Abstract
Objective
To determine if ChatGPT can generate useful suggestions for improving clinical decision support (CDS) logic and to assess noninferiority compared to human-generated suggestions.
...Methods
We supplied summaries of CDS logic to ChatGPT, an artificial intelligence (AI) tool for question answering that uses a large language model, and asked it to generate suggestions. We asked human clinician reviewers to review the AI-generated suggestions as well as human-generated suggestions for improving the same CDS alerts, and rate the suggestions for their usefulness, acceptance, relevance, understanding, workflow, bias, inversion, and redundancy.
Results
Five clinicians analyzed 36 AI-generated suggestions and 29 human-generated suggestions for 7 alerts. Of the 20 suggestions that scored highest in the survey, 9 were generated by ChatGPT. The suggestions generated by AI were found to offer unique perspectives and were evaluated as highly understandable and relevant, with moderate usefulness, low acceptance, bias, inversion, redundancy.
Conclusion
AI-generated suggestions could be an important complementary part of optimizing CDS alerts, can identify potential improvements to alert logic and support their implementation, and may even be able to assist experts in formulating their own suggestions for CDS improvement. ChatGPT shows great potential for using large language models and reinforcement learning from human feedback to improve CDS alert logic and potentially other medical areas involving complex, clinical logic, a key step in the development of an advanced learning health system.
Hepatitis carcinoma (HCC) accounts for the majority of liver cancer–related deaths globally. Cirrhosis often precedes HCC clinically in a strong, temporal relationship. Therefore, identifying ...cirrhosis patients at higher risk of HCC is crucial to physicians' clinical decision-making and patient management. Effective estimates of at-risk patients can facilitate timely therapeutic interventions and thereby enhance patient outcomes and well-being. We develop a novel, meta-path, attention-based deep learning method to identify at-risk cirrhosis patients. The proposed method integrates complex patient–medication interactions, essential patient–patient and medication–medication links, and the combined effects of medication and comorbidity to support downstream predictions. An empirical test of the proposed method's predictive utilities, relative to nine existing methods, uses a large sample of real-world cirrhosis patient data. The comparative results indicate that the proposed method can identify at-risk patients more effectively than all the benchmarks. The current research has important implications for clinical decision support and patient management, and it can facilitate patient self-management and treatment compliance too.
•HCC is a leading cause of morbidity and mortality, often following cirrhosis.•Accurate estimates of patients at risk of HCC is crucial to patient management.•A deep learning–based method is proposed to identify at-risk cirrhosis patients.•It integrates patient–medication interactions and combined effects of medications.•Evaluations show its efficacy for clinical decision-making and patient management.
Blockchain technology has received significant attention recently, as it offers a reliable decentralized infrastructure for all kinds of business transactions. Software-producing organizations are ...increasingly considering blockchain technology for inclusion into their software products. Selecting the best fitting blockchain platform requires the assessment of its functionality, adaptability, and compatibility to the existing software product. Novice software developers and architects are not experts in every domain, so they should either consult external experts or acquire knowledge themselves. The decision-making process gets more complicated as the number of decision-makers, alternatives, and criteria increases. Hence, a decision model is required to externalize and organize knowledge regarding the blockchain platform selection context. Recently, we designed a decision support system to use such decision models to support decision-makers with their technology selection problems in software production. In this article, we introduce a decision model for the blockchain platform selection problem. The decision model has been evaluated through three real-world case studies at three software-producing organizations. The case-study participants asserted that the approach provides significantly more insight into the blockchain platform selection process, provides a richer prioritized option list than if they had done their research independently, and reduces the time and cost of the decision-making process.
Special Issue on “Decision Support Systems in an uncertain world” Costa, Ana Paula Cabral Seixas; Kamissoko, Daouda; Moreno‐Jiménez, José Maria
International transactions in operational research,
March 2024, 2024-03-00, 20240301, Letnik:
31, Številka:
2
Journal Article
Display omitted
•Current environmental risk assessment approaches hamper offshore energy expansion.•Strategically planned DST development can enable substantial savings, improving resource efficiency ...and high quality EIA.•The main midrange scenario results in potential cost savings of 1,580 M€ until 2050.•The DST development is beneficial for economy of future energy development and marine environmental protection.
In the transition to a sustainable energy system, there is an urgent need for expansion of offshore renewable energy installations. To ensure sustainable development also with respect to the marine environment, a variety of decision support tools (DSTs) are currently under development, aiming at potentially increased quality and efficiency for environmental risk assessment (EIA) of planned offshore energy installations. However, the savings potential of a DSTs is to a large extent governed by the timing of the DST development, which in turn is directly dependent on the investment rate over time. A set of development scenarios were evaluated, simulating different degrees of strategic implementation and successful utilization of the DST for offshore energy. Using the situation in Sweden as a case study, we demonstrate that a planned investment can lead to considerably lower total costs for the EIA at a national level, at the same time allowing for improved quality of the EIA in line with the ambitions in both marine spatial planning and existing goals within marine environmental management.
We have conducted a pragmatic clinical trial aimed to assess whether an electrocardiogram (ECG)-based, artificial intelligence (AI)-powered clinical decision support tool enables early diagnosis of ...low ejection fraction (EF), a condition that is underdiagnosed but treatable. In this trial ( NCT04000087 ), 120 primary care teams from 45 clinics or hospitals were cluster-randomized to either the intervention arm (access to AI results; 181 clinicians) or the control arm (usual care; 177 clinicians). ECGs were obtained as part of routine care from a total of 22,641 adults (N = 11,573 intervention; N = 11,068 control) without prior heart failure. The primary outcome was a new diagnosis of low EF (≤50%) within 90 days of the ECG. The trial met the prespecified primary endpoint, demonstrating that the intervention increased the diagnosis of low EF in the overall cohort (1.6% in the control arm versus 2.1% in the intervention arm, odds ratio (OR) 1.32 (1.01-1.61), P = 0.007) and among those who were identified as having a high likelihood of low EF (that is, positive AI-ECG, 6% of the overall cohort) (14.5% in the control arm versus 19.5% in the intervention arm, OR 1.43 (1.08-1.91), P = 0.01). In the overall cohort, echocardiogram utilization was similar between the two arms (18.2% control versus 19.2% intervention, P = 0.17); for patients with positive AI-ECGs, more echocardiograms were obtained in the intervention compared to the control arm (38.1% control versus 49.6% intervention, P < 0.001). These results indicate that use of an AI algorithm based on ECGs can enable the early diagnosis of low EF in patients in the setting of routine primary care.
Sepsis remains the top cause of morbidity and mortality of hospitalised patients despite concerted efforts. Clinical decision support for sepsis has shown mixed results reflecting heterogeneous ...populations, methodologies and interventions.
To determine whether the addition of a real-time electronic health record (EHR)-based clinical decision support alert improves adherence to treatment guidelines and clinical outcomes in hospitalised patients with suspected severe sepsis.
Patient-level randomisation, single blinded.
Medical and surgical inpatient units of an academic, tertiary care medical centre.
1123 adults over the age of 18 admitted to inpatient wards (intensive care units (ICU) excluded) at an academic teaching hospital between November 2014 and March 2015.
Patients were randomised to either usual care or the addition of an EHR-generated alert in response to a set of modified severe sepsis criteria that included vital signs, laboratory values and physician orders.
There was no significant difference between the intervention and control groups in primary outcome of the percentage of patients with new antibiotic orders at 3 hours after the alert (35% vs 37%, p=0.53). There was no difference in secondary outcomes of in-hospital mortality at 30 days, length of stay greater than 72 hours, rate of transfer to ICU within 48 hours of alert, or proportion of patients receiving at least 30 mL/kg of intravenous fluids.
An EHR-based severe sepsis alert did not result in a statistically significant improvement in several sepsis treatment performance measures.
Multimorbidity, the presence of more than one condition in a single individual, is a global health issue in primary care. Multimorbid patients tend to have a poor quality of life and suffer from a ...complicated care process. Clinical decision support systems (CDSSs) and telemedicine are the common information and communication technologies that have been used to reduce the complexity of patient management. However, each element of telemedicine and CDSSs is often examined separately and with great variability. Telemedicine has been used for simple patient education as well as more complex consultations and case management. For CDSSs, there is variability in data inputs, intended users, and outputs. Thus, there are several gaps in knowledge about how to integrate CDSSs into telemedicine and to what extent these integrated technological interventions can help improve patient outcomes for those with multimorbidity.
Our aims were to (1) broadly review system designs for CDSSs that have been integrated into each function of telemedicine for multimorbid patients in primary care, (2) summarize the effectiveness of the interventions, and (3) identify gaps in the literature.
An online search for literature was conducted up to November 2021 on PubMed, Embase, CINAHL, and Cochrane. Searching from the reference lists was done to find additional potential studies. The eligibility criterion was that the study focused on the use of CDSSs in telemedicine for patients with multimorbidity in primary care. The system design for the CDSS was extracted based on its software and hardware, source of input, input, tasks, output, and users. Each component was grouped by telemedicine functions: telemonitoring, teleconsultation, tele-case management, and tele-education.
Seven experimental studies were included in this review: 3 randomized controlled trials (RCTs) and 4 non-RCTs. The interventions were designed to manage patients with diabetes mellitus, hypertension, polypharmacy, and gestational diabetes mellitus. CDSSs can be used for various telemedicine functions: telemonitoring (eg, feedback), teleconsultation (eg, guideline suggestions, advisory material provisions, and responses to simple queries), tele-case management (eg, sharing information across facilities and teams), and tele-education (eg, patient self-management). However, the structure of CDSSs, such as data input, tasks, output, and intended users or decision-makers, varied. With limited studies examining varying clinical outcomes, there was inconsistent evidence of the clinical effectiveness of the interventions.
Telemedicine and CDSSs have a role in supporting patients with multimorbidity. CDSSs can likely be integrated into telehealth services to improve the quality and accessibility of care. However, issues surrounding such interventions need to be further explored. These issues include expanding the spectrum of medical conditions examined; examining tasks of CDSSs, particularly for screening and diagnosis of multiple conditions; and exploring the role of the patient as the direct user of the CDSS.
The diagnosis of type 2 diabetes (T2D) at an early stage has a key role for an adequate T2D integrated management system and patient's follow-up. Recent years have witnessed an increasing amount of ...available electronic health record (EHR) data and machine learning (ML) techniques have been considerably evolving. However, managing and modeling this amount of information may lead to several challenges, such as overfitting, model interpretability, and computational cost. Starting from these motivations, we introduced an ML method called sparse balanced support vector machine (SB-SVM) for discovering T2D in a novel collected EHR dataset (named Federazione Italiana Medici di Medicina Generale dataset). In particular, among all the EHR features related to exemptions, examination, and drug prescriptions, we have selected only those collected before T2D diagnosis from an uniform age group of subjects. We demonstrated the reliability of the introduced approach with respect to other ML and deep learning approaches widely employed in the state-of-the-art for solving this task. Results evidence that the SB-SVM overcomes the other state-of-the-art competitors providing the best compromise between predictive performance and computation time. Additionally, the induced sparsity allows to increase the model interpretability, while implicitly managing high-dimensional data and the usual unbalanced class distribution.