Measuring Payroll Employment: A Note on the Current Employment Statistics

Input modelling is a complex task within the Monte Carlo simulation, especially when the systems and processes under investigation reveal the non-linear behavior of several interdependent variables. Commonly used approaches for Monte Carlo simulation input modelling include selecting probability distributions and fitting them to existing data; resampling random variates from historical data; and using real-world data as an input model, which in the age of big data becomes more feasible. Each of the approaches comes with its own set of drawbacks. This note aims to describe a new method of input modelling for GDP Monte Carlo simulation based on interpolation of the GDP historical records. Also, this method has been implemented as a publicly available online tool using the Microsoft Azure Machine Learning Studio. A similar approach can be applied to other macroeconomic indicators, e.g., consumer price index (inflation) or current employment statistics. This note is intended for economists, data scientists, and operations research analysts interested in the GDP Monte Carlo simulation. It can also be used by academics, researchers, and practitioners in a broad subject area for generating input data for Monte Carlo simulation. Specifically, it can be of interest for Ph.D. candidates (VAC specialty 5.2.6) performing development of theory and methods of decision-making in economic and social systems, and application of artificial intelligence and big data methods in management.

To meet the Basel II regulatory requirements for the Advanced Measurement Approaches, the bank’s internal model must include the use of internal data, relevant external data, scenario analysis and factors reflecting the business environment and internal control systems. Quantification of operational risk cannot be based only on historical data but should involve scenario analysis. Historical internal operational risk loss data have limited ability to predict future behaviour moreover, banks do not have enough internal data to estimate low frequency high impact events adequately. Historical external data are difficult to use due to different volumes and other factors. In addition, internal and external data have a survival bias, since typically one does not have data of all collapsed companies. The idea of scenario analysis is to estimate frequency and severity of risk events via expert opinions taking into account bank environment factors with reference to events that have occurred (or may have occurred) in other banks. Scenario analysis is forward looking and can reflect changes in the banking environment. It is important to not only quantify the operational risk capital but also provide incentives to business units to improve their risk management policies, which can be accomplished through scenario analysis. By itself, scenario analysis is very subjective but combined with loss data it is a powerful tool to estimate operational risk losses. Bayesian inference is a statistical technique well suited for combining expert opinions and historical data. In this paper, we present examples of the Bayesian inference methods for operational risk quantification.

This article focuses on the research of enterprise accounting information recognition system based on data mining, pointing out that traditional accounting information systems and management accounting methods in the era of big data rely too much on internal historical financial data, making it difficult to effectively process key internal and external unstructured data, resulting in insufficient depth of strategic decision analysis. Data mining technology provides a new path for integrating internal and external data and building a strategic management accounting system. A five layer strategic management accounting system framework was developed, which includes a basic theoretical layer and a data storage layer. The framework integrates theories such as Porter’s Five Forces model and regression analysis techniques. Taking e-commerce company M as a case study, the data mining application in scenarios such as intelligent supply chain replenishment was analyzed. Logistic regression model was used to identify the authenticity of financial reports, and LSTM neural network was used to predict sales data. The results showed that after applying the framework, M company’s market share reached 46% and growth rate was 36% in the 12th month. The logistics unit cost supported order volume increased by 400%. This study achieved interdisciplinary integration of data mining and strategic management accounting, providing enterprises with information recognition and strategic decision-making tools to help them optimize management and maintain core competitiveness through data-driven optimization in complex environments.

US health care providers are seeking to reduce costs while simultaneously maintaining quality of care. One strategy for the reinvention of the health care industry is the more effective use of new quality and information technology solutions. Results are presented from a survey of 98 top executives at Baylor Health Care System (BHCS), a large, multifunction health care organization in Dallas, TX. The survey sought to assess the executives' perceptions of current BHCS quality practices. The study used a survey developed for the health care industry based on the Malcom Baldrige National Quality Award (MBNQA) criteria. This paper reports findings related to the quality of BHCS internal and external data and information quality. Factor analysis and regression models using the survey data were used to highlight findings that include: (1) the need for a $50+ million information system transformation at BHCS as an essential action item to achieve the organization's critical success factors, and (2) the importance of internal and external data and information in achieving business process redesign and a quality transformation at BHCS. Results highlight the need for further research investigating the dimensions associated with the MBNQA criteria and their relationship with the information and analysis component.

Total metabolic tumor volume (TMTV) segmentation has significant value enabling quantitative imaging biomarkers for lymphoma management. In this work, we tackle the challenging task of automated tumor delineation in lymphoma from PET/CT scans using a cascaded approach. Our study included 1418 2-[18F]FDG PET/CT scans from four different centers. The dataset was dividedinto 900 scans for development/validation/testing phasesand 518 for multi-center external testing. The former consisted of 450 lymphoma, lung cancer, and melanoma scans, along with 450 negative scans, while the latter consisted of lymphoma patients from different centers with diffuse large B cell, primary mediastinal large B cell, and classic Hodgkin lymphoma cases. Our approach involves resampling PET/CT images into different voxel sizes in the first step, followed by training multi-resolution 3D U-Nets on each resampled dataset using a fivefold cross-validation scheme. The models trained on different data splits were ensemble. After applying soft voting to the predicted masks, in the second step, we input the probability-averaged predictions, along with the input imaging data, into another 3D U-Net. Models were trained with semi-supervised loss. We additionally considered the effectiveness of using test time augmentation (TTA) to improve the segmentation performance after training. In addition to quantitative analysis including Dice score (DSC) and TMTV comparisons, the qualitative evaluation was also conducted by nuclear medicine physicians. Our cascaded soft-voting guided approach resulted in performance with an average DSC of 0.68 ± 0.12 for the internal test data from developmental dataset, and an average DSC of 0.66 ± 0.18 on the multi-site external data (n = 518), significantly outperforming (p < 0.001) state-of-the-art (SOTA) approaches including nnU-Net and SWIN UNETR. While TTA yielded enhanced performance gains for some of the comparator methods, its impact on our cascaded approach was found to be negligible (DSC: 0.66 ± 0.16). Our approach reliably quantified TMTV, with a correlation of 0.89 with the ground truth (p < 0.001). Furthermore, in terms of visual assessment, concordance between quantitative evaluations and clinician feedback was observed in the majority of cases. The average relative error (ARE) and the absolute error (AE) in TMTV prediction on external multi-centric dataset were ARE = 0.43 ± 0.54 and AE = 157.32 ± 378.12 (mL) for all the external test data (n = 518), and ARE = 0.30 ± 0.22 and AE = 82.05 ± 99.78 (mL) when the 10% outliers (n = 53) were excluded. TMTV-Net demonstrates strong performance and generalizability in TMTV segmentation across multi-site external datasets, encompassing various lymphoma subtypes. A negligible reduction of 2% in overall performance during testing on external data highlights robust model generalizability across different centers and cancer types, likely attributable to its training with resampled inputs. Our model is publicly available, allowing easy multi-site evaluation and generalizability analysis on datasets from different institutions.

Alzheimer’s disease (AD) is a global healthcare challenge lacking a simple and affordable detection method. We propose a novel deep learning framework, Eye-AD, to detect Early-onset Alzheimer’s Disease (EOAD) and Mild Cognitive Impairment (MCI) using OCTA images of retinal microvasculature and choriocapillaris. Eye-AD employs a multilevel graph representation to analyze intra- and inter-instance relationships in retinal layers. Using 5751 OCTA images from 1671 participants in a multi-center study, our model demonstrated superior performance in EOAD (internal data: AUC = 0.9355, external data: AUC = 0.9007) and MCI detection (internal data: AUC = 0.8630, external data: AUC = 0.8037). Furthermore, we explored the associations between retinal structural biomarkers in OCTA images and EOAD/MCI, and the results align well with the conclusions drawn from our deep learning interpretability analysis. Our findings provide further evidence that retinal OCTA imaging, coupled with artificial intelligence, will serve as a rapid, noninvasive, and affordable dementia detection.

ABSTRACTBI solutions are constantly being developed to support decision-making at various organisational levels. These solutions facilitate the compilation, aggregation and summarisation of large volumes of data. Consequently, the business value created by these systems is increasing as they sustain more and more advanced analytics, ranging from descriptive analytics, to predictive analytics, to prescriptive analytics. However, most organisations work primarily with internal data. Despite many references in the literature to the value hidden in external data, details on how such data can be used are scarce. In this paper, we present the results of an extensive action case study at a public waste management company. The results illustrate how external data from several external data sources, integrated into an up-and-running BI solution, are used jointly to allow for descriptive and predictive analytics, as well as prescriptive analytics. In addition, details of these analytical values are given and related to organisational benefits.

SummaryWe investigate applying and extending an exhaust data framework, using an empirical analysis to explore and compare different predictive analytic capabilities of both internal and external exhaust data for estimating sales. We use internal exhaust data that explores the relationship between app usage and web traffic data and estimation of sales and find the ability to predict sales at least 4 days ahead. We also develop predictive models of sales, using external data of Google searches, extending the previous research to include additional macroeconomic Google variables and Wikipedia pageviews, finding that we can predict at least 4 months ahead, suggesting a portfolio of exhaust data be used. We introduce the roles of internal and external exhaust data, direct and indirect exhaust data and transformed exhaust data, into an exhaust data framework. We examine what appear to be different levels of information fineness and predictability from those exhaust data sources. We also note the importance of the types of devices (e.g., mobile) and the types of commerce (e.g., mobile commerce) in creating and finding different types of exhaust. Finally, we apply an existing exhaust data framework to develop macroeconomic data exhaust variables, as the means of capturing inflation and unemployment information, using Google searches.

As the implementation of Patient-Reported Outcomes Measurement Information System (PROMIS) scales has increased, so has the number of studies linking legacy scale scores to PROMIS scale scores. Variability in linked scores for a given PROMIS score can be considerable, leading to potential bias. An alternative method is imputation using a bridge study. We sought to compare linking to this alternative novel method in group-level analyses using linked legacy scores. Adult patients who completed PROMIS Depression and Patient Health Questionnaire (PHQ-9) were included. We randomly allocated data samples to be missing either PROMIS Depression or PHQ-9. We estimated PROMIS T scores using six methods: Linking methods by Choi et al. (2014), linking in our internal data, imputation using bridge study data from external data and from our internal data, each with and without patient demographics. Estimated mean PROMIS T scores using the linking and imputation methods were compared to actual PROMIS T scores across varying proportions of missingness and sample size. We also compared regression coefficients for the six estimation methods to a model using actual PROMIS T scores. Mean estimated versus actual PROMIS T scores varied between 1 and 4 points for the linking methods and within 0.4 points for the imputation method using internal data with patient demographics. The imputation methods had estimated regression coefficients closer to that of the model using actual scores as compared to the linking methods. For group-level analyses, imputation using a bridge study may be a feasible alternative to using linked scores or can be used as a sensitivity analysis. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

How do macroeconomic expectations affect consumer decisions? We examine this question using a natural field experiment with 2,872 credit card customers from a large commercial bank. We conduct a survey to measure consumer expectations about future inflation and the nominal exchange rate and combine this with an information-provision experiment that generates exogenous variation in these expectations. We merge the survey and experimental data with detailed administrative data on the subjects' credit card transactions and balances. The experiment is designed to test three standard predictions from models of intertemporal consumption choice: inflation expectations should affect spending on durables; exchange rate expectations should affect spending on tradables; and, holding constant the nominal interest rate, inflation expectations should affect borrowing. We find that the information provided to participants strongly affects subjective expectations. However, we do not find any significant effects on actual consumer behavior (as measured in administrative data) or self-reported consumption plans (as measured in survey data). Our preferred interpretation is that consumers are not sophisticated enough to factor inflation and exchange rate expectations into their consumption decisions. The absence of a link between consumer expectations and behavior has potentially important implications for macroeconomic policies such as forward guidance. Institutional subscribers to the NBER working paper series, and residents of developing countries may download this paper without additional charge at www.nber.org.

Predictive maintenance of physical systems can only be achieved by monitoring their most critical elements to track their health assessment during operation. The acquired data is processed to extract relevant features, which are used to estimate the state of the system at any time and detect any loss of performance that may occur due to the critical element. We propose in this work an architecture of generic method to supervise this critical element and generate a Health Indicator (HI) for the physical system. The generated HI takes into account the evolution in time of the healthy status of the physical systems. The proposed method is based on sensors data that allow us to extract in real time the values of features constituting themselves the HI construction bloc input, through several HI obtaining test. Block diagram of the approach is made, then checked using benchmark data taken from “NASA data repository prognosis” associated to an element used in different operating conditions are checked. This approach is classified as data driven method which use sensors data that inform us about the real-time values of features.

Summary Meta-analysis has become a powerful tool for improving inference by gathering evidence from multiple sources. It pools summary-level data from different studies to improve estimation efficiency with the assumption that all participating studies are analysed under the same statistical model. It is challenging to integrate external summary data calculated from different models with a newly conducted internal study in which individual-level data are collected. We develop a novel statistical inference framework that can effectively synthesize internal and external data for the integrative analysis. The new framework is versatile enough to assimilate various types of summary data from multiple sources. We establish asymptotic properties for the proposed procedure and prove that the new estimate is theoretically more efficient than the internal data based maximum likelihood estimate, as well as a recently developed constrained maximum likelihood approach that incorporates the external information. We illustrate an application of our method by evaluating cervical cancer risk using data from a large cervical screening program.

With the advances in deep learning, including Convolutional Neural Networks (CNN), automated diagnosis technology using medical images has received considerable attention in medical science. In particular, in the field of ultrasound imaging, CNN trains the features of organs through an amount of image data, so that an expert-level automatic diagnosis is possible only with images of actual patients. However, CNN models are also trained on the features that reflect the inherent bias of the imaging machine used for image acquisition. In other words, when the domain of data used for training is different from that of data applied for an actual diagnosis, it is unclear whether consistent performance can be provided by the domain bias. Therefore, we investigate the effect of domain bias on the model with liver ultrasound imaging data obtained from multiple domains. We have constructed a dataset considering the manufacturer and the year of manufacturing of 8 ultrasound imaging machines. First, training and testing were performed by dividing the entire data, in a commonly used method. Second, we have utilized the training data constructed according to the number of domains for the machine learning process. Then we have measured and compared the performance on internal and external domain data. Through the above experiment, we have analyzed the effect of domains of data on model performance. We show that the performance scores evaluated with the internal domain data and the external domain data do not match. We especially show that the performance measured in the evaluation data including the internal domain was much higher than the performance measured in the evaluation data consisting of the external domain. We also show that 3-level classification performance is slightly improved over 5-level classification by mitigating class imbalance by integrating similar classes. The results highlight the need to develop a new methodology for mitigating the machine bias problem so that the model can work correctly even on external domain data, as opposed to the usual approach of constructing evaluation data in the same domain as the training data.

AI-Assisted Echocardiographic Prescreening of Heart Failure With Preserved Ejection Fraction on the Basis of Intrabeat Dynamics

To assess strategies for enhancing the generalizability of healthcare artificial intelligence models, we analyzed the impact of preprocessing approaches applied to medical free text, compared single- versus multiple-institution data models, and evaluated data divergence metrics. From 1,607,393 procedures across 44 U.S. institutions, deep neural network models were created to classify anesthesiology Current Procedural Terminology codes from medical free text. Three levels of text preprocessing were analyzed from minimal to automated (cSpell) with comprehensive physician review. Kullback–Leibler Divergence and k-medoid clustering were used to predict single- vs multiple-institutional model performances. Single-institution models showed a mean accuracy of 92.5% [2.8% SD] and 0.923 [0.029] F1 on internal data but generalized poorly on external data (− 22.4% [7.0%]; − 0.223 [0.081]). Free text preprocessing minimally altered performance (+ 0.51% [2.23]; + 0.004 [0.020]). An all-institution model performed worse on internal data (-4.88% [2.43%]; − 0.045 [0.020]), but improved generalizability to external data (+ 17.1% [8.7%]; + 0.182 [0.073]). Compared to vocabulary overlap and Jaccard similarity, Kullback–Leibler Divergence correlated with model performance (R2 of 0.41 vs 0.16 vs 0.08, respectively) and was successful clustering institutions and identifying outlier data. Overall, pre-processing medical free text showed limited utility improving generalization of machine learning models, single institution models performed best but generalized poorly, while combined data models improved generalization but never achieved performance of single-institutional models. Kullback–Leibler Divergence provided valuable insight as a reliable heuristic to evaluate generalizability. These results have important implications in developing broad use artificial intelligence healthcare applications, providing valuable insight into their development and evaluations.