Mesoscale effects of trader learning behaviors in financial markets: A multi-agent reinforcement learning study.

Recent advances in the field of machine learning have yielded novel research perspectives in behavioural economics and financial markets microstructure studies. In this paper we study the impact of individual trader leaning characteristics on markets using a stock market simulator designed with a multi-agent architecture. Each agent, representing an autonomous investor, trades stocks through reinforcement learning, using a centralized double-auction limit order book. This approach allows us to study the impact of individual trader traits on the whole stock market at the mesoscale in a bottom-up approach. We chose to test three trader trait aspects: agent learning rate increases, herding behaviour and random trading. As hypothesized, we find that larger learning rates significantly increase the number of crashes. We also find that herding behaviour undermines market stability, while random trading tends to preserve it.

The peer effects of resident stock market participation: Evidence from 2019 CHFS.

Limited resident's participation in the stock market has become a key constraint to the capital market development. Utilizing the 2019 China Household Financial Survey (CHFS) data, our paper designs probit models to examine the peer effects of residents' stock market participation and explore the intermediary mechanisms with a multiple intermediary model. We find that: (1) Resident involvement in stock market decision-making exhibits significant peer effects. (2) Heterogeneity analysis reveals that males and rural residents display more pronounced peer effects than females and urban residents. Additionally, middle-aged residents demonstrate more potent peer effects than their younger and older counterparts, with the intensity of peer effects correlating with education levels. (3)We observe that the peer effects of market participation operate by altering economic expectations and enhancing residents' financial literacy. (4) Further investigation establishes that individuals engaging in stock market investments manifest peer effects when deciding whether to diversify their stock portfolio. This study holds reference value for analyzing the impact of social interaction on financial behaviors and regulating individuals' financial conduct.

Pricing decision and channel selection of fresh agricultural products dual-channel supply chain based on blockchain.

The application of blockchain can effectively improve the efficiency of fresh agricultural product circulation and consumer trust, but it can also increase investment costs. In this context, this paper introduces parameters such as blockchain unit variable cost, the level of blockchain technology investment, and consumer channel preference in two dual-channel supply chain systems dominated by fresh agricultural product manufacturers: online direct sales and distribution. It compares and analyzes pricing and channel selection strategies in both cases of not using and using blockchain. The research shows that when blockchain is used, manufacturer profits are higher in the direct sales model than in the distribution model. Traditional retailers' profits are lower in the direct sales model than in the distribution model. Total supply chain profits are higher in the direct sales model than in the distribution model, and they exhibit an inverted "U" shape as the level of blockchain investment increases. In the online direct sales model, if the blockchain technology unit variable cost is within a certain threshold range, manufacturer profits, traditional retailer profits, and total supply chain profits are all higher than when blockchain technology is not used. In the online distribution model, when the blockchain variable cost and blockchain usage level meet certain conditions, manufacturers, traditional retailers, and online distributors all have higher profits when using blockchain technology than when not using it. This study provides theoretical guidance for the practical application of blockchain technology in dual-channel fresh agricultural product supply chains.

Cross-sectional analysis of use of real-world data in single technology appraisals of oncological medicine by the National Institute for Health and Care Excellence in 2011-2021.

OBJECTIVES: This study aims to identify how real-world data (RWD) have been used in single technology appraisals (STAs) of cancer drugs by the National Institute for Health and Care Excellence (NICE). DESIGN: Cross-sectional study of NICE technology appraisals of cancer drugs for which guidance was issued between January 2011 and December 2021 (n=229). The appraisals were reviewed following a published protocol to extract the data about the use of RWD. The use of RWD was analysed by reviewing the specific ways in which RWD were used and by identifying different patterns of use. PRIMARY OUTCOME MEASURE: The number of appraisals where RWD are used in the economic modelling. RESULTS: Most appraisals used RWD in their economic models. The parametric use of RWD was commonly made in the economic models (76% of the included appraisals), whereas non-parametric use was less common (41%). Despite widespread use of RWD, there was no dominant pattern of use. Three sources of RWD (registries, administrative data, chart reviews) were found across the three important parts of the economic model (choice of comparators, overall survival and volume of treatment). CONCLUSIONS: NICE has had a long-standing interest in the use of RWD in STAs. A systematic review of oncology appraisals suggests that RWD have been widely used in diverse parts of the economic models. Between 2011 and 2021, parametric use was more commonly found in economic models than non-parametric use. Nonetheless, there was no clear pattern in the way these data were used. As each appraisal involves a different decision problem and the ability of RWD to provide the information required for the economic modelling varies, appraisals will continue to differ with respect to their use of RWD.

A short-term price prediction-based trading strategy.

Quantitative investment theory has emerged as a prominent and widely researched domain within the financial markets, where investors predominantly focus on discerning the intricate influences of market dynamics. In this paper, we proposed a short-term prediction-based trading strategy, which can equiponderate between return and risk, considerations while accounting for investor risk preferences. This strategy employs GM(1,1) to capture nuanced features of price dynamics in short-term intervals and update the GM(1,1) model with the latest data. Subsequently, a multi-objective planning equation is formulated to optimize asset allocations by determining the optimal holding that strikes between specific returns and risk mitigation. In the end, this work conducts a case study and sensitivity analysis using five years of gold and bitcoin price data spanning from 2016 to 2021. This empirical examination serves to affirm the efficacy and resilience of the proposed trading strategy. The case study reveals that proficient short-term price forecasting serves as a potent means to proactively mitigate risk, facilitating, judicious and objective trading practices. Moreover, it underscores the strategy's tangible utility as a guide for real-world investment decisions.

Digital economy and green total factor productivity in China.

The development of information technology has created conducive conditions for the digital economy. The digital economy is regarded as a critical pathway for transforming traditional economic models. Green total factor productivity serves as an indicator for assessing the quality of economic development. During pivotal periods of economic transition, the digital economy and green total factor productivity have emerged as two prominent themes for achieving sustainable economic development. But the impact of digital economy on green total factor productivity is less discussed. Innovation environment refers to a confluence of conditions shaped by factors such as talent, funding, cultural atmosphere and government policies, all of which collectively support innovative activities within a region. The institutional environment encompasses the aggregate of economic, political, social, and legal rules. Currently, there is little discussion on bringing innovation environment and institutional environment into the impact of digital economy on green total factor productivity. To fill the research gap, this paper adopts the Slack based measure-Directional distance function model and Malmquist-Luenberger productivity index to measure green total factor productivity in each region based on the panel data collected from 30 provinces in China from 2004 to 2019. Generalized Method of Moments method is constructed to carry out an empirical study on the impact of digital economy on green total factor productivity. This paper constructs a panel threshold model with innovation environment and institutional environment as threshold variables. In further analysis, this paper employs panel quantile regression for the empirical analysis of the impact of the digital economy on green total factor productivity. Further analysis elucidates the evident disparities in the influence of the digital economy on green total factor productivity at various levels. The research results can provide a guide for discussing the green value of the digital economy and its role in fostering the development of a green economy.

Markov modeling for cost-effectiveness using federated health data network.

OBJECTIVE: To introduce 2 R-packages that facilitate conducting health economics research on OMOP-based data networks, aiming to standardize and improve the reproducibility, transparency, and transferability of health economic models. MATERIALS AND METHODS: We developed the software tools and demonstrated their utility by replicating a UK-based heart failure data analysis across 5 different international databases from Estonia, Spain, Serbia, and the United States. RESULTS: We examined treatment trajectories of 47 163 patients. The overall incremental cost-effectiveness ratio (ICER) for telemonitoring relative to standard of care was 57 472 €/QALY. Country-specific ICERs were 60 312 €/QALY in Estonia, 58 096 €/QALY in Spain, 40 372 €/QALY in Serbia, and 90 893 €/QALY in the US, which surpassed the established willingness-to-pay thresholds. DISCUSSION: Currently, the cost-effectiveness analysis lacks standard tools, is performed in ad-hoc manner, and relies heavily on published information that might not be specific for local circumstances. Published results often exhibit a narrow focus, central to a single site, and provide only partial decision criteria, limiting their generalizability and comprehensive utility. CONCLUSION: We created 2 R-packages to pioneer cost-effectiveness analysis in OMOP CDM data networks. The first manages state definitions and database interaction, while the second focuses on Markov model learning and profile synthesis. We demonstrated their utility in a multisite heart failure study, comparing telemonitoring and standard care, finding telemonitoring not cost-effective.

Simplified Methods for Modelling Dependent Parameters in Health Economic Evaluations: A Tutorial.

BACKGROUND: In health economic evaluations, model parameters are often dependent on other model parameters. Although methods exist to simulate multivariate normal (MVN) distribution data and estimate transition probabilities in Markov models while considering competing risks, they are technically challenging for health economic modellers to implement. This tutorial introduces easily implementable applications for handling dependent parameters in modelling. METHODS: Analytical proofs and proposed simplified methods for handling dependent parameters in typical health economic modelling scenarios are provided, and implementation of these methods are illustrated in seven examples along with the SAS and R code. RESULTS: Methods to quantify the covariance and correlation coefficients of correlated variables based on published summary statistics and generation of MVN distribution data are demonstrated using examples of physician visits data and cost component data. The use of univariate normal distribution data instead of MVN distribution data to capture population heterogeneity is illustrated based on the results from multiple regression models with linear predictors, and two examples are provided (linear fixed-effects model and Cox proportional hazards model). A conditional probability method is introduced to handle two or more state transitions in a single Markov model cycle and applied in examples of one- and two-way state transitions. CONCLUSIONS: This tutorial proposes an extension of routinely used methods along with several examples. These simplified methods may be easily applied by health economic modellers with varied statistical backgrounds.

A US payer perspective health economic model assessing value of monitoring disease activity to inform discontinuation and re-initiation of DMT in multiple sclerosis.

OBJECTIVES: We evaluate the potential clinical and cost impacts of discontinuing disease-modifying therapy (DMT) in people with multiple sclerosis (PwMS) when age-related immunosenescence can reduce DMT efficacy while increasing associated risks. METHODS: A Markov model simulated clinical and cost impacts to the patient and payers when a proportion of eligible patients with relapsing remitting multiple sclerosis (RRMS) discontinue DMT. Eligibility was defined as age >55 years, an RRMS diagnosis of >5 years, and no history of relapses for 5 years. Increasing the proportion of eligible patients willing to discontinue therapy was also modeled. Clinical and cost inputs were from published literature. RESULTS: Difference in EDSS progression between eligible patients who did and did not attempt discontinuation was not significant. After 1 year of eligibility, per-patient costs were $96k lower in the cohort that attempted discontinuation; however a higher proportion of relapses were seen in this group. When the proportion of patients willing to discontinue DMT increased, clinical findings remained consistent while the average cost per patient decreased. CONCLUSION: While there are increased clinical and cost benefits as more eligible patients attempt discontinuation, the risk of relapses can increase. Timely disease monitoring is required to manage safe DMT discontinuation.

Emergent invariance and scaling properties in the collective return dynamics of a stock market.

A key metric to determine the performance of a stock in a market is its return over different investment horizons (τ). Several works have observed heavy-tailed behavior in the distributions of returns in different markets, which are observable indicators of underlying complex dynamics. Such prior works study return distributions that are marginalized across the individual stocks in the market, and do not track statistics about the joint distributions of returns conditioned on different stocks, which would be useful for optimizing inter-stock asset allocation strategies. As a step towards this goal, we study emergent phenomena in the distributions of returns as captured by their pairwise correlations. In particular, we consider the pairwise (between stocks i, j) partial correlations of returns with respect to the market mode, ci,j(τ), (thus, correcting for the baseline return behavior of the market), over different time horizons (τ), and discover two novel emergent phenomena: (i) the standardized distributions of the ci,j(τ)'s are observed to be invariant of τ ranging from from 1000min (2.5 days) to 30000min (2.5 months); (ii) the scaling of the standard deviation of ci,j(τ)'s with τ admits good fits to simple model classes such as a power-law τ-λ or stretched exponential function [Formula: see text] (λ, ß > 0). Moreover, the parameters governing these fits provide a summary view of market health: for instance, in years marked by unprecedented financial crises-for example 2008 and 2020-values of λ (scaling exponent) are substantially lower. Finally, we demonstrate that the observed emergent behavior cannot be adequately supported by existing generative frameworks such as single- and multi-factor models. We introduce a promising agent-based Vicsek model that closes this gap.

Benefits of a digital health technology for older nursing home residents. A de-novo cost-effectiveness model for digital health technologies to aid in the assessment of toileting and containment care needs.

The aim of this study was first, to introduce a comprehensive, de-novo health economic (HE) model incorporating the full range of activities involved in toileting and containment care (T&CC) for people with incontinence, capturing all the potential benefits and costs of existing and future Digital Health Technologies (DHT) aimed at improving continence care, for both residential care and home care. Second, to use this novel model to evaluate the cost-effectiveness of the DHT TENA SmartCare Identifi in the implementation of person-centred continence care (PCCC), compared with conventional continence care for Canadian nursing home residents. The de-novo HE model was designed to evaluate technologies across different care settings from the perspective of several stakeholders. Health states were based on six care need profiles with increasing need for toileting assistance, three care stages with varying degrees of toileting success, and five levels of skin health. The main outcomes were incremental costs and quality-adjusted life years. The effectiveness of the TENA SmartCare Identifi was based primarily on trial data combined with literature and expert opinion where necessary. Costs were reported in CAD 2020. After 2 years, 21% of residents in the DHT group received mainly toileting as their continence care strategy compared with 12% in the conventional care group. Conversely, with the DHT 15% of residents rely mainly on absorbent products for incontinence care, compared with 40% with conventional care. On average, residents lived for 2.34 years, during which the DHT resulted in a small gain in quality-adjusted life years of 0.015 and overall cost-savings of $1,467 per resident compared with conventional care. Most cost-savings were achieved through reduced costs for absorbent products. Since most, if not all, stakeholders gain from use of the DHT-assisted PCCC, widespread use in Canadian residential care facilities should be considered, and similar assessments for other countries encouraged.

Social Risk and Dialysis Facility Performance in the First Year of the ESRD Treatment Choices Model.

Importance: The End-Stage Renal Disease Treatment Choices (ETC) model randomly selected 30% of US dialysis facilities to receive financial incentives based on their use of home dialysis, kidney transplant waitlisting, or transplant receipt. Facilities that disproportionately serve populations with high social risk have a lower use of home dialysis and kidney transplant raising concerns that these sites may fare poorly in the payment model. Objective: To examine first-year ETC model performance scores and financial penalties across dialysis facilities, stratified by their incident patients' social risk. Design, Setting, and Participants: A cross-sectional study of 2191 US dialysis facilities that participated in the ETC model from January 1 through December 31, 2021. Exposure: Composition of incident patient population, characterized by the proportion of patients who were non-Hispanic Black, Hispanic, living in a highly disadvantaged neighborhood, uninsured, or covered by Medicaid at dialysis initiation. A facility-level composite social risk score assessed whether each facility was in the highest quintile of having 0, 1, or at least 2 of these characteristics. Main Outcomes and Measures: Use of home dialysis, waitlisting, or transplant; model performance score; and financial penalization. Results: Using data from 125 984 incident patients (median age, 65 years [IQR, 54-74]; 41.8% female; 28.6% Black; 11.7% Hispanic), 1071 dialysis facilities (48.9%) had no social risk features, and 491 (22.4%) had 2 or more. In the first year of the ETC model, compared with those with no social risk features, dialysis facilities with 2 or more had lower mean performance scores (3.4 vs 3.6, P = .002) and lower use of home dialysis (14.1% vs 16.0%, P < .001). These facilities had higher receipt of financial penalties (18.5% vs 11.5%, P < .001), more frequently had the highest payment cut of 5% (2.4% vs 0.7%; P = .003), and were less likely to achieve the highest bonus of 4% (0% vs 2.7%; P < .001). Compared with all other facilities, those in the highest quintile of treating uninsured patients or those covered by Medicaid experienced more financial penalties (17.4% vs 12.9%, P = .01) as did those in the highest quintile in the proportion of patients who were Black (18.5% vs 12.6%, P = .001). Conclusions: In the first year of the Centers for Medicare & Medicaid Services' ETC model, dialysis facilities serving higher proportions of patients with social risk features had lower performance scores and experienced markedly higher receipt of financial penalties.

A Scoping Review and Taxonomy of Epidemiological-Macroeconomic Models of COVID-19.

OBJECTIVES: The COVID-19 pandemic placed significant strain on many health systems and economies. Mitigation policies decreased health impacts but had major macroeconomic impact. This article reviews models combining epidemiological and macroeconomic projections to enable policy makers to consider both macroeconomic and health objectives. METHODS: A scoping review of epidemiological-macroeconomic models of COVID-19 was conducted, covering preprints, working articles, and journal publications. We assessed model methodologies, scope, and application to empirical data. RESULTS: We found 80 articles modeling both the epidemiological and macroeconomic outcomes of COVID-19. Model scope is often limited to the impact of lockdown on health and total gross domestic product or aggregate consumption and to high-income countries. Just 14% of models assess disparities or poverty. Most models fall under 4 categories: compartmental-utility-maximization models, epidemiological models with stylized macroeconomic projections, epidemiological models linked to computable general equilibrium or input-output models, and epidemiological-economic agent-based models. We propose a taxonomy comparing these approaches to guide future model development. CONCLUSIONS: The epidemiological-macroeconomic models of COVID-19 identified have varying complexity and meet different modeling needs. Priorities for future modeling include increasing developing country applications, assessing disparities and poverty, and estimating of long-run impacts. This may require better integration between epidemiologists and economists.

The Difference Method Approach for Sampling Order Constrained Parameters: An Improved Implementation and Important Limitations.

A health economic model may include a set of related inputs whose true values are uncertain, but that can be assumed to follow a logical order. Various approaches are available for performing probabilistic sensitivity analysis while preserving the order constraint, one such approach is known as the difference method. The difference method approach appears to have many of the required properties, has been endorsed by good practice guidelines, and is likely to prove a popular approach. However, the proposed implementation of the difference method approach is cumbersome, requiring numerical estimation, which might present a barrier to its adoption. Furthermore, it is unclear whether the method can always be applied to three or more model inputs and whether it is unbiased across all possible input values. This study has investigated these three issues for ordered inputs bounded between 0 and 1. An analytic solution is given that allows for more straightforward and compact implementation. The difference method approach cannot always be applied to a set of three or more model inputs, and this depends on the relative size of the variances of the logit-transformed Beta distributions fitted to each variable. The approach can also produce samples with biased means and variances under certain combinations of input means and variances. It is recommended that the difference method approach be used where appropriate; however, an understanding of its limitations is necessary to identify such cases.

The role of digital transformation in supply chain efficiency and economic output.

From the perspective of sustainable supply chain management (SSCM), this research looks at the key elements influencing how small- and medium-sized companies (SMEs) move toward a circular economy (CE). This research aims to understand the elements that influence SMEs to embrace CE principles and determine the real-world applications of SSCM practices. This research gathered and analyzed data from diverse European SMEs working inside CE networks using a mixed-method approach. We received answers from several of these firms using a survey form sent and emailed to them. The replies were then assessed using an independent t test to account for any biases. We used confirmatory factor analysis (CFA) for the validity assessment, compound consistency, and corrected-item-total association measures to validate the model's validity and reliability. According to our research, SMEs are influenced significantly by societal pressures, green economic incentives, and environmental dedication when deciding whether to adopt CE practices. Our study further emphasizes the importance of SSCM for SMEs' successful transition to a CE model, especially regarding resource and waste management efficiency. This work contributes to the corpus of research on the topic by providing empirical support for the function of SSCM in easing the transition towards CE in the setting of SMEs. The results might serve as a reference for managers and policymakers as they create plans to encourage SMEs to embrace CE practices and to emphasize the advantages of such a change on the economic, social, and environmental fronts. Putting a particular emphasis on the vital roles that public pressure, green financial incentives, and ecological dedication play, this research provides insights into the complex interactions between SSCM and CE transition in SMEs. Further study is needed to examine how these determinants could fluctuate across various industries and geographies.

Photobiomodulation for Oral Mucositis - A Microcosting and Budget Impact Analysis from a Brazilian Perspective

ABSTRACT Objective: To measure the costs of preventive and therapeutic protocols of Photobiomodulation (PBM) for oral mucositis (OM) and their budgetary impact on Brazil's Ministry of Health (BMH). Material and Methods: A partial economic analysis was performed to estimate the costs using a bottom-up approach from a social perspective. Monetary values were assigned in Brazilian reais (BRL). The costs of the preventive protocol were calculated for five, 30, and 33 consecutive PBM sessions, depending on the antineoplastic treatment instituted. The costs of the therapeutic protocol were calculated for 5 or 10 sessions. The annual financial and budgetary impact was calculated considering the groups of oncologic patients with a higher risk of development of OM, such as those with head and neck and hematological cancer and pediatric patients. Results: The cost of a PBM session was estimated at BRL 23.75. The financial impact of providing one preventive protocol per year for all oncologic patients would be BRL 14,282,680.00, 0.030% of the estimated budget for hospital and outpatient care of the BMH in 2022. The financial and budgetary impacts of providing one treatment for OM for all patients in one year would be BRL 2,225,630.31 (0.005%, most optimistic scenario) and BRL 4,451,355.63 (0.009%, most pessimistic scenario). Conclusion: The budgetary impact of implementing PBM protocols in the Brazilian Healthcare System is small, even in a pessimistic scenario.

Effect of network size on comparing different stock networks.

We analyzed complex networks generated by the threshold method in the Korean and Indian stock markets during the non-crisis period of 2004 and the crisis period of 2008, while varying the size of the system. To create the stock network, we randomly selected N stock indices from the market and constructed the network based on cross-correlation among the time series of stock prices. We computed the average shortest path length L and average clustering coefficient C for several ensembles of generated stock networks and found that both metrics are influenced by network size. Since L and C are affected by network size N, a direct comparison of graph measures between stock networks with different numbers of nodes could lead to erroneous conclusions. However, we observed that the dependency of network measures on N is significantly reduced when comparing larger networks with normalized shortest path lengths. Additionally, we discovered that the effect of network size on network measures during the crisis period is almost negligible compared to the non-crisis periods.

The economic value of insulin glargine 300 U/mL (Gla-300) in people ≥18 years of age with type 2 diabetes mellitus: a value-based economic model from a U.S. payer perspective.

AIMS: This study aimed to evaluate the value and affordability of insulin glargine 300 U/mL (Gla-300) in a budget impact model from a United States (U.S.) payer perspective by leveraging recent real-world evidence (RWE) studies and incorporating the recent insulin price caps where applicable. MATERIALS AND METHODS: An economic model for a hypothetical one million U.S. health-plan population was developed to assess the budgetary impact of therapeutic interchanges in either direction between the two long- and longer-acting basal insulins (BIs) for patients with type 2 diabetes over a three-year model horizon. The utilization of long-acting BIs, longer-acting BIs, biosimilar BIs, and insulin degludec (IDeg-100) were informed by IQVIA data and internal forecasting at Sanofi. The DELIVER-2 and DELIVER-naïve studies provided healthcare resource utilization (HCRU) parameters. In the model base case, 24% of patients switched from long-acting BIs to insulin glargine biosimilars, IDeg-100, and other longer-acting BIs (Gla-300) by projected year 3. RESULTS: The base case total costs were $10,145 per patient per year (PPPY) in year 3 for the cumulative population. When all patients switched to Gla-300, the total costs in year 3 were $8,799, reflecting a net savings of -$660 PPPY compared to the budget increase of $686 PPPY in the base case. However, the longer-acting to long-acting BIs reversal scenario demonstrated a budgetary decrease of $676 PPPY over the model horizon. The reduction in incremental PPPY cost of $93 was observed using net drug costs rather than wholesale acquisition costs (WAC). LIMITATIONS: The market shares for years 1-3 were based on expectations supported by the clinicians' expert opinions and were not obtained from real-world data. CONCLUSIONS: The economic value of increased utilization of Gla-300 was driven by the reduction in HCRU, costs and market shares assumptions. Budgetary reductions were achieved by switching patients from long-acting BIs to Gla-300.

Type 2 Diabetes (T2D) is a chronic and debilitating condition that can lead to severe macro or microvascular complications. To mitigate these complications, it is crucial to effectively manage blood glucose levels. When other treatments prove ineffective in achieving adequate glucose control, insulin-based therapy becomes necessary. However, insulin-based treatments often come with the risk of hypoglycemic episodes, which can lead to increased utilization of healthcare resources (HCRU) and have a negative impact on costs.This study aimed to assess the budgetary impact of higher market shares of longer-acting basal insulins (specifically insulin glargine Gla-300) compared to long-acting basal insulins, insulin glargine biosimilars, and insulin degludec (IDeg) in the treatment of T2D. The perspective taken was that of a U.S. payer, taking into account the recent insulin price caps where applicable.The economic benefit of increased utilization of Gla-300 was driven by reductions in HCRU, costs, and market share assumptions. This resulted in a budgetary increase of $686 per patient per year (PPPY). In an alternative scenario where all patients transitioned to Gla-300, it led to a net savings of $660 PPPY.These findings provide valuable insights for decision-makers and healthcare professionals when making choices related to formulary placement and treatment utilization.

Hybrid deep learning models with multi-classification investor sentiment to forecast the prices of China's leading stocks.

The prediction of stock prices has long been a captivating subject in academic research. This study aims to forecast the prices of prominent stocks in five key industries of the Chinese A-share market by leveraging the synergistic power of deep learning techniques and investor sentiment analysis. To achieve this, a sentiment multi-classification dataset is for the first time constructed for China's stock market, based on four types of sentiments in modern psychology. The significant heterogeneity of sentiment changes in the sectors' leading stock markets is trained and mined using the Bi-LSTM-ATT model. The impact of multi-classification investor sentiment on stock price prediction was analyzed using the CNN-Bi-LSTM-ATT model. It finds that integrating sentiment indicators into the prediction of industry leading stock prices can enhance the accuracy of the model. Drawing upon four fundamental sentiment types derived from modern psychology, our dataset provides a comprehensive framework for analyzing investor sentiment and its impact on forecasting the stock prices of China's A-share market.