Integrated Information System Research Articles

Systematic application of traffic‐signal‐control system architecture design and selection using model‐based systems engineering and Pareto frontier analysis

AbstractThe global population rise has increased vehicles on roads, complicating traffic management. Inefficient traffic control systems cause significant economic losses owing to commuter time wastage, high energy consumption, and greenhouse gas emissions. Traffic signal control systems (TSCSs) are vital in traffic management, impacting traffic flow significantly; therefore, studies are exploring new optimization approaches that adapt to changing traffic conditions. However, they concentrate on either new technology infusion or on control algorithm optimization, and do not holistically address the architectural configuration of the system. In this study, we presented a unique case study by applying an existing systematic framework to the TSCS system architecture design and selection process. This application demonstrates that TSCS enhancement is a multifaceted process that requires a comprehensive assessment of not only technical aspects, such as the control algorithm, but also factors including system architecture, security, and data integrity. Because of the increasing reliance of TSCSs on data exchange between their various subsystems, this case study also adopted a cybersecurity perspective of the system and introduced cyber resiliency as a crucial metric for evaluating TSCS architecture performance. Furthermore, through the applied framework, an optimal TSCS architectural configuration with executable options was identified by generating multiple TSCS architectural configurations using decision option patterns and identifying those on the Pareto frontier to understand the architectural decision‐making process. Traffic engineers and transportation planners can use this case study application as a guide to optimize TSCSs employed in existing transportation networks and design more efficient transportation networks for future urban development.

A comprehensive review on the integration of geographic information systems and artificial intelligence for landfill site selection: A systematic mapping perspective.

Properly selecting landfill sites for waste disposal is crucial for mitigating environmental and public health risks. Geographic Information Systems (GISs) and Artificial Intelligence (AI) techniques have emerged as valuable tools for identifying suitable landfill locations. This study presents a systematic mapping study (SMS) that investigates the usage of GIS and AI in landfill site selection. We searched six databases (IEEE Xplore, ACM Digital Library, Science Direct, Emerald Insight, Taylor & Francis Online and Web of Science) using predefined keywords related to landfills, GIS and AI. From 858 initially retrieved articles, we selected 48 relevant articles for in-depth analysis. Our research aimed to answer various questions, such as publication trends, the geographic distribution of case studies, criteria for assessing landfill suitability, tools and techniques employed, preliminary site screening methods, decision-making processes, limitations and future research directions. We used bubble charts, bar charts and tables to visualize the results. The findings of our study highlight the growing interest in using GIS and AI for landfill site selection and emphasize the importance of incorporating multi-criteria decision-making techniques. Furthermore, the results reveal the need for developing more advanced AI models, addressing the limitations of current approaches and exploring novel visualization techniques for enhancing landfill site selection processes. This study provides valuable insights for researchers and practitioners in waste management, environmental science and geoinformatics. It sets the groundwork for future research on improving GIS- and AI-based landfill site selection methodologies.

Correlation Aware Relevance-Based Semantic Index for Clinical Big Data Repository.

In this paper, we focus on indexing mechanisms for unstructured clinical big integrated data repository systems. Clinical data is unstructured and heterogeneous, which comes in different files and formats. Accessing data efficiently and effectively are critical challenges. Traditional indexing mechanisms are difficult to apply on unstructured data, especially by identifying correlation information between clinical data elements. In this research work, we developed a correlation-aware relevance-based index that retrieves clinical data by fetching most relevant cases efficiently. In our previous work, we designed a methodology that categorizes medical data based on the semantics of data elements and merges them into an integrated repository. We developed a data integration system for medical data sources that combines heterogeneous medical data and provides access to knowledge-based database repositories to different users. In this research work, we designed an indexing system using semantic tags extracted from clinical data sources and medical ontologies that retrieves relevant data from database repositories and speeds up the process of data retrieval. Our objective is to provide an integrated biomedical database repository that can be used by radiologists as a reference, or for patient care, or by researchers. In this paper, we focus on designing a technique that performs data processing for data integration, learn the semantic properties of data elements, and develop a correlation-aware topic index that facilitates efficient data retrieval. We generated semantic tags by identifying key elements from integrated clinical cases using topic modeling techniques. We investigated a technique that identifies tags for merged categories and provides an index to fetch data from an integrated database repository. We developed a topic coherence matrix that shows how well a topic is supported by a corpus from clinical cases and medical ontologies. We were able to find more relevant results using an annotation index from an integrated database repository, and there was a 61% increase in a recall. We evaluated results with the help of experts and compared them with naive index (index with all terms from the corpus). Our approach improved data retrieval quality by providing most relevant results and reduced data retrieval time as we applied correlation-aware index on an integrated data repository. Topic indexing approach proposed in this research work identifies tags based on a correlation between different data elements, improves data retrieval time, and provides most relevant cases as an outcome of this system.

Critical Watershed Prioritization through Multi-Criteria Decision-Making Techniques and Geographical Information System Integration for Watershed Management

The Precambrian hard rock topography of the Manbhum-Singhbhum plateau, which is well known for its semi-arid climates prone to drought, is often seen in Purulia district in West Bengal, India. Despite the district’s middling groundwater capacity, 17 out of 20 blocks have exorbitant fluoride pollution in the groundwater that negatively impacts the health of local residents. Approximately 13% of the whole area suffers from severe erosion. It is evident that the river Kangsabati and its tributaries are not well fed by rainwater and thereby there is always a dearth of ground water. The aim of this study was to identify and prioritize integral watersheds in the Purulia area using Multi-Criteria Decision Making (MCDM) and Geographic Information Systems (GIS). The evaluation was carried out in the Bandu sub-watershed, which contains five micro watersheds: 2A2B5m, 2A2B5k, 2A2B5h, 2A2B5b, and 2A2B5j. The analysis considered five major factors: lithological properties, land use and land cover, soil erosion, groundwater recharge, and hydrogeomorphology. The weights of these criteria were determined by the Analytical Hierarchy Process (AHP) model, which was then prioritized using the Techniques for Order of Preference by Similarity to the Ideal Solution (TOPSIS) technique. This study emphasized an integrated approach to assess watershed hazards and to establish rational conservation goals. The Central Ground Water Board (CGWB) of India report was referred during data analysis. As a result of this study, the 2A2B5k watershed emerged as the most critical due to its susceptibility across the analyzed parameters. This thorough plan demonstrated the usefulness of identifying watershed threads and prioritizing conservation efforts.

Integration of Geographic Information Systems and Spatial Data Analysis in Location Decision Making for Manufacturing Industries

Integration of Geographic Information Systems and Spatial Data Analysis in Location Decision Making for Manufacturing Industries

Remote Sensing-Enabled Urban Growth Simulation Overlaid with AHP-GIS-Based Urban Land Suitability for Potential Development in Mersin Metropolitan Area, Türkiye

This study delves into the integration of analytic hierarchy process (AHP) and geographic information system (GIS) techniques to identify suitable areas for urban development in six districts within the Mersin Metropolitan Area of Turkey. The specific aim is to generate an urban land use suitability map, in order to facilitate informed decision-making for urban development. Drawing on open Landsat satellite imagery and employing the random forest (RF) algorithm, the study spans a fifteen-year period, over which land use/land cover (LULC) changes are measured. Furthermore, a novel approach is introduced by incorporating the urban land use suitability map into an urban growth simulation model developed using a logistic regression (LR) algorithm. This simulation forecasts urban growth up to 2027, enabling planners to evaluate potential development areas against suitability criteria. Findings reveal spatial patterns of land suitability and projected urban growth, aiding decision-makers in selecting optimal areas for development while preserving ecological integrity. Notably, the study emphasizes the importance of considering various factors such as topography, accessibility, soil capability, and geology in urban planning processes. The results showcase significant proportions of the study area as being moderately to highly suitable for urban development, alongside notable shifts in LULC classes over the years. Additionally, the overlay analysis of simulated urban growth and land suitability maps highlights areas with contrasting suitability levels, offering valuable insights for sustainable urban growth strategies. By overlaying the urban land suitability map with a simulated LULC map for 2027, it is revealed that 2247.3 hectares of potential new urbanization areas demonstrate very high suitability for settlement, while 7440.12 hectares exhibit very low suitability. By providing a comprehensive framework for assessing urban land suitability and projecting future growth, this research offers practical implications for policymakers, urban planners, and stakeholders involved in Mersin’s development trajectory, ultimately fostering more sustainable and resilient urban landscapes.

Reliability analysis of intelligent manufacturing systems based on improved FMEA combined with machine learning

Along with the booming of intelligent manufacturing, the reliability management of intelligent manufacturing systems appears to be becoming more significant. Failure mode and effects analysis (FMEA) is a prospective reliability management instrument extensively utilized to manage failure modes of systems, products, processes, and services in various industries. However, the conventional FMEA method has been criticized for its inherent limitations. Machine learning can handle large amounts of data and has merits in reliability analysis and prediction, which can help in failure mode classification and risk management under limited resources. Therefore, this paper devises a method for complex systems based on an improved FMEA model combined with machine learning and applies it to the reliability management of intelligent manufacturing systems. First, the structured network of failure modes is constructed based on the knowledge graph for intelligent manufacturing systems. Then, the grey relation analysis (GRA) is applied to determine the risk prioritization of failure modes. Hereafter, the k-means algorithm in unsupervised machine learning is employed to cluster failure modes into priority classes. Finally, a case study and further comparative analysis are implemented. The results demonstrate that failure modes in system security, production quality, and information integration are high-risk and require more resources for prevention. In addition, recommendations for risk prevention and monitoring of intelligent manufacturing systems were given based on the clustering results. In comparison to the conventional FMEA method, the proposed method can more precisely capture the coupling relationship between the failure modes compared with. This research provides significant support for the reliability and risk management of complex systems such as intelligent manufacturing systems.

Healthcare Integrated Information System in Indonesia

The United States (US), leads the world in medical science and technology. Lead by clear definitions in almost all sectors of clinical research, training and governance practices. Likewise, the pharmaceutical and medical device (medical equipment) manufacturers are considered one of the leading in the world. Therefore, many of the definitions and rules have also been adopted into global regulations by the world health organization, the World Health Organization (WHO). Currently, these rules have been implemented into the health information system (HIS), which further rapidly being adopted and used in many countries. Nowadays, health facilities (HF) around the world have used HIS, which are basic or have reached an advanced level. This paper will describe how the development of HIS and applied products from utilization of information technology (IT) in Indonesia, along with the opportunities and challenges in the future.

Artificial intelligence in accounting

Artificial Intelligence (AI) technologies open up broad horizons for enhancing business efficiency and advancing various professional domains, boosting their productivity and compe­titiveness. There is an active exploration of approaches to incorporating AI technologies in the accounting sphere, promising a seamless transition from human to machine involvement. The aim of this article is to summarize the acquired experience, identify perspectives, constraints, and risks associated with the use of AI technologies in the professional activities of accountants. The research is based on the hypothesis that widespread use of AI in the professional activity of an accountant with an insufficient level of professional skepticism and caution carries significant threats and risks for both the accountant and the business as a whole. Scientific search methods, comparative and critical analysis, theoretical generalization, and synthesis were used. A prerequisite for imple­menting AI technologies in accounting is expert information systems and ERP systems. The analysis of AI technology implementation experience in various industries demonstrates their relevance in the accounting field for performing routine tasks (automated recognition of primary documents, processing incoming signals, and other standard operations with a simultaneous reduction in the probability of errors), analyzing large datasets, and providing information support for decision-making (pro­ces­sing business data and regulatory docu­ments), training professionals, and organi­zing internal and external communication (parti­cularly between humans and machines). Identi­fied potential risks include breaches of privacy and data security, misinterpretation of output data, and the disregard of activity context, external and internal environments, especially due to the absence of emotional intelligence, which influences the trust level in integrated information systems. The requirement for the application of professional assessments and judgments, mandated by regulatory documents, limits the scope of AI technology utilization in accounting. Future research should focus on exploring the possibilities of widespread integ­ration of AI technologies in information systems for accounting and improving legislation based on the principle of risk assessment.

Social Policy: How is the Innovation in the Integrated Service and Referral System (SLRT) Services in the City of Bandung?

This study aims to analyze innovation in the implementation of the Integrated Service and Referral System (SLRT) as a social policy in the city of Bandung. SLRT is a holistic approach in providing social and welfare services to the community by integrating various existing programs and resources. This research focuses on innovations that have been implemented in SLRT and their impact on the effectiveness and efficiency of social service delivery. This research method involves a qualitative approach with descriptive methods. The results showed that the implementation of the Cetar Juara Integrated Service and Referral System in Bandung City had succeeded in overcoming the fragmented challenges of previous poverty reduction. Through an integrated approach, SLRT has provided fast and effective services to the poor and vulnerable. Innovations such as the development of integrated information systems, mobile applications, online services, and partnerships with the private sector have been significant in increasing the efficiency and accessibility of services. Thus, the results of the study indicate that SLRT Cetar Juara has had a positive, sustainable impact in overcoming poverty problems and improving people’s welfare.

An Integration of Logistic Regression and Geographic Information System for Development of a Landslide Hazard Index to Land Use: A Case Study in Pingtung County in Southern Taiwan

In Taiwan, mountainous areas account for approximately two-thirds of the total area. The steep terrain and concentrated rainfall during typhoons cause landslides, which pose a considerable threat to mountain settlements. Therefore, models for analyzing rainfall-induced landslide hazards are urgently required to ensure adequate land use in mountainous areas. In this study, focusing on Pingtung County in southern Taiwan, we developed a landslide hazard index (IRL) to land use. Using FORMOSA-2 and SPOT-5 satellite images, data were collected before and after four typhoons (one in 2009 and three in 2013). The ArcGIS random tree classifier was used for interpreting satellite images to explore surface changes and disasters, which were used to analyze slope disturbances. The product of the maximum 3-h rolling rainfall intensity and effective accumulated rainfall was used as a rainfall trigger index (IRT). Considering environmental and slope disturbance factors, an index of slope environmental strength potential (ISESP) was developed through logistic regression (LR). Landslide hazard to land use was estimated using IRT and ISESP. The average coefficient of agreement (Kappa) was approximately 0.71 (medium to high accuracy); the overall accuracy of slope environmental strength potential analysis was approximately 80.4%. At a constant ISESP, IRT increased with the increasing hazard potential of rainfall-induced landslides. Furthermore, IRT and ISESP were positively correlated with landslide occurrence. When large ISESP values occur (e.g., fragile environment and high land development intensity), small IRT values may induce landslides.

Machine learning and IoT based MIMO-UWB Antenna Integrated with Ku-Band for Seamless Wireless Communication

The implementation of machine learning algorithms with advanced antenna technologies, such as Multiple Input Multiple Output Ultra-Wideband -UWB- and Cup-Ban, has emerged as a powerful method for improving wireless communication systems. This research focuses on the effectiveness of applying three machine learning algorithms, which are Deep Q-Networks -DQN- , Label Propagation, and Model-Agnostic Meta-Learning (MAML). Using several experiments, we analyzed the throughput, latency, and packet loss of every algorithm. These were part of the project designed on a wireless signal combined with MIMO-UWB and Ku-Band. Nevertheless, MAML has the highest average throughput of 261.3 Mbps, and the other algorithms follow one by one: DQN with 252.5 Mbps and Label Propagation with 240.6 Mbps. As to latency, the lowest average is 9.0 ms and 11.0 ms for DQN and 14.2 ms for Label Propagation. Finally, MAML proved the least packet losses with the average value of 0.18% and DQN with 0.39% and 0.73% of Label Propagation .The results presented above indicate that by adapting more quickly to changing wireless environments, MAML effectively optimizes communication performance in terms of throughput, latency, and packet loss. Specifically, through its ability to accelerate the allocation of resources and management of networks as a whole, more frequent and rapid learning with MAML results in better system reliability and data integrity.

Identification and Modeling of SI-LAUT: Information System for Indonesian Maritime Resources Using Penta-Helix Model

Indonesia, as a country predominantly surrounded by the sea, holds significant potential in marine resources, fisheries, and other maritime fields. However, there is still a lack of awareness and understanding among the Indonesian population regarding these maritime aspects. Currently, there are various media and information sources related to this topic, ranging from websites and applications to supporting information systems. Nevertheless, users often struggle to find and comprehend this information easily and comprehensively. Existing information systems tend to be fragmented or operate independently, leaving many laypeople unable to fully optimize the existing potential. To address this, researchers aim to identify and model a comprehensive and integrated information system focused on marine and other maritime resources, known as SI-LAUT The research method employed in this study consists of literature review, stakeholder identification based on the Penta-Helix model, analysis of the existing system, and gap analysis in comparison to previous research that focused on the implementation of other maritime and marine information systems. The results of this research consists of a recommendation for an information system development model that can assist various stakeholders based on the Penta-Helix Model. These stakeholders include government bodies, entrepreneurs, academics, as well as the general public or other communities. The goal is to optimize the management and utilization of Indonesia’s marine resources, ultimately positioning it as a global maritime powerhouse.

Effective Data Migration Strategies Using Talend and DataStage

Modern company operations need reliable data migration across systems to preserve continuity, performance, and business process integrity. Data transfer techniques need careful preparation, powerful tools, and system knowledge. Talend and IBM DataStage, two renowned data integration and migration systems, are used in this study to implement successful data transfer techniques. Talend and DataStage provide ETL, data quality management, and real-time integration services for data migration. Talend, an open-source platform, supports several data sources and formats with flexibility, scalability, and many connections. Organizations seeking cost-effective solutions appreciate it for its real-time data processing, user-friendly interface, and comprehensive data transformation capabilities. Talend's powerful data profiling, cleaning, and governance tools assure high-quality, compliant data migration. IBM DataStage, part of IBM InfoSphere, is a sophisticated ETL tool for large-scale data integration. DataStage is ideal for complicated data settings with big data volumes because to its great performance and scalability. DataStage can handle the most difficult data migration operations due to its parallel processing and interaction with IBM's data management environment. Enterprises who need a dependable data migration solution can benefit from the platform's metadata management, data lineage, and real-time data integration, which interface with many databases and applications.

The Perception of Chronic Disease Management of Family Physicians and Family Medicine Residents

Aim: This study aims to evaluate the attitudes and behaviors of family physicians and family medicine residents working in primary care regarding the management of chronic diseases and the use of diagnosis and treatment guidelines. Methods: In the cross-sectional study, data were collected from the participants online, with the help of a questionnaire in the first part consisting of the sociodemographic characteristics of the physicians and their views, behaviors and attitudes about chronic care, and in the second part, a data form prepared by the researchers using the Patient Assessment of Chronic Illness Care Scale. Results: Of the participants, 57.3% use the diagnosis and treatment guidelines prepared for chronic diseases, 37.7% (n=148) do not use guidelines. The remaining 5.1% (n=20) are not aware of such guidelines. Among the physicians who do not use guides, 58.8% stated that they don’t use guides because they don’t have sufficient motivation to use the diagnosis and treatment guides in their daily practice, 49.3% don’t have enough time to use the guides, 29.1% don’t have foreign language proficiency to follow international guides. Conclusion: Family physicians will be able to take a more active role in the management of chronic diseases after the development of diagnostic treatment guides for primary care and the establishment of the necessary infrastructure for integrated information systems that can be accessed electronically. Keywords: chronic disease, family practice, physicians, disease management

Multimodal monitoring in patients with acute brain injury – A survey from critical care providers

BackgroundMultimodal neuromonitoring (MMM) aims to improve outcome after acute brain injury, and thus admission in specialized Neurocritical Care Units with potential access to MMM is necessary. Various invasive and noninvasive modalities have been developed, however there is no strong evidence to support monitor combinations nor is there a known standardized approach. The goal of this study is to identify the most used invasive and non-invasive neuromonitoring modalities in daily practice as well as ubiquitousness of MMM standardization. MethodsIn order to investigate current availability and protocolized implementation of MMM among neurocritical care units in US and non-US intensive care units, we designed a cross-sectional survey consisting of a self-administered online questionnaire of 20 closed-ended questions disseminated by the Neurocritical Care Society. ResultsTwenty-one critical care practitioners responded to our survey with a 76% completion rate. The most commonly utilized non-invasive neuromonitoring modalities were continuous electroencephalography followed by transcranial doppler. The most common invasive modalities were external ventricular drain followed by parenchymal intracranial pressure (ICP) monitoring. MMM is most utilized in patients with subarachnoid hemorrhage and there were no differences regarding established institutional protocol, 24-h cEEG availability and invasive monitor placement between teaching and non-teaching hospitals. MMM is considered standard of care in 28% of responders' hospitals, whereas in 26.7% it is deemed experimental and only done as part of clinical trials. Only 26.7% hospitals use a computerized data integration system. ConclusionOur survey revealed overall limited use of MMM with no established institutional protocols among institutions. Ongoing research and further standardization of MMM will clarify its benefit to patients suffering from severe brain injury.

The future of accounting in Ukraine: trends and forecasts in the conditions of rapid digital transformation

The paper is devoted to the study of trends and forecasts of the development of accounting in Ukraine in the conditions of rapid digital transformation. Scientific and empirical methods (collection and comparison of information), as well as complex analytical methods (synthesis and generalization) were used during the research. The informational basis of the paper is the scientific works of both domestic and foreign scientists who studied accounting issues in the conditions of rapid digital transformation. The paper noted that accounting in Ukraine today is undergoing major changes in connection with the introduction of digital technologies, which is a necessary and key stage for ensuring the effective functioning of the organization. It was noted that digitization of accounting and its integration into the company's information system is not only a necessity, but also a strategic step in modern business. This process is aimed at optimizing financial processes, ensuring fast and accurate data processing. An integrated information system allows not only to store information, but also to analyze it, providing the company's management with valuable insights for making strategic decisions. This approach turns accounting into a powerful tool that contributes to the growth and success of the enterprise in conditions of constant competition. It is also stated that in the future accounting in Ukraine will continue to evolve rapidly under the influence of digital transformation and the latest technologies. The paper examines key trends and forecasts for the future of accounting in Ukraine in conditions of rapid digital transformation: process automation, "cloud" technologies, data analysis and forecasting, blockchain, cyber security. The conclusion states that the future of accounting in Ukraine is inextricably linked to the digital transformation taking place in modern business. Successful adaptation to the trends considered in the study will require not only technological readiness, but also cultural and organizational changes aimed at continuous improvement of processes and personnel skills.

The Profile of The Public Accountant, a Response to the Organizational Needs of Non-Profit Entities in the Fourth Industrial Revolution?

Objective: Over time, challenging changes have occurred in industries worldwide, which are transforming productive, economic and commercial relationships. These changes have been called revolutions and we are currently experiencing one of them; the so-called fourth industrial revolution, which eliminates the terms between physical and digital activities. This transition will significantly impact education and organizations because they will require people with new technical and methodological skills. This research aims to identify a professional profile for the public accountant, which adapts to the needs of non-profit organizations in the city of Medellín, in response to the demands generated by the arrival of the fourth industrial revolution. Theoretical framework: For an empirical study, regarding the fact that these entities are always studied from their economic activity, organization and fiscal aspects, but it is the first time that they are taken into account for an analysis in the requirement of their needs with a view to to the corporate purpose of non-profit entities and the fourth industrial revolution. Method: Under a qualitative approach using the inductive method with a phenomenological design, to collect data we will use the technique of personal interviews with open questions directed to the administrators and/or owners of the Non-Profit Entities (ESAL). With this methodology we can achieve the general objective to the extent that, by applying the design steps and their respective analysis; The levels of association between the different hermeneutical and lexical units can be verified, in order to determine needs and trends between the different participants and the results of the research. Results and Conclusions: For the processing and analysis of the data, the size of the population of 20 non-profit organizations in the city of Medellín, it was possible to identify the needs of the public accountant profile from the social and technological aspects. Repercussions of the research: It is a commitment of Public Accountants to maintain the highest levels of professional competence to respond to the needs of organizations generated by the fourth industrial revolution. The accounting professional must have knowledge of integrated data systems, the expansion of cloud computing, the Internet of Things, among others. Therefore, it is necessary to identify the changes that will impact the environment of the public accountant profile and the responses of organizations to these challenges. Originality/value: It is considered that this research, due to its novelty and originality, will generate new knowledge for Higher Education Institutions - IES, to the extent that, through the needs or requirements of the profile of the public accountant, they can make an adjustment to the curriculum of this discipline, managing to integrate the company with the university, this type of organizations are also taken into account by the HEIs.

AIMS TO DIGITALISE THE CIRCULATION OF PRECIOUS METALS, PRECIOUS STONES AND THEIR PRODUCTS

The need to digitalise economic sectors in today’s world is perceived as an objective reality. In the circulation of precious metals, precious stones and their products, the digitalisation process is at a fairly high level, with continuous improvement. The article analyses the progress made in achieving the goals of the implementation of the State Integrated Information System in the Sphere of Control over the Circulation of Precious Metals and Precious Stones at all stages (GIIS DMDK), which is the main project of digitalisation of the industry.

Using machine learning models to predict falls in hospitalised adults

BackgroundIdentifying patients at high risk of falling is crucial in implementing effective fall prevention programs. While the integration of information systems is becoming more widespread in the healthcare industry, it poses a significant challenge in analysing vast amounts of data to identify factors that could enhance patient safety. ObjectiveTo determine fall-associated factors and develop high-performance prediction tools for at-risk patients in acute and sub-acute care services in Australia. MethodsA retrospective study of 672,400 patients admitted to acute and sub-acute care services within a large metropolitan tertiary health service in Victoria, Australia, between January 1, 2019, and December 31, 2021. Data were obtained from four sources: the Department of Health Victorian Admitted Episodes Dataset, RiskManTM, electronic health records, and the health workforce dataset. Machine learning techniques, including Random Forest and Deep Neural Network models, were used to analyse the data, predict patient falls, and identify the most important risk factors for falls in this population. Model performance was evaluated using accuracy, F1-score, precision, recall, specificity, Matthew's correlation coefficient, and the area under the receiver operating characteristic curve (AUC). ResultsThe deep neural network and random forest models were highly accurate in predicting hospital patient falls. The deep neural network model achieved an accuracy of 0.988 and a specificity of 0.999, while the RF achieved an accuracy of 0.989 and a specificity of 1.000. The top 20 variables impacting falls were compared across both models, and 12 common factors were identified. These factors can be broadly classified into three categories: patient-related factors, staffing-related factors, and admission-related factors. Although not all factors are modifiable, they must be considered when planning fall prevention interventions. ConclusionThe study demonstrated machine learning's potential to predict falls and identify key risk factors. Further validation across diverse populations and settings is essential for broader applicability.