to identify primary anatomic or reserve TSAs and to predict postoperative adverse outcomes within 90days postdischarge, including all-cause hospital readmissions, postoperative complications, emergency room visits, and mortality. We screened 108 candidate predictors, including demographics, social determinants of health, TSA indications, prior 12-month hospital, and skilled nursing home admissions, comorbidities measured by hierarchical conditional categories, and prior orthopedic device-related complications. We used two approaches to reduce the number of predictors based on 80% of the data: 1) the Least Absolute Shrinkage and Selection Operator logistic regression and 2) the machine-learning-based cross-validation approach, with the resulting predictor sets being assessed in the remaining 20% of the data. A scoring system was created based on the final regression models' coefficients, and score cutoff points were determined for low, medium, and high-risk patients. A total of 208,634 TSA cases were included. There was a 6.8% hospital readmission rate with 11.2% of cases having at least one postoperative adverse outcome. Fifteen covariates were identified for predicting hospital readmission with the area under the curve of 0.70, and 16 were selected to predict any adverse postoperative outcome (area under the curve =0.75). The Least Absolute Shrinkage and Selection Operator and machine learning approaches had similar performance. Advanced age and a history of fracture due to orthopedic devices are among the top predictors of hospital readmissions and other adverse outcomes. The score range for hospital readmission and an adverse postoperative outcome was 0 to 48 and 0 to 79, respectively. The cutoff points for the low, medium, and high-risk categories are 0-9, 10-14, ≥15 for hospital readmissions, and 0-11, 12-16, ≥17 for the composite outcome. Based on Medicare fee-for-service claims data, this study presents a preoperative risk stratification tool to assess hospital readmission or adverse surgical outcomes following TSA. Further investigation is warranted to validate these tools in a variety of diverse demographic settings and improve their predictive performance.