Artificial Intelligence-based Decision Support Research Articles

Optimizing discharge after major surgery using an artificial intelligence–based decision support tool (DESIRE): An external validation study

BackgroundIn the DESIRE study (Discharge aftEr Surgery usIng aRtificial intElligence), we have previously developed and validated a machine learning concept in 1,677 gastrointestinal and oncology surgery patients that can predict safe hospital discharge after the second postoperative day. Despite strong model performance (area under the receiver operating characteristics curve of 0.88) in an academic surgical population, it remains unknown whether these findings can be translated to other hospitals and surgical populations. We therefore aimed to determine the generalizability of the previously developed machine learning concept. MethodsWe externally validated the machine learning concept in gastrointestinal and oncology surgery patients admitted to 3 nonacademic hospitals in The Netherlands between January 2017 and June 2021, who remained admitted 2 days after surgery. Primary outcome was the ability to predict hospital interventions after the second postoperative day, which were defined as unplanned reoperations, radiological interventions, and/or intravenous antibiotics administration. Four forest models were locally trained and evaluated with respect to area under the receiver operating characteristics curve, sensitivity, specificity, positive predictive value, and negative predictive value. ResultsAll models were trained on 1,693 epsiodes, of which 731 (29.9%) required a hospital intervention and demonstrated strong performance (area under the receiver operating characteristics curve only varied 4%). The best model achieved an area under the receiver operating characteristics curve of 0.83 (95% confidence interval [0.81–0.85]), sensitivity of 77.9% (0.67–0.87), specificity of 79.2% (0.72–0.85), positive predictive value of 61.6% (0.54–0.69), and negative predictive value of 89.3% (0.85–0.93). ConclusionThis study showed that a previously developed machine learning concept can predict safe discharge in different surgical populations and hospital settings (academic versus nonacademic) by training a model on local patient data. Given its high accuracy, integration of the machine learning concept into the clinical workflow could expedite surgical discharge and aid hospitals in addressing capacity challenges by reducing avoidable bed-days.

Customer models for artificial intelligence-based decision support in fashion online retail supply chains

Fashion is a global, multi-trillion dollar industry devoted to producing and selling clothing, footwear, and accessories to individuals or groups of people. Its sheer numbers, together with social and environmental sustainability concerns, and the move towards digitalization of customer-centric operations, make the fashion business a prime target for Decision Support Systems (DSSs). On the other hand, decision support in fashion retail is particularly problematic and embraces all major supply chain domains. Decisions in an online fashion retail supply chain (FRSC) are highly dependent on time-varying customers' preferences and product availability, often leading to a combinatorial explosion. To address such a problem, DSSs could greatly benefit from high-quality information stored in customer models (CMs), constructed by using Artificial Intelligence techniques, allowing informed decisions on how to personalize (adapt) to match the customer's needs and preferences. Combinations of CMs with recommender systems (RSs) have been increasingly utilized in fashion e-commerce to provide personalized product recommendations. Nevertheless, works on enhancing CMs for e-commerce or other decision-making chain domains are scanty. This paper offers a systematic review of the literature on fashion CMs with applications to decision-making in FRSCs, mining topics for a research agenda. Research on the theme is relevant and urgent for the fashion business, which is still in its infancy. Work on the agenda topics could benefit distinct fashion stakeholders, not just customers, and produce well-grounded decision-making in varied FRSC contexts and dynamics.

Comparison of Insulin Dose Adjustments Made by Artificial Intelligence-Based Decision Support Systems and by Physicians in People with Type 1 Diabetes Using Multiple Daily Injections Therapy.

Objective: Artificial intelligence-based decision support systems (DSS) need to provide decisions that are not inferior to those given by experts in the field. Recommended insulin dose adjustments on the same individual data set were compared among multinational physicians, and with recommendations made by automated Endo.Digital DSS (ED-DSS). Research Design and Methods: This was a noninterventional study surveying 20 physicians from multinational academic centers. The survey included 17 data cases of individuals with type 1 diabetes who are treated with multiple daily insulin injections. Participating physicians were asked to recommend insulin dose adjustments based on glucose and insulin data. Insulin dose adjustments recommendations were compared among physicians and with the automated ED-DSS. The primary endpoints were the percentage of comparison points for which there was agreement on the trend of insulin dose adjustments. Results: The proportion of agreement and disagreement in the direction of insulin dose adjustment among physicians was statistically noninferior to the proportion of agreement and disagreement observed between ED-DSS and physicians for basal rate, carbohydrate-to insulin ratio, and correction factor (P < 0.001 and P ≤ 0.004 for all three parameters for agreement and disagreement, respectively). The ED-DSS magnitude of insulin dose change was consistently lower than that proposed by the physicians. Conclusions: Recommendations for insulin dose adjustments made by automatization did not differ significantly from recommendations given by expert physicians regarding the direction of change. These results highlight the potential utilization of ED-DSS as a useful clinical tool to manage insulin titration and dose adjustments.

Artificial intelligence-based decision support model for new drug development planning

New drug development guarantees a very high return on success, but the success rate is extremely low. Pharmaceutical companies have attempted to use various strategies to increase the success rate of drug development, but this goal has been difficult to achieve. In this study, we developed a model that can guide effective decision-making at the planning stage of new drug development by leveraging machine learning. The Drug Development Recommendation (DDR) model, we present here, is a hybrid model for recommending and/or predicting drug groups suitable for development by individual pharmaceutical companies. It combines association rule learning, collaborative filtering, and content-based filtering approaches for enterprise-customized recommendations. In the case of content-based filtering applying a random forest classification algorithm, the accuracy and area under curve were 78% and 0.74, respectively. In particular, the DDR model was applied to predict the success probability of companies developing Coronavirus disease 2019 (COVID-19) vaccines. It was demonstrated that the higher the predicted score from the DDR model, the more progress in the clinical phase of the COVID-19 vaccine development. Although our approach has limitations that should be improved, it makes scientific as well as industrial contributions in that the DDR model can support rational decision-making prior to initiating drug development by considering not only technical aspects but also company-related variables.

Digital Health Policy and Programs for Hospital Care in Vietnam: Scoping Review.

BackgroundThere are a host of emergent technologies with the potential to improve hospital care in low- and middle-income countries such as Vietnam. Wearable monitors and artificial intelligence–based decision support systems could be integrated with hospital-based digital health systems such as electronic health records (EHRs) to provide higher level care at a relatively low cost. However, the appropriate and sustainable application of these innovations in low- and middle-income countries requires an understanding of the local government’s requirements and regulations such as technology specifications, cybersecurity, data-sharing protocols, and interoperability.ObjectiveThis scoping review aims to explore the current state of digital health research and the policies that govern the adoption of digital health systems in Vietnamese hospitals.MethodsWe conducted a scoping review using a modification of the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. PubMed and Web of Science were searched for academic publications, and Thư Viện Pháp Luật, a proprietary database of Vietnamese government documents, and the Vietnam Electronic Health Administration website were searched for government documents. Google Scholar and Google Search were used for snowballing searches. The sources were assessed against predefined eligibility criteria through title, abstract, and full-text screening. Relevant information from the included sources was charted and summarized. The review process was primarily undertaken by one researcher and reviewed by another researcher during each step.ResultsIn total, 11 academic publications and 20 government documents were included in this review. Among the academic studies, 5 reported engineering solutions for information systems in hospitals, 2 assessed readiness for EHR implementation, 1 tested physicians’ performance before and after using clinical decision support software, 1 reported a national laboratory information management system, and 2 reviewed the health system’s capability to implement eHealth and artificial intelligence. Of the 20 government documents, 19 were promulgated from 2013 to 2020. These regulations and guidance cover a wide range of digital health domains, including hospital information management systems, general and interoperability standards, cybersecurity in health organizations, conditions for the provision of health information technology (HIT), electronic health insurance claims, laboratory information systems, HIT maturity, digital health strategies, electronic medical records, EHRs, and eHealth architectural frameworks.ConclusionsResearch about hospital-based digital health systems in Vietnam is very limited, particularly implementation studies. Government regulations and guidance for HIT in health care organizations have been released with increasing frequency since 2013, targeting a variety of information systems such as electronic medical records, EHRs, and laboratory information systems. In general, these policies were focused on the basic specifications and standards that digital health systems need to meet. More research is needed in the future to guide the implementation of digital health care systems in the Vietnam hospital setting.

Value co-creation ‘gradients’: enabling human-machine interactions through AI-based DSS

Artificial Intelligence-based Decision Support Systems (AI-based DSS) are becoming increasingly important in many contexts. This work aims to define a type of human-machine interactions for new value co-creation processes' ranks, to help identify factors that can stimulate value co-creation in human-machine interactions. To understand if the outcome of a man-machine interaction can contribute to the co-creation of value, and in what way, the work carried out is epistemological and typological, also based on System Thinking. A matrix of novel gradients of the relationships between humans and non-humans has been created, and the typology of human-machine interactions has been identified for the new degrees of value co-creation processes, as well as the new specific scale of skills, in terms of language, learning, know-how, level of trust and endowment of knowledge, as a whole. The main implications concern the need to customize Decision Support Systems (DSS), to enhance different levels of intensity of relationships, and to identify insights for Decision Making AI - based users.

Sustainable production in cement via artificial intelligence based decision support system: Case study

CEM III cement is the mixture of ground granulated blast furnace slag (GGBS) and Portland cement clinker. Portland cement clinker has been effectively substituted by GGBS in order to improve strength and performance concrete supplying both economic and environmental benefits such as resource and energy savings. The activity index of the GGBS is positively correlated with the 28-day compressive strengths of CEM III mix cements. However, it is necessary to wait for a test period of 28 days for the acquisition of the activity index value of granulated blast furnace slag. This situation negatively impacts the cost of production, product quality and the environmental impacts of the product. Therefore, it is required to have a decision support system that can predict the activity index without waiting for the test process of 28 days using some parameters obtained physical and chemical analysis at current. The paper aims to develop a decision support system for the prediction of activity index of granulated blast furnace slag at 28 days. Prediction abilities of artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS) are investigated for the decision support system. According to the artificial neural network results, the mean absolute percentage error value for the whole data set has been calculated as 2.27 %. The comparisons show that ANN overcomes ANFIS approach. According to these results, the proposed decision support system has helped the determination of mixtures optimally and led to the decrease in CO2 emission of CEM III production process.

Development of an Intelligent Decision Support System for Attaining Sustainable Growth within a Life Insurance Company

Consumer behaviour is one of the most important and complex areas of research. It acknowledges the buying behaviour of consumer clusters towards any product, such as life insurance policies. Among various factors, the three most well-known determinants on which human conjecture depends for preferring a product are demographic, economic and psychographic factors, which can help in developing an accurate market design and strategy for the sustainable growth of a company. In this paper, the study of customer satisfaction with regard to a life insurance company is presented, which focused on comparing artificial intelligence-based, data-driven approaches to classical market segmentation approaches. In this work, an artificial intelligence-based decision support system was developed which utilises the aforementioned factors for the accurate classification of potential buyers. The novelty of this paper lies in developing supervised machine learning models that have a tendency to accurately identify the cluster of potential buyers with the help of demographic, economic and psychographic factors. By considering a combination of the factors that are related to the demographic, economic and psychographic elements, the proposed support vector machine model and logistic regression model-based decision support systems were able to identify the cluster of potential buyers with collective accuracies of 98.82% and 89.20%, respectively. The substantial accuracy of a support vector machine model would be helpful for a life insurance company which needs a decision support system for targeting potential customers and sustaining its share within the market.

Routine clinical care data from thirteen cardiac outpatient clinics: design of the Cardiology Centers of the Netherlands (CCN) database

BackgroundDespite the increasing availability of clinical data due to the digitalisation of healthcare systems, data often remain inaccessible due to the diversity of data collection systems. In the Netherlands, Cardiology Centers of the Netherlands (CCN) introduced “one-stop shop” diagnostic clinics for patients suspected of cardiac disease by their general practitioner. All CCN clinics use the same data collection system and standardised protocol, creating a large regular care database. This database can be used to describe referral practices, evaluate risk factors for cardiovascular disease (CVD) in important patient subgroups, and develop prediction models for use in daily care.Construction and contentThe current database contains data on all patients who underwent a cardiac workup in one of the 13 CCN clinics between 2007 and February 2018 (n = 109,151, 51.9% women). Data were pseudonymised and contain information on anthropometrics, cardiac symptoms, risk factors, comorbidities, cardiovascular and family history, standard blood laboratory measurements, transthoracic echocardiography, electrocardiography in rest and during exercise, and medication use. Clinical follow-up is based on medical need and consisted of either a repeat visit at CCN (43.8%) or referral for an external procedure in a hospital (16.5%). Passive follow-up via linkage to national mortality registers is available for 95% of the database.Utility and discussionThe CCN database provides a strong base for research into historically underrepresented patient groups due to the large number of patients and the lack of in- and exclusion criteria. It also enables the development of artificial intelligence-based decision support tools. Its contemporary nature allows for comparison of daily care with the current guidelines and protocols. Missing data is an inherent limitation, as the cardiologist could deviate from standardised protocols when clinically indicated.ConclusionThe CCN database offers the opportunity to conduct research in a unique population referred from the general practitioner to the cardiologist for diagnostic workup. This, in combination with its large size, the representation of historically underrepresented patient groups and contemporary nature makes it a valuable tool for expanding our knowledge of cardiovascular diseases.Trial registration: Not applicable.

Prospective study of artificial intelligence-based decision support to improve head and neck radiotherapy plan quality

Background and purposeVolumetric modulated arc therapy (VMAT) planning for head and neck cancer is a complex process. While the lowest achievable dose for each individual organ-at-risk (OAR) is unknown a priori, artificial intelligence (AI) holds promise as a tool to accurately estimate the expected dose distribution for OARs. We prospectively investigated the benefits of incorporating an AI-based decision support tool (DST) into the clinical workflow to improve OAR sparing. Materials and methodsThe DST dose prediction model was based on 276 institutional VMAT plans. Under an IRB-approved prospective trial, the physician first generated a custom OAR directive for 50 consecutive patients (physician directive, PD). The DST then estimated OAR doses (AI directive, AD). For each OAR, the treating physician used the lower directive to form a hybrid directive (HD). The final plan metrics were compared to each directive. A dose difference of 3 Gray (Gy) was considered clinically significant. ResultsCompared to the AD and PD, the HD reduced OAR dose objectives by more than 3 Gy in 22% to 75% of cases, depending on OAR. The resulting clinical plan typically met these lower constraints and achieved mean dose reductions between 4.3 and 16 Gy over the PD, and 5.6 to 9.1 Gy over the AD alone. Dose metrics achieved using the HD were significantly better than institutional historical plans for most OARs and NRG constraints for all OARs. ConclusionsThe DST facilitated a significantly improved treatment directive across all OARs for this generalized H&N patient cohort, with neither the AD nor PD alone sufficient to optimally direct planning.

A modified version of GoogLeNet for melanoma diagnosis

ABSTRACT Differential diagnosis of malignant melanoma, which is the cause of more than 75% of deaths amongst skin lesions, is vital for patients. Artificial intelligence-based decision support systems developed for the analysis of medical images are in the solution of such problems. In recent years, various deep learning algorithms have been developed to be used for this purpose. In our previous study, we compared the performances of AlexNet, GoogLeNet and ResNet-50 for the differential diagnosis of benign and malignant melanoma on International Skin Imaging Collaboration: Melanoma Project (ISIC) dataset. In this study, we proposed a CNN model by modifying the GoogLeNet algorithm and we compared the performance of this model with the previous results. For the experiments, we used 19,373 benign and 2197 malignant diagnosed dermoscopy images obtained from this public archive. We compared the performance results according to the eight different performance metrics including polygon area metric (PAM), classification accuracy (CA), sensitivity (SE), specificity (SP), area under curve (AUC), kappa (K), F measure metric (FM) and time complexity (TC) measures. According to the results, our proposed CNN achieved the best classification accuracy with 0.9309 and decreased the time complexity of GoogLeNet from 283 min 50 to 256 min 26 s.

Adjustment of Insulin Pump Settings in Type 1 Diabetes Management: Advisor Pro Device Compared to Physicians' Recommendations.

To compare insulin dose adjustments made by physicians to those made by an artificial intelligence-based decision support system, the Advisor Pro, in people with type 1 diabetes (T1D) using an insulin pump and self-monitoring blood glucose (SMBG). This was a multinational, non-interventional study surveying 17 physicians from 11 countries. Each physician was asked to provide insulin dose adjustments for the settings of the pump including basal rate, carbohydrate-to-insulin ratios (CRs), and correction factors (CFs) for 15 data sets of pumps and SMBG of people with T1D (mean age 18.4 ± 4.8 years; eight females; mean glycated hemoglobin 8.2% ± 1.4% [66 ± 11mmol/mol]). The recommendations were compared among the physicians and between the physicians and the Advisor Pro. The study endpoint was the percentage of comparison points for which there was an agreement on the direction of insulin dose adjustments. The percentage (mean ± SD) of agreement among the physicians on the direction of insulin pump dose adjustments was 51.8% ± 9.2%, 54.2% ± 6.4%, and 49.8% ± 11.6% for the basal, CR, and CF, respectively. The automated recommendations of the Advisor Pro on the direction of insulin dose adjustments were comparable )49.5% ± 6.4%, 55.3% ± 8.7%, and 47.6% ± 14.4% for the basal rate, CR, and CF, respectively( and noninferior to those provided by physicians. The mean absolute difference in magnitude of change between physicians was 17.1% ± 13.1%, 14.6% ± 8.4%, and 23.9% ± 18.6% for the basal, CR, and CF, respectively, and comparable to the Advisor Pro 11.7% ± 9.7%, 10.1% ± 4.5%, and 25.5% ± 19.5%, respectively, significant for basal and CR. Considerable differences in the recommendations for changes in insulin dosing were observed among physicians. Since automated recommendations by the Advisor Pro were similar to those given by physicians, it could be considered a useful tool to manage T1D.

Insulin dose optimization using an automated artificial intelligence-based decision support system in youths with type 1 diabetes.

Despite the increasing adoption of insulin pumps and continuous glucose monitoring devices, most people with type 1 diabetes do not achieve their glycemic goals1. This could be related to a lack of expertise or inadequate time for clinicians to analyze complex sensor-augmented pump data. We tested whether frequent insulin dose adjustments guided by an automated artificial intelligence-based decision support system (AI-DSS) is as effective and safe as those guided by physicians in controlling glucose levels. ADVICE4U was a six-month, multicenter, multinational, parallel, randomized controlled, non-inferiority trial in 108 participants with type 1 diabetes, aged 10-21 years and using insulin pump therapy (ClinicalTrials.gov no. NCT03003806). Participants were randomized 1:1 to receive remote insulin dose adjustment every three weeks guided by either an AI-DSS, (AI-DSS arm, n = 54) or by physicians (physician arm, n = 54). The results for the primary efficacy measure-the percentage of time spent within the target glucose range (70-180 mg dl-1 (3.9-10.0 mmol l-1))-in the AI-DSS arm were statistically non-inferior to those in the physician arm (50.2 ± 11.1% versus 51.6 ± 11.3%, respectively, P < 1 × 10-7). The percentage of readings below 54 mg dl-1 (<3.0 mmol l-1) within the AI-DSS arm was statistically non-inferior to that in the physician arm (1.3 ± 1.4% versus 1.0 ± 0.9%, respectively, P < 0.0001). Three severe adverse events related to diabetes (two severe hypoglycemia, one diabetic ketoacidosis) were reported in the physician arm and none in the AI-DSS arm. In conclusion, use of an automated decision support tool for optimizing insulin pump settings was non-inferior to intensive insulin titration provided by physicians from specialized academic diabetes centers.

Artificial Intelligence in Decision Support Systems for Type 1 Diabetes.

Type 1 diabetes (T1D) is a chronic health condition resulting from pancreatic beta cell dysfunction and insulin depletion. While automated insulin delivery systems are now available, many people choose to manage insulin delivery manually through insulin pumps or through multiple daily injections. Frequent insulin titrations are needed to adequately manage glucose, however, provider adjustments are typically made every several months. Recent automated decision support systems incorporate artificial intelligence algorithms to deliver personalized recommendations regarding insulin doses and daily behaviors. This paper presents a comprehensive review of computational and artificial intelligence-based decision support systems to manage T1D. Articles were obtained from PubMed, IEEE Xplore, and ScienceDirect databases. No time period restrictions were imposed on the search. After removing off-topic articles and duplicates, 562 articles were left to review. Of those articles, we identified 61 articles for comprehensive review based on algorithm evaluation using real-world human data, in silico trials, or clinical studies. We grouped decision support systems into general categories of (1) those which recommend adjustments to insulin and (2) those which predict and help avoid hypoglycemia. We review the artificial intelligence methods used for each type of decision support system, and discuss the performance and potential applications of these systems.

A novel hybrid artificial intelligence-based decision support framework to predict lead time

ABSTRACT Inventory and routing are the two most important elements to company’s survival in supply chain environments. Hence, solution approaches of inventory routing problem (IRP) should assure adequate inventory level and also provide an efficient route. In this case, hybrid approaches can empower researchers to solve the IRP. The aim of this study is to develop a new hybrid methodology that includes two phases to provide a generic framework for IRP. In Phase I, genetic algorithm-based simulation optimisation is used to dynamically perform inventory control and routing decisions. In Phase II, artificial intelligence (AI)-based simulation in which the lead time of supply chain members is predicted is employed to extend the functionality of the method in Phase I. The proposed hybrid methodology gives insights into the cross-fertilisation of AI, simulation, and optimisation for researchers. Therefore, this integration can be applied to different supply chain problems by using similar methods.

Inherent Bias in Artificial Intelligence-Based Decision Support Systems for Healthcare.

The objective of this article is to discuss the inherent bias involved with artificial intelligence-based decision support systems for healthcare. In this article, the authors describe some relevant work published in this area. A proposed overview of solutions is also presented. The authors believe that the information presented in this article will enhance the readers’ understanding of this inherent bias and add to the discussion on this topic. Finally, the authors discuss an overview of the need to implement transdisciplinary solutions that can be used to mitigate this bias.

Decision Support System for Management Decision in High-Risk Business Environment

Abstract As a result of substantial variations in global financial markets, constructing an enterprise risk prewarning mechanism is essential. A vast amount of related studies have implemented monetary-related indicators to depict the full spectrum of an enterprise’s operating performance. Merely considering monetary-related indicators is unable to produce an in-depth understanding of an enterprise. To fill this gap, the balanced scorecard (BSC), with the advantages of being able to capture both monetary and nonmonetary indicators, was introduced. Unfortunately, the BSC also has its own challenges, one of which is the lack of consideration given to risk exposure, which affects an enterprise’s profit variation. Thus, this study extends the original BSC by considering risk exposure and introduces an artificial intelligence-based decision support system for management decision. The inherent decision logic embedded into neural network-based mechanisms is opaque and hard to comprehend by users. To handle the challenge, this study further incorporates fit theory with a knowledge visualization technique to handle the opaque nature of the model so as to decrease the cognitive load and mental burden. The empirical results show that the introduced model is a promising alternative for management decisions in highly fluctuating financial markets.

HIV Drug-Resistant Patient Information Management, Analysis, and Interpretation

IntroductionThe science of information systems, management, and interpretation plays an important part in the continuity of care of patients. This is becoming more evident in the treatment of human immunodeficiency virus (HIV) and acquired immune deficiency syndrome (AIDS), the leading cause of death in sub-Saharan Africa. The high replication rates, selective pressure, and initial infection by resistant strains of HIV infer that drug resistance will inevitably become an important health care concern. This paper describes proposed research with the aim of developing a physician-administered, artificial intelligence-based decision support system tool to facilitate the management of patients on antiretroviral therapy.MethodsThis tool will consist of (1) an artificial intelligence computer program that will determine HIV drug resistance information from genomic analysis; (2) a machine-learning algorithm that can predict future CD4 count information given a genomic sequence; and (3) the integration of these tools into an electronic medical record for storage and management.ConclusionThe aim of the project is to create an electronic tool that assists clinicians in managing and interpreting patient information in order to determine the optimal therapy for drug-resistant HIV patients.

Artificial intelligence-based decision support system to manage quality of durum wheat products

Background The long term competitiveness of food companies as well as the general health and wellness of citizens depend on the availability of products meeting the demands of safe, healthy and tasty foods. Therefore there is a need to merge heterogeneous data in order to develop the necessary decision support systems. Aims The objective of this paper is to propose an approach for durum wheat chain analysis based on a knowledge management system in order to help prediction. Material and Methods The approach is based on an information system allowing for experimental data and expert knowledge representation as well as reasoning mechanisms, including the decision tree learning method. Results The results include the structure of the knowledge management system for durum wheat process data, statistics and prediction results using decision trees. The use of expert rules for decision support is introduced and a method for confronting expert knowledge with experimental data is proposed. Different case studies from the durum wheat process are given. Discussion Our specific original contributions are: the design of a hybrid system combining both data and knowledge, the advantage of not requiring an a priori model, and therefore, an increased genericity, and the potential use for both risk and benefit analysis. Conclusion The approach can be reused for other purposes within the chain, and can also be transferred to other domains. Such a project is a starting point to integrate new knowledge from multidisciplinary fields, and constitutes a tool for structuring the international cereal research community.

Artificial Intelligence–Based Decision Support Technologies in Pavement Management

The field of road pavement engineering has seen an explosion of artificial intelligence–based applications since the late 1980s. Such applications are found at key stages of the decision process involved in pavement management. In the analysis phase, they perform pavement diagnosis and deterioration modeling tasks. In the design phase, they enable rehabilitation needs to be assessed and contribute to the identification and selection of maintenance actions. Finally, in the choice phase, they are applied for priority programming of rehabilitation and maintenance. They either represent alternative approaches to existing systems or collaborate to make the overall system more efficient. The purpose of this article is to summarize the findings of up‐to‐date research articles concerning the application of artificial intelligence to pavement management and to illustrate the potential such tools can offer to pavement engineers. Artificial intelligence techniques include expert systems, artificial neural networks, fuzzy logic, genetic algorithms, and hybrid systems.