Erroneous Decisions Research Articles

Software Defect Estimation Using Machine Learning

Abstract: In recent years, software has become increasingly vital in our daily lives. We come across it in various forms like Alexa to automatic mops. Building a software is a huge task, it involves many stages. The developer is required to build or design a software within the given deadline and with the allotted budget. During which few erroneous decisions might be taken which lead to poor logic, improper design etc. That would make the user dissatisfied. In order to let the device achieve the users desired outcome we must build a flawless software. To build one as that, one must predict if any defects are present. As a result, we employ seven machine learning algorithms to assist us in predicting any software flaws

Automatically Correcting Noisy Labels for Improving Quality of Training Set in Domain-specific Sentiment Classification

Classification model performance can be degraded by label noise in the training set. The sentiment classification domain also struggles with this issue, whereby customer reviews can be mislabeled. Some customers give a rating score for a product or service that is inconsistent with the review content. If business owners are only interested in the overall rating picture that includes mislabeling, this can lead to erroneous business decisions. Therefore, this issue became the main challenge of this study. If we assume that customer reviews with noisy labels in the training data are validated and corrected before the learning process, then the training set can generate a predictive model that returns a better result for the sentiment analysis or classification process. Therefore, we proposed a mechanism, called polarity label analyzer, to improve the quality of a training set with noisy labels before the learning process. The proposed polarity label analyzer was used to assign the polarity class of each sentence in a customer review, and then polarity class of that customer review was concluded by voting. In our experiment, datasets were downloaded from TripAdvisor and two linguistic experts helped to assign the correct labels of customer reviews as the ground truth. Sentiment classifiers were developed using the k-NN, Logistic Regression, XGBoost, Linear SVM and CNN algorithms. After comparing the results of the sentiment classifiers without training set improvement and the results with training set improvement, our proposed method improved the average scores of F1 and accuracy by 20.59%.

Electrophysiological correlates of confidence differ across correct and erroneous perceptual decisions

Every decision we make is accompanied by an estimate of the probability that our decision is accurate or appropriate. This probability estimate is termed our degree of decision confidence. Recent work has uncovered event-related potential (ERP) correlates of confidence both during decision formation and after a decision has been made. However, the interpretation of these findings is complicated by methodological issues related to ERP amplitude measurement that are prevalent across existing studies. To more accurately characterise the neural correlates of confidence, we presented participants with a difficult perceptual decision task that elicited a broad range of confidence ratings. We identified a frontal ERP component within an onset prior to the behavioural response, which exhibited more positive-going amplitudes in trials with higher confidence ratings. This frontal effect also biased measures of the centro-parietal positivity (CPP) component at parietal electrodes via volume conduction. Amplitudes of the error positivity (Pe) component that followed each decision were negatively associated with confidence for trials with decision errors, but not for trials with correct decisions, with Bayes factors providing moderate evidence for the null in the latter case. We provide evidence for both pre- and post-decisional neural correlates of decision confidence that are observed in trials with correct and erroneous decisions, respectively. Our findings suggest that certainty in having made a correct response is associated with frontal activity during decision formation, whereas certainty in having committed an error is instead associated with the post-decisional Pe component. These findings also highlight the possibility that some previously reported associations between decision confidence and CPP/Pe component amplitudes may have been a consequence of ERP amplitude measurement-related confounds. Re-analysis of existing datasets may be useful to test this hypothesis more directly.

ON THE WAY TO QMS IMPLEMENTATION: THE MAIN MILESTONES AND ISSUES IN EMERGING ECONOMY

The aim of the research is to analyze typical problems in the implementation of quality management systems (QMS) on the basis of private production enterprises which operate in emerging economy context and to develop a rational strategic plan for the design and implementation of such a system, taking into account the experience of successful organizations. The main benefits of implementing QMS are presented. In the article it is recommended to consider the formation of QMS as a project with the appropriate stages of activities. The following positions are envisaged at the initiation stage: formalization of the decision on QMS implementation, appointment of project participants, project team training, as well as development of mission, vision, quality policy and QMS process structure. At the implementation stage, it is proposed to develop and approve QMS documents, as well as to implement an internal audit program. At the stage of project closure, it is advisable to put into operation the developed system and pass a certification audit in order to obtain a certificate of compliance with the requirements of ISO 9001. The article presents the structure, content, sequence and estimated duration of all the stages of the project, as well as the division of responsibilities between the project team members. Emphasis is placed on the main issues which can arise at different stages of such a project. In the paper the following range of issues was identified: inconsistency of QMS processes structure with the existing organizational structure of the enterprise; incorrect definition of the performance indicators for processes at different hierarchy levels; erroneous decisions in the internal documentation system organizing. In its turn, in the article the causes for the above-mentioned issues were identified, namely: insufficient motivation of project participants, lack of time or other necessary resources, unwillingness to change the current management system of the company, inconsistency of real goals with the stated ones, etc. In the article it is proposed to divide the main causes of issues into three basic groups: by project participants (personal), bureaucratic (systemic) and leadership (administrative). The authors propose a number of measures to minimize the risks of issues in the QMS implementation, and determine the distribution of areas of responsibility for these measures organizing.

Development methodology of metrological support of maintenance by the technical state of communication means

Peculiarities of metrological support for technical maintenance based on the condition of large-scale communication devices (tens and hundreds of thousands of elements) consisting of separate subsystems, whose functionality can be checked, maintenance and restoration of functionality can be performed autonomously, are considered. It is suggested to increase the efficiency of technical maintenance according to the condition to take into account the peculiarities of metrological support, to establish a rational sequence of operations, and to reasonably choose measuring equipment depending on the requirements. For this, the methodology uses a complex indicator that combines individual parameters of checks and the probability of their preferred choice. This makes it possible to assess the technical condition of the means of communication in a minimum time with a given probability. In addition, it is possible to quantitatively estimate the time of maintenance, taking into account metrological reliability and the probability of correct assessment of the result of checking parameters by means of measuring equipment. The procedure for using the obtained results is formalized and an example of implementation is given. For the first time, the results of the latest research in the field of technical and metrological support of means of communication during their technical operation are taken into account, namely, the possibility of erroneous assessment of the results of parameter checks, the possibility of failure of measuring equipment, which allows to significantly increase the probability of correct assessment of the technical condition of means of communication during their maintenance according to condition. In addition, taking into account modern achievements in technical diagnostics made it possible to quantitatively estimate the maximum value of the maintenance time based on the state of the means of communication and compare it with the acceptable value specified in the technical documentation. The functional dependencies of the proposed complex coefficient of the feasibility of each inspection, on the metrological reliability of the measuring equipment and the probability of erroneous decisions in the evaluation of the inspection values after measuring the relevant parameters, were obtained and investigated. The area of existence of solutions for calculating the complex coefficient from the quality of metrological support is defined. It is advisable to use the obtained results during the development of the technological process of maintenance of promising and existing means of communication, as well as when planning the activities of specialists during scheduled maintenance work on equipment at field and stationary communication nodes.

MODELING OF BUSINESS PROCESSES ON THE BASIS OF BUILDING AN OPTIMAL SYSTEM OF COMPLEXING ADAPTIVE-ORGANIZATIONAL MECHANISM MANAGEMENT OF ENTERPRISES

The article is devoted to topical issues of research of peculiarities of business process modeling on the basis of construction of optimal system of complexing of adaptive-organizational mechanism of management. The study developed a scientific approach to business process modeling based on the use of complex adaptive-organizational management mechanism through simulation modeling of business processes based on matrix construction, which gives a more accurate assessment of the system and more fully describes the cause-and-effect relationship –«status-adaptation-management-status» оn the enterprise. The researched description of the given functional dependences with use of a method of simulation modeling of business processes gives the chance to construct dynamics of forecast states of system of activity of the enterprise that will avoid erroneous decisions and will allow to construct subspace of management business-processes of the enterprise.

Информационно-алгоритмическое обеспечение эффективных систем управления

Modern production machinery is equipped with multifunctional automated process control systems (APCS) based on software and hardware complexes (SHC) of a network hierarchical structure. The experience of designing and operating multifunctional process control systems proves that the efficiency of the systems being developed significantly depends on the array of problems at different stages of the technology design and system modernization. It is to be developed, both at the fundamental level of local automatic control systems and at a higher level of hierarchical system structure. At the same time, special attention is paid to the software failure, which is fixed, as a rule, by periodically updating all the content. For process control systems, such an approach under the operation conditions of power equipment is unacceptable. In this regard, the effectivity problems of complex systems are to be classified in terms of technological process factors, the theory of automatic control and instrumental factors associated with the proper software implementation. As a theoretical basis to solve the problem of information sufficiency and synthesis of structurally stable systems, the methods of potentials and coordinates of the thermodynamics of irreversible processes are used. The testing method is applied as a tool to analyze and diagnose software and hardware tools. The authors have defined three groups of factors: system, controller and local. The task to analyze the conformity of information and algorithmic support means to expert and verify the absence of defects in the software of a multifunctional system and the fulfillment of the declared requirements. The automated testing system is a unified environment to analyze the execution of test scenarios. It provides continuous validation and verification of the information and algorithmic support of the SHC. In particular, a methodology has been developed to carry out resource tests of the software and hardware complex and checking the operation of the mechanisms for backing up, synchronizing, and replacing its components by simulating failures in the processor modules, hardware and software components. A set of methodological factors has been defined to develop advanced software and hardware systems for process control systems. It significantly affects the adequacy of the information and algorithmic support of a complex system. A technology of automated testing of software and hardware tools of the SHC has been developed. Methods to solve interdisciplinary problems are generalized. The authors recommend solving the problems at the earlier stages of a complex system design. The proposed technology to develop and diagnose automatically software and hardware of the SHC by implementing a single environment to study, compare and detect the defects of the SHC software throughout the entire life cycle of the process control system allows you to identify and eliminate the mutual negative influence of the SHC components both at the development stage and at the stage of the subsequent system organization, including solving the problem of information security at the stage of system installation and operation. The developed approach to solve complex interdisciplinary problems that require solution at the early stages of designing complex systems makes it possible to avoid fundamentally erroneous decisions and increase the competitiveness of the SHC as a systemically important APCS complex at the time of installation.

Automated control of complex metallurgical units based on the CBR method

The paper considers the actual problem of human-machine control of complex technological units and complexes, which are characterized by a large variety of states, multidimensionality, variability, and uncertainty. Such units in the ferrous metallurgy include coke batteries, blast furnaces, steelmaking units (arc furnaces, oxygen converters), foundry and rolling complexes, rolling mills, main workshops and production facilities. The effectiveness of the model approach to the creation of control systems for such objects is shown to be insufficient for the XXI century. Alternative approaches based on the concept of best reasoning (CBR) are considered. In particular, they include full-scale model and full-scale approaches to the development of support systems and management decision-making. The well-known full-scale model procedures for applying the best reasoning (methods of typical situations and exemplary technological cycles) are presented. The authors propose a new CBR method of automated selection and implementation of control actions with the participation of process operators for process control systems. A modified CBR-cycle of control selection and the corresponding functional scheme of the software control system for a cyclic technological unit were developed. The improved CBR-cycle includes the following additional operations: correction of control decisions for selected cases; retrospective optimization of implemented control decisions; preservation of not only the best and optimized, but also erroneous decisions; updating of the case base; formation of solutions in unique or previously unreported situations. The structure of the case information model is formed on the example of software control of steel melting in the conditions of an oxygen converter shop. It includes three sections: data on the specific situation in the control system, parameters of the selected control actions, and results of steel melting. An example of the control program formation for the preparation and execution of the upcoming steel melting is based on the data of a pre-selected melting case in the conditions of a modern oxygen converter process.

Improving the robustness and accuracy of biomedical language models through adversarial training

Deep transformer neural network models have improved the predictive accuracy of intelligent text processing systems in the biomedical domain. They have obtained state-of-the-art performance scores on a wide variety of biomedical and clinical Natural Language Processing (NLP) benchmarks. However, the robustness and reliability of these models has been less explored so far. Neural NLP models can be easily fooled by adversarial samples, i.e. minor changes to input that preserve the meaning and understandability of the text but force the NLP system to make erroneous decisions. This raises serious concerns about the security and trust-worthiness of biomedical NLP systems, especially when they are intended to be deployed in real-world use cases. We investigated the robustness of several transformer neural language models, i.e. BioBERT, SciBERT, BioMed-RoBERTa, and Bio-ClinicalBERT, on a wide range of biomedical and clinical text processing tasks. We implemented various adversarial attack methods to test the NLP systems in different attack scenarios. Experimental results showed that the biomedical NLP models are sensitive to adversarial samples; their performance dropped in average by 21 and 18.9 absolute percent on character-level and word-level adversarial noise, respectively, on Micro-F1, Pearson Correlation, and Accuracy measures. Conducting extensive adversarial training experiments, we fine-tuned the NLP models on a mixture of clean samples and adversarial inputs. Results showed that adversarial training is an effective defense mechanism against adversarial noise; the models’ robustness improved in average by 11.3 absolute percent. In addition, the models’ performance on clean data increased in average by 2.4 absolute percent, demonstrating that adversarial training can boost generalization abilities of biomedical NLP systems. This study takes an important step towards revealing vulnerabilities of deep neural language models in biomedical NLP applications. It also provides practical and effective strategies to develop secure, trust-worthy, and accurate intelligent text processing systems in the biomedical domain.

Uncertainty‐aware convolutional neural network for explainable artificial intelligence‐assisted disaster damage assessment

Accurate damage assessment is a critical step in post-disaster risk assessment, mitigation, and recovery. Current practices performed by experts and reconnaissance teams in the form of field evaluation require considerable time and resources. Recent advances in remote sensing imagery, artificial intelligence (AI), and computer vision have enhanced automated and rapid disaster damage assessment. Recent literature has shown promising progress in AI-assisted aerial damage assessment. However, accounting for the uncertainty in the outcome for improved quantification of confidence and enhanced model explainability for human decision-makers remains one of the key challenges. Overlooking uncertainty can lead to erroneous decisions, especially in highly-consequential tasks such as damage assessment. The aim of this study is to develop uncertainty-aware deep learning models for the assessment of post-disaster damage using aerial imaging. Within the framework of variational Bayesian inference, Monte Carlo dropout sampling technique is used to propagate epistemic uncertainty in model predictions. With this stochastic setting, the model produces damage prediction labels with softmax as random variables, which helps quantify confidence in the model outcome using appropriate measures of uncertainty. Two networks are implemented and trained separately on two different disaster damage datasets consisting of unmanned aerial vehicle building footage as well as satellite-captured post-disaster imagery. The first network attains 59.4% accuracy in building classification, and the second network gives an accuracy of 55.1%. Results from uncertainty analysis, model confidence quantification, and analyzing model attention zone can lead to more explainable and risk-informed automated damage assessment outcomes using AI technology.

Legal regulation of the use of scientific and technical means when solving crimes by employees of the criminal investigation department in Donbass in 1918–1953

The article reflects the main aspects of formation of legal regulation of the use of scientific and technical means when solving crimes by the employees of the criminal investigation department in Donbass in 19181953. A close relationship is indicated between the degree of introduction of scientific and technical means into the activities of operational officers of the criminal investigation department with the growth of quantitative and qualitative indicators in the fight against crime in Donbass in 19181953. Particular attention is paid to the interaction of operational and forensic departments of the internal affairs bodies in solving various types of crimes and there made it possible to effectively counteract crime and the growth of its most dangerous manifestations in the postwar years in the Soviet Union. It is summarized that on the basis of the accumulated experience, new research methods, scientific and technical methods were developed, which were introduced into the practice of criminal investigation. Supporting the need for direct cooperation of the investigative authorities with experts, it is indicated that it is inadmissible to make erroneous decisions based on the experts conclusions due to the influence of various factors.

Topical questions of population migration typology

The current international situation draws the attention of the whole society to the issues of population migration. The migration of millions of people causes concern both at the state and at the public level. Of great importance are theoretical scientific research that explains the content of these processes. A prerequisite for the development of a new concept of the migration policy of the Republic of Kazakhstan for 2022-2026 is the consideration of scientific foundations. Although there are studies on the topic of migration, there are not many works in the domestic literature regarding its typology and classification. If, when studying any topic, the conceptual apparatus and its classification are not determined, then there may be various misunderstandings, as a result of which erroneous decisions can be made. Therefore, the definition of the basic concepts, types, classifications of each phenomenon is of great importance. There are several options for the typology and classification of population migration among the scientific community. In this article, an analysis of fundamental and modern scientific opinions from near and far abroad on the topic is carried out, a typology of population migration is proposed. In addition, its difference from the classification of migration is indicated. This is a systematic work to make a reasonable contribution to a comprehensive understanding of the phenomenon of migration, its classification according to characteristics, the exchange of scientific opinions in the direction of the multiplicity of species. Keywords: population migration, typology of population migration, classification of population migration, signs of population migration.

Financial Literacy and New Business Entry

Abstract The issue of the relationship between financial literacy and entrepreneurship is still not a fully explored research area. On the one hand, there are common views that financial literacy and education in finance are necessary in every individual’s life, and that an insufficient level of financial literacy may result in erroneous economic decisions. On the other hand, research on the impact of narrowly defined financial literacy on business start-up decisions is still rare. As a result, there are no clear indications regarding the need for education in the area of finance in order to stimulate entrepreneurial decisions, including the survival of launched economic undertakings. This article deals with the relationship between financial literacy and chosen entrepreneurial aspects such as 1) Phases of Entrepreneurial Activity; 2) Entrepreneurial potential; 3) Motivation; 4) Involvement in the technology sector; and 5) Business exit reasons. All of the above aspects are embedded in the context of financial literacy. The article sheds light on the relationship between financial literacy and entrepreneurship and creates a background for further attempts to deepen understanding of this issue.

Limitation of Water Footprint Sustainability Assessment: A Review

Water is nature resource that is essential for all life, for the functioning of ecosystems, and also for the human society. Sustainable use of water resource is important for sustainable development of human society. Water scarcity can lead to conflicts between different water users. Therefore, several sustainability assessment tools were developed in recent years. Water Footprint Sustainability Assessment, which is a part of Water Footprint Assessment methodology, is one of them. Each sustainability assessment tool has its own limitations. It is important to know these limitations because incorrect application of sustainability assessment can lead to erroneous or improper decisions. In this article, risks connected to the Water Footprint Sustainability Assessment are reviewed and discussed in several examples. Individual parts are focused on blue, green, and grey water sustainability assessment. The article contributes to the scientific debate on limits of Water Footprint Sustainability Assessment as the key element of everyday applications, identification of needs of future research and subsequent development of new or improved procedures of sustainability assessment in the framework of Water Footprint Assessment.
 Keywords: volumetric water footprint; sustainability assessment; sustainable development; limitation of methodology

Accounting for Sampling Weights in the Analysis of Spatial Distributions of Disease Using Health Survey Data, with an Application to Mapping Child Health in Malawi and Mozambique.

Most analyses of spatial patterns of disease risk using health survey data fail to adequately account for the complex survey designs. Particularly, the survey sampling weights are often ignored in the analyses. Thus, the estimated spatial distribution of disease risk could be biased and may lead to erroneous policy decisions. This paper aimed to present recent statistical advances in disease-mapping methods that incorporate survey sampling in the estimation of the spatial distribution of disease risk. The methods were then applied to the estimation of the geographical distribution of child malnutrition in Malawi, and child fever and diarrhoea in Mozambique. The estimation of the spatial distributions of the child disease risk was done by Bayesian methods. Accounting for sampling weights resulted in smaller standard errors for the estimated spatial disease risk, which increased the confidence in the conclusions from the findings. The estimated geographical distributions of the child disease risk were similar between the methods. However, the fits of the models to the data, as measured by the deviance information criteria (DIC), were different.

Conditional power in vaccine trials with seasonal variations

ABSTRACT Conditional power (CP) is widely used in clinical trial monitoring to quantify the evidence for futility stopping or sample size adaptation during the trial. When planning an interim analysis in vaccine trials for seasonal infectious diseases, CPs calculated under the hypothesized or currently estimated effect sizes may not truly reflect future data due to seasonal variations in disease incidence and/or vaccine efficacy (VE). Relying on these estimates alone could lead to erroneous decisions. Therefore, we carried out simulation studies to investigate the use of seven different choices for the drift parameter in computing CP or predictive power (PP) in end-of-season interim analysis. Our simulations showed that, when used to inform futility stopping, CP under the hypothesized effect and a weighted PP under a normal prior distribution appear to outperform others in terms of the overall type II error rate. All CPs and PPs considered in this study resulted in comparable powers and expected sample sizes when used to inform sample size adaptation. The performance of either CP or PP largely depends on the extent to which the chosen drift parameter or the prior distribution of the drift parameter matches the remainder of the trial. Weighted CP/PP tends to be less sensitive to settings where observed data and emerging data in future seasons differ substantially as they incorporate both current estimate and future variations. Therefore, weighted strategies deserve further exploration and perhaps increased usage in guiding trial operations because they are more robust to inaccuracies in prediction. In summary, for vaccine trials with seasonal variations, a decision on trial operations should be guided by a careful consideration of plausible CPs and PPs calculated under reasonable assumptions leveraging the data, prior hypotheses, and new evidence on clinical relevance.

Decision Making Control Algorithm for Cogeneration Plants in Operating with the Heat Accumulator Deep Analysis Model

Accurate production planning in both the short and long term is very important in cogeneration plants. Especially if the cogeneration unit operates under free electricity market conditions, which complicates the decision-making process as an additional planning condition with variable heat, fuel, and CO2 costs. On the other hand, when a cogeneration plant uses a heat accumulation system, it is impossible to make a production decision without using a computer system; the human factor in decision-making can lead to erroneous decisions without traceability. The role of modern computer systems is growing and greatly influences the optimal production planning process in cogeneration plants, regardless of the installed capacity and in the operation with heat accumulation. One of the problems solved by the research is the integration of real operating modes and conditions (applied thermal insulation solution) into the production decision algorithms. The developed methodology allows not only to plan the operating modes of the cogeneration plant, but also to evaluate the efficiency of the battery solution. This study shows the developed methodology for calculating heat loss for a heat accumulator depending on the operating mode and the need to introduce a correction coefficient. When determining the total influencing expenses of the cost model of the heat accumulator operation mode, their mutual influence is shown and integrated into the decision-making algorithm for the next day's free-market conditions. The aim of the algorithm is maximally increasing the total gross revenue threshold for the planning of cogeneration operations and to exclude operating modes that may cause losses.

A ARBITRAGEM COMO MECANISMO DE RESOLUÇÃO DE CONFLITOS NOS PROCESSOS DE CONTRATAÇÕES PÚBLICAS

This text aims to present a discussion related to the use of arbitration in contracts with the government, more specifically, in public contracts. For this, methodologically based on the assumptions of qualitative research, bibliographical descriptive character, it was sought, from current legislation and doctrines, to establish some theoretical articulations related to the applicability of this principle in public administration. Such articulations show that the doctrine has been positioning itself in the sense that there is a certain division at the level of public interest regarding the analyzed object, in the sense that only when it is primary, that is, the nature of the collective is really essential, does it lack enjoy the unavailability of the public interest, but in other cases, which are of secondary interest and deal with economic situations, the use of arbitration by the Public Administration is fully acceptable and even beneficial. In addition, it appears that the procedure, when installed, results in extremely technical decisions, with expert referees, obeying efficiency and bringing speed to decisions in a country where there is still a lot to be done by the infrastructure sector, for example, warding off erroneous decisions by auctioneers and servers, who in most cases do not have the technical knowledge to make a decision.

Assessing and Enhancing Adversarial Robustness of Predictive Analytics: An Empirically Tested Design Framework

ABSTRACT As predictive analytics increasingly applies supervised machine learning (SML) models to inform mission-critical decision-making, adversaries become incentivized to exploit the vulnerabilities of these SML models and mislead predictive analytics into erroneous decisions. Due to the limited understanding and awareness of such adversarial attacks, the predictive analytics knowledge and deployment need a principled technique for adversarial robustness assessment and enhancement. In this research, we leverage the technology threat avoidance theory as the kernel theory and propose a research framework for assessing and enhancing the adversarial robustness of predictive analytics applications. We instantiate the proposed framework by developing a robust text classification system, the ARText system. The proposed system is rigorously evaluated in comparison with benchmark methods on two tasks extensively enabled by SML: spam review detection and spam email detection, which then confirmed the utility and effectiveness of our ARText system. Results from numerous experiments revealed that our proposed framework could significantly enhance the adversarial robustness of predictive analytics applications.

Using clinical decision support systems in breast cancer treatment: a critical review

Decision-making in breast cancer treatment is a complex process. There is no certainty of the effects of a treatment regimen in a specific patient and the consequences of erroneous decisions can be serious or even fatal for the patient. Clinical decision support systems (CDSSs) are technology aids that have been progressively introduced in clinical practice to reduce decision errors and improve the quality of clinical decisions.This article presents a critical review of the empirical literature on the use of CDSSs in breast cancer treatment decision-making. Three articles were included and two salient challenges identified in the design and research of CDSSs. First, there is a lack of standardisation in the tumour and patient factors and the health goals used to predict the benefit of different treatment options, as well as in the methods used for the evaluation of these. Second, the design of CDSSs follows a biomedical, disease-focused approach to healthcare, and this reductionist approach also prevails in the related scholarly literature.