Repetitive Decisions Research Articles

Predicting Adherence to Home-Based Cardiac Rehabilitation with Data-Driven Methods

Cardiac rehabilitation (CR) focuses on the improvement of health or the prevention of further disease progression after an event. Despite the documented benefits of CR programs, the participation remains suboptimal. Home-based CR programs have been proposed to improve uptake and adherence. The goal of this study was to apply an end-to-end methodology including machine learning techniques to predict the 6-month adherence of cardiovascular disease (CVD) patients to a home-based telemonitoring CR program, combining patients’ clinical information with their actual program participation during a short familiarization phase. Fifty CVD patients participated in such a program for 6 months, enabling personalized guidance during a phase III CR study. Clinical, fitness, and psychological data were measured at baseline, whereas actual adherence, in terms of weekly exercise session duration and patient heart rate, was measured using wearables. Hierarchical clustering was used to identify different groups based on (1) patients’ clinical baseline characteristics, (2) exercise adherence during the familiarization phase, and (3) the whole program adherence, whereas the output of the clustering was determined using repetitive decision trees (DTs) and random forest (RF) techniques to predict long-term adherence. Finally, for each cluster of patients, network analysis was applied to discover correlations of their characteristics that link to adherence. Based on baseline characteristics, patients were clustered into three groups, with differences in behavior and risk factors, whereas adherent, non-adherent, and transient adherent patients were identified during the familiarization phase. Regarding the prediction of long-term adherence, the most common DT showed higher performance compared with RF (precision: 80.2 ± 19.5% and 71.8 ± 25.8%, recall: 94.5 ± 14.5% and 71.8 ± 25.8% for DT and RF accordingly). The analysis of the DT rules and the analysis of the feature importance of the RF model highlighted the significance of non-adherence during the familiarization phase, as well as that of the baseline characteristics to predict future adherence. Network analysis revealed different relationships in different clusters of patients and the interplay between their behavioral characteristics. In conclusion, the main novelty of this study is the application of machine learning techniques combining patient characteristics before the start of the home-based CR programs with data during a short familiarization phase, which can predict long-term adherence with high accuracy. The data used in this study are available through connected health technologies and standard measurements in CR; thus, the proposed methodology can be generalized to other telerehabilitation programs and help healthcare providers to improve patient-tailored enrolment strategies and resource allocation.

Assessing Users’ Behavior on the Adoption of Digital Technologies in Management and Accounting Information Systems

The exponential trend of digital technologies, doubled by the mobility restrictions imposed during the COVID-19 pandemic, caused a paradigm shift in traditional economic models. Digital transformation has become increasingly common in all types of organizations and affects all activities. Organizations have adopted digital technologies to increase efficiency and effectiveness in management, marketing, and accounting. This paper aims to assess the impact of digital transformation on project management, marketing, and decision-making processes in users’ perceptions. The study begins with theoretical research on the digitalization of management and accounting information systems and conducts an empirical investigation based on a questionnaire. First, the paper assesses users’ perceptions of implementing digital technologies. The answers of 442 professionals from project management, marketing, and decision making were processed using structural equation modeling. The results show that users’ acceptance of digitalization is higher in decision making due to the significant contribution of artificial intelligence in repetitive decision making. Project management and marketing also benefit from digitalization, yet non-repetitive activities remain mainly the responsibility of the human factor.

Robust experience replay sampling for multi-agent reinforcement learning

• Propose new algorithms for acquiring suitable experiences from buffer through filtering. • Strengthen exploration strategy by reducing repetitive decisions at a given state. • Improve performance which is higher than or comparable to the baseline algorithms. • Achieve early convergence and improved policy searching compared to the baselines. Learning from the relevant experiences leads to fast convergence if the experiences provide useful information. We present the new and simple yet efficient technique to find suitable samples of experiences to train the agents in a given state of an environment. We intended to increase the number of states visited and unique sequences that efficiently reduce the number of states the agents have to explore or exploit. Our technique implicitly introduces additional strength to the exploration-exploitation trade-off. It filters the samples of experiences that can benefit more than half the number of agents and then utilizes the experiences to extract useful information for decision making. First, we compute the similarities between the observed state and previous states in the experiences to achieve this filtering. Then, we filter the samples using the hyper-parameter, z , to decide which experiences will be suitable. We found out that agents learn quickly and efficiently since sampled experiences provide useful information that speeds up convergence. In every episode, most agents learn or contribute to improve the total expected future return. We further study our approaches’ generalization ability and present different settings to show significant improvements in diverse experiment environments.

Decision fatigue in low-value prostate cancer screening.

Low-value prostate-specific antigen (PSA) testing is common yet contributes substantial waste and downstream patient harm. Decision fatigue may represent an actionable target to reduce low-value urologic care. The objective of this study was to determine whether low-value PSA testing patterns by outpatient clinicians are consistent with decision fatigue. Outpatient appointments for adult men without prostate cancer were identified at a large academic health system from 2011 through 2018. The authors assessed the association of appointment time with the likelihood of PSA testing, stratified by patient age and appropriateness of testing based on clinical guidelines. Appointments included those scheduled between 8:00am and 4:59pm, with noon omitted. Urologists were examined separately from other clinicians. In 1,581,826 outpatient appointments identified, the median patient age was 54years (interquartile range, 37-66years), 1,256,152 participants (79.4%) were White, and 133,693 (8.5%) had family history of prostate cancer. PSA testing would have been appropriate in 36.8% of appointments. Clinicians ordered testing in 3.6% of appropriate appointments and in 1.8% of low-value appointments. Appropriate testing was most likely at 8:00am (reference group). PSA testing declined through 11:00am (odds ratio [OR], 0.57; 95% CI, 0.50-0.64) and remained depressed through 4:00pm (P<.001). Low-value testing was overall less likely (P<.001) and followed a similar trend, declining steadily from 8:00am (OR, 0.48; 95% CI, 0.42-0.56) through 4:00pm (P<.001; OR, 0.23; 95% CI, 0.18-0.30). Testing patterns in urologists were noticeably different. Among most clinicians, outpatient PSA testing behaviors appear to be consistent with decision fatigue. These findings establish decision fatigue as a promising, actionable target for reducing wasteful and low-value practices in routine urologic care. Decision fatigue causes poorer choices to be made with repetitive decision making. This study used medical records to investigate whether decision fatigue influenced clinicians' likelihood of ordering a low-value screening test (prostate-specific antigen [PSA]) for prostate cancer. In more than 1.5 million outpatient appointments by adult men without prostate cancer, the chances of both appropriate and low-value PSA testing declined as the clinic day progressed, with a larger decline for appropriate testing. Testing patterns in urologists were different from those reported by other clinicians. The authors conclude that outpatient PSA testing behaviors appear to be consistent with decision fatigue among most clinicians, and interventions may reduce wasteful testing and downstream patient harms.

A systematic literature review on intelligent automation: Aligning concepts from theory, practice, and future perspectives

With the recent developments in robotic process automation (RPA) and artificial intelligence (AI), academics and industrial practitioners are now pursuing robust and adaptive decision making (DM) in real-life engineering applications and automated business workflows and processes to accommodate context awareness, adaptation to environment and customisation. The emerging research via RPA, AI and soft computing offers sophisticated decision analysis methods, data-driven DM and scenario analysis with regard to the consideration of decision choices and provides benefits in numerous engineering applications. The emerging intelligent automation (IA) – the combination of RPA, AI and soft computing – can further transcend traditional DM to achieve unprecedented levels of operational efficiency, decision quality and system reliability. RPA allows an intelligent agent to eliminate operational errors and mimic manual routine decisions, including rule-based, well-structured and repetitive decisions involving enormous data, in a digital system, while AI has the cognitive capabilities to emulate the actions of human behaviour and process unstructured data via machine learning, natural language processing and image processing. Insights from IA drive new opportunities in providing automated DM processes, fault diagnosis, knowledge elicitation and solutions under complex decision environments with the presence of context-aware data, uncertainty and customer preferences. This sophisticated review attempts to deliver the relevant research directions and applications from the selected literature to the readers and address the key contributions of the selected literature, IA’s benefits, implementation considerations, challenges and potential IA applications to foster the relevant research development in the domain.

Low‐value Prostate Cancer Screening: Decision Fatigue in Outpatient Providers’ PSA Testing Practices

Research ObjectiveLow‐value prostate‐specific antigen (PSA) testing is responsible for substantial waste and potential harm to patients, yet it accounts for nearly half of prostate cancer (PCa) screening. Decision fatigue, the progressive decline in consistency and quality of choices with repetitive decision making, has been observed in breast and colorectal cancer care. Our aim was to determine whether low‐value PSA testing patterns by outpatient providers are consistent with decision fatigue.Study DesignOutpatient encounters across various specialties were stratified by clinical guidelines as whether a PSA test order would be appropriate or low value. The primary endpoint was whether a PSA test was ordered. Logistic generalized estimating equations were used to analyze PSA test likelihood by appropriateness, with spline functions representing trends by hour. Models were adjusted for patient‐, provider‐, and appointment‐level factors and stratified by specialty.Population StudiedMen without PCa at a large academic health system from July 2011 to June 2018 were identified. In total, 1,761,815 outpatient visits were completed by this cohort of men during the specified time period.Principal FindingsOf these 1,761,815 outpatient encounters, a PSA test was ordered during 3.7% when it would be considered appropriate and 1.8% when it was low value. The overall likelihood of an encounter resulting in any PSA test was greatest at 8:00am, tapering off by 12:00pm (OR = 0.66; 0.58–0.75) and persisting at this nadir through 4:00pm (OR = 0.65; 0.56–0.77). Testing patterns differed between specialties, with nonurologists exhibiting a proportionately greater decline in the likelihood of ordering an appropriate test as the day progressed. Urologists showed a different pattern, with appropriate decisions relatively preserved throughout the day even as inappropriate testing declined in the middle of the day.ConclusionsIn a framework where PSA testing decisions are considered complex and the default position is to not test, PSA testing among nonurologists is consistent with decision fatigue. That is, testing is most likely early in the day when complex decisions are easiest. The pattern of PSA testing among urologists is different and may not be explained by decision fatigue. This may be due to differences in the default position for testing or greater PSA testing expertise, which lightens the cognitive load of decision making.Implications for Policy or PracticeFuture efforts to improve value and reduce waste in PSA testing might employ clinical decision support, which has been shown to be an effective intervention in the setting of decision fatigue. Interventions should ideally be tailored to each specialty’s unique needs.Primary Funding SourceNational Institutes of Health.

A data-driven methodology for the automated configuration of online algorithms

With the goal of devising algorithms for decision support in operational tasks, we introduce a new methodology for the automated configuration of algorithms for combinatorial online optimization problems. The procedure draws upon available instance data and is capable of recognizing data patterns which prove beneficial to the overall outcome. Since online optimization requires repetitive decision making without complete future information, no online algorithm can be optimal for every instance and it is reasonable to restrict attention to rule-based algorithms. We consider such algorithms in the form of procedures which derive their decisions using a threshold value. Threshold values are computed by evaluating a mathematical term (threshold value expression) composed of the available instance data elements. The goal then consists of determining the structure of the threshold value expression leading to the best algorithm performance. To this end, we employ a simulated annealing scheme returning the most favorable term composition given the available instance data. The resulting methodology can be implemented as part of data-driven decision support systems in order to facilitate knowledge-based decision making. Decision rules are generated in an automated fashion once historical input data is provided. The methodology is successfully instantiated in a series of computational experiments for three classes of combinatorial online optimization problems (scheduling, packing, lot sizing). Results show that automatically configured online algorithms are even capable of substantially outperforming well-known online algorithms in respective problem settings. We attribute this effect to the methodology's capability of integrating instance data into the process of algorithm configuration.

An integrated conceptual framework of decision-making in soccer refereeing

ABSTRACT Decision-making (DM) is a critical aspect of soccer refereeing. Referees make numerous repetitive decisions, many of which are dependent on appropriate field location and effective interaction with their assistants. Considering the complexity of the sequential DM process, it is not surprising that referees exhibit high decision error rates. Most extant research has focused on the underlying mechanism of the DM process as well as on various influential factors. Less attention has been given to models that consider the range of influential factors which affect the DM process. This article, therefore, presents a new conceptual framework of sequential DM for soccer referees that relies on Tenenbaum’s (2003. Expert athletes: An integrated approach to decision making. In J. Starkes & A. Ericsson (Eds.), Expert performance in sports: Advances in research on sport expertise (pp. 191–218). Human Kinetics) conceptual framework and the existing literature. We start by reviewing research on DM in soccer refereeing and then discuss conceptual considerations. We then present the new conceptual framework. This model incorporates a range of factors, including physical fitness and fatigue, field positioning, visual attention, contextual factors, game management, expertise, psychological factors, and team factors. Data obtained from a sample of 20 elite referees and assistants demonstrated the face validity of the new model. Finally, we introduce implications for training referees’ DM skills and highlight avenues for future research and conceptual developments.

Erectile dysfunction management after failed phosphodiesterase-5-inhibitor trial: a cost-effectiveness analysis.

To evaluate the cost-effectiveness of alternate erectile dysfunction (ED) management options after failed first line phosphodiesterase-5-inhibitors (PDE5-I). An empiric, repetitive decision tree analysis model was constructed using literature review and expert clinical judgement. This assessed the expected costs and quality adjusted life years (QALYs) of decision alternatives over a 10-year period. The model incorporated interventions including alternate PDE5-Is, intracorporal injections (ICI) with alprostadil or trimix (alprostadil, phentolamine, and papaverine), and inflatable penile prosthesis placement (IPP) and included respective risks of failure, subsequent interventions, and other complications (including priapism risk). Average model QALY estimates obtained from the literature were as follows: ED =0.56, successful alternate PDE5-I =0.70, successful ICI =0.70, and successful IPP =0.78. Cost data were calculated from a high-volume academic center and published manufacturer data. Over the 10-year period, IPP placement was the most cost-effective management option per preserved QALY (QALY =7.82, cost =$22,009/10 years) as compared to ICI alprostadil (QALY =8.51, cost =$62,890/10 years), ICI trimix (QALY =8.47, cost =$48,617/10 years) and alternate PDE5-I (QALY =7.73, $52,883/10 years). Using expert opinion and published utility, cost, and complication data in a decision analysis, we demonstrated that IPP placement is the most cost-effective ED intervention following failed initial PDE5-I over a 10-year period as compared to alternate treatment options. Such cost-effectiveness outcomes may be used in ED management counseling.

Striatal Microstimulation Induces Persistent and Repetitive Negative Decision-Making Predicted by Striatal Beta-Band Oscillation

Persistent thoughts inducing irrationally pessimistic and repetitive decisions are often symptoms of mood and anxiety disorders. Regional neural hyperactivities have been associated with these disorders, but it remains unclear whether there is a specific brain region causally involved in these persistent valuations. Here, we identified potential sources of such persistent states by microstimulating the striatum of macaques performing a task by which we could quantitatively estimate their subjective pessimistic states using their choices to accept or reject conflicting offers. We found that this microstimulation induced irrationally repetitive choices with negative evaluations. Local field potentials recorded in the same microstimulation sessions exhibited modulations of beta-band oscillatory activity that paralleled the persistent negative states influencing repetitive decisions. These findings demonstrate that local striatal zones can causally affect subjective states influencing persistent negative valuation and that abnormal beta-band oscillations can be associated with persistency in valuation accompanied by an anxiety-like state.

A general modeling approach to online optimization with lookahead

A vast number of real world problems are coined by an information release over time and the related need for repetitive decision making over time. Optimization problems arising in this context are called online since decisions have to be made although not all data is known. Due to technological advances, algorithms may also resort to a limited preview (lookahead) on future events. We first embed the paradigm of online optimization with lookahead into the theory of optimization and develop a concise understanding of lookahead. We further find that the effect of lookahead can be decomposed into an informational and a processual component. Based on analogies to discrete event systems, we then formulate a generic modeling framework for online optimization with lookahead and derive a classification scheme which facilitates a thorough categorization of different lookahead concepts. After an assessment of performance measurement approaches with relevance to practical needs, we conduct a series of computational experiments which illustrate how the general concept of lookahead applies to specific instantiations and how a knowledge pool on lookahead effects in applications can be built up using the general classification scheme.

Experimental evidence on case-based decision theory

This paper starts out from the proposition that case-based decision theory (CBDT) is an appropriate tool to explain human decision behavior in situations of structural ignorance. Although the developers of CBDT suggest its reality adequacy, CBDT has not yet been tested empirically very often, especially not in repetitive decision situations. Therefore, our main objective is to analyse the decision behavior of subjects in a repeated-choice experiment by comparing the explanation power of CBDT to reinforcement learning and to classical decision criteria under uncertainty namely maximin, maximax, and pessimism-optimism. Our findings substantiate a predominant significantly higher validity of CBDT compared to the classical criteria and to reinforcement learning. For this reason, the experimental results confirm the suggested reality adequacy of CBDT in repetitive decision situations of structural ignorance.

Economic Analysis of Hepatitis B Screening and Treatment

Economic Analysis of Hepatitis B Screening and Treatment

A new process-based ontology for KBE system implementation: application to inspection process planning

This paper focuses in the definition of a new ontology (Onto-Process) and the resulting informal model. The developed ontology constitutes an improvement to other ontologies since it covers the requirements of manufacturing processes engineering and, in particular, the inspection planning process with automated machines. Inspection planning activity usually implies to make repetitive and well-known decisions. These decisions are often based on the knowledge of inspection operators; therefore, it is a good candidate for implementing a knowledge-based engineering system. The sequence of activities involved in the inspection planning has been identified using Icam definition diagrams (IDEF0) in order to express the knowledge at a high level. These diagrams constitute an important support for defining the sequence of activities and the information flow. Later on, this information has been analyzed in depth using conceptual maps and it has been classified into units of knowledge. Then, each of these units of knowledge is decomposed into elementary objects of knowledge and relationships among them are defined. In a first approach, the ontology has been tested using a very particular but essential task in inspection planning: the activity related to the definition of contact points over inspection surfaces. In this activity, decisions must be made about the number, distribution, and sequencing of points. In the methodology developed in this paper the differences between form and non-form error inspection is considered. Finally, the knowledge required to support these decisions is represented using Onto-Process.

Conceptual principles and ontology for a KBE implementation in inspection planning

The inspection process planning with coordinate measuring machines involves repetitive and well-known decisions to make about the different strategies to use, although much of this knowledge is today implicit in the expert mind. Therefore, the inspection planning is a good activity for implementing knowledge-based engineering (KBE) systems. However, the origin of KBE is in the design activity and, traditionally, the different methodologies have been applied to that activity. In this paper, the focus is the application of a known methodology traditionally used in the design process to the inspection process with coordinate measuring machines. The paper considers the knowledge elicitation phase, that is, the knowledge identification before its formalisation and implementation in a platform. The identification of knowledge is done in a high-abstraction level using a combination of IDEF0 diagrams and a text analysis application. The knowledge extracted was represented in a first approximation by means of a modified ontology to adapt the original MOKA ontology to the inspection process.

How Incorporating Feedback Mechanisms in a DSS Affects DSS Evaluations

Model-based decision support systems (DSS) improve performance in many contexts that are data-rich, uncertain, and require repetitive decisions. But such DSS are often not designed to help users understand and internalize the underlying factors driving DSS recommendations. Users then feel uncertain about DSS recommendations, leading them to possibly avoid using the system. We argue that a DSS must be designed to induce an alignment of a decision maker's mental model with the decision model embedded in the DSS. Such an alignment requires effort from the decision maker and guidance from the DSS. We experimentally evaluate two DSS design characteristics that facilitate such alignment: (i) feedback on the upside potential for performance improvement and (ii) feedback on corrective actions to improve decisions. We show that, in tandem, these two types of DSS feedback induce decision makers to align their mental models with the decision model, a process we call deep learning, whereas individually these two types of feedback have little effect on deep learning. We also show that deep learning, in turn, improves user evaluations of the DSS. We discuss how our findings could lead to DSS design improvements and better returns on DSS investments.

Diversity of ability and cognitive style for group decision processes

This research investigates the potential for two forms of error diversity (ability diversity and diversity of cognitive style) to increase the accuracy of multi-agent group decision processes. An experimental methodology is employed that rigorously controls for the sources of error diversity. The results indicate that ability diversity decreases group decision errors by approximately 4%. Cognitive diversity is much more effective; decision errors are reduced by approximately 13% by groups formed from four cognitive classes. As sources of ability and cognitive diversity increase, the generalization error of the group decision decreases, and the prominence of the most capable member (i.e., expert) in the group diminishes. Thus, the popular reliance on using more capable members to create high performance homogenous groups may be misguided. This research indicates that a better strategy is to create groups of members that ‘think differently’ and cooperate to produce a group decision. Using this strategy, we are able to reduce the group decision error in two bankruptcy detection data sets by 11–47%. Reductions of this magnitude in high volume, high value, and repetitive decision environments characterizing the financial domain are extremely significant, where error reductions of even a fraction of a percent are welcome.

Customer retention and cross-buying in the banking industry: An integration of service attributes, satisfaction and trust

Most previous studies have focused on customer retention and have ignored the importance of customers’ cross-buying behaviour. Customer retention seems to be the result of a kind of repetitive decision by the customers, but their decision to cross-buy involves a more complicated process. In this study, the authors examine the effects of locational convenience, one-stop shopping convenience, firm reputation, firm expertise, and direct mailings on both customer retention and cross-buying. The mediating roles of satisfaction and trust in the relationships between service attributes, customer retention, and cross-buying are also examined. The results indicate that banks can use different service attributes to influence customer retention and cross-buying. Trust and satisfaction play different mediating roles in the relationships between service attributes, customer retention, and cross-buying.

The impact of the risk of consequence on the relative demand for continuous online assurance

This study analyzes the impact of the risk of consequence on the demand for continuous online assurance (COA) when making repetitive valuation and choice decisions. Participants in four laboratory settings choose whether to purchase COA to aid in making repetitive decisions. One valuation and one choice setting each offer COA at its mean price of indifference while two other settings price COA substantially lower (at a greater risk of consequence). Participants are compensated for making correct decisions while minimizing purchases. Results indicate that COA demand is (1) greater and more consistent when making repetitive valuation decisions than choice decisions, especially with an increase in risk of consequence, (2) greater and more consistent when making repetitive valuation decisions with an increase in the risk of consequence, but (3) only marginally greater when making repetitive choice decisions with an increase in the risk of consequence. The impact of these results on the development of COA is discussed.

A receiver with iterative soft decision and forward error correction

As a receiving method suitable for channels with intersymbol interference such as frequency selective fading, a method is proposed in which the soft decision using the hard decision sequence generated from the data after forward error correction (FEC) is alternated with FEC. In the conventional receiver with a serial configuration of the equalizer, deinverter, and decoder, the performance of the equalizer significantly affects the overall receiver characteristics. Hence, the performance of the equalizer is emphasized. On the other hand, in the proposed method the error generated in the initial equalization can be corrected by repetitive soft decision and FEC. Therefore, the method does not strongly depend on the performance of the equalizer used in the initial equalization. Hence, even if an equalizer requiring a smaller amount of process with a somewhat degraded performance is used in the initial equalization in place of a high-performance equalizer, the amount of process for the entire receiver can be decreased without degrading the characteristics of the proposed method very much. In this paper, the characteristics of the proposed method are evaluated by computer simulation. The following are the confirmed conclusions. (1) The proposed method using the maximum-likelihood sequence estimation (MLSE) as the equalization has superior BER characteristics over the conventional method using a maximum a posteriori (MAP) equalizer and MLSE. (2) In a transmission channel with a large delay spread, the degradation of the BER characteristics of the proposed method using the delayed decision-feedback sequence estimation (DDFSE) in place of MLSE is very slight while the amount of processing can be reduced substantially from that in the conventional method using MLSE. © 2000 Scripta Technica, Electron Comm Jpn Pt 1, 83(9): 76–85, 2000