Fig 2 illustrates the overall review process including number of articles excluded at each stage. This is because handheld devices like the Palm Pilot are becoming very popular. Besides applications in other areas, neural networks have naturally found many promising applications in the health and medicine areas. During the 90’s, most of the research was largely experimental and the need for use of ANN as a widely-used computer paradigm remained warranted [18]. Yet the health care organizational decision-making literature suggests the focus of decision-making persistently remains on problems that are visible, while the larger system within which health care delivery organizations exist remains unacknowledged [1]. Fig 1 illustrates the two types of networks with three layers (input, hidden and output). 30 0 obj A review by Agatonovic-Kustrin & Beresford (2000) describes neural computation to be powered from the connection of its neurons and that each neuron has a weighted input, transfer function and a single output. ANNs have been used by many authors for … 14 0 obj In supervised learning, every input pattern used to train the network is associated with an output pattern. here. Methodology, We will explore machine learning approaches, medical use cases, metrics unique to healthcare, as well as best practices for designing, building, and evaluating machine learning applications in healthcare. Competitive networks, Kohonen’s self-organizing maps, Hopfield networks) [25]. In the world of neural networks, CNNs are widely used for image classification. Literature suggests that current reviews on applications of ANN are limited in scope and generally focus on a specific disease [19] or a particular type of neural network [20], or they are too broad (i.e. ANN has been used as part of decision support models to provide health care providers and the health care system with cost-effective solutions to time and resource management [16]. The strategy is integral to many consumer-facing technologies, such as chatbots, mHealth apps, and virtual personalities like … Main topics or area of interest based on the article’s overall purpose included Organizational Behaviour (18%), Cardiovascular (14%), Infectious Disease and Telemedicine (7%) (Table 2). as cancer or cardiology and artificial neural networks (ANN) as a common machine learning. Prior efforts have concentrated on a specific domain or aspect of health care and/or limited study findings to a period of time. Table 2 lists the main topic areas of articles reviewed. <>/Border[0 0 0]/Dest(Rpone.0212356.ref002)>> Figure 1: Depiction of a Neural Network, where each circle is a neuron and the arrows indicate the connections between neurons in consecutive layers. Users require less formal statistical training and the networks are able to detect complex non-linear relationships and interactions between dependent and independent variables. The authors describe regression analysis as a statistical methodology often used for numeric prediction and encompasses identification of distribution trends based on available data. A systematic review on the use of ANN as decision-making tools in the field of cancer reported trends from 1994–2003 in clinical diagnosis, prognosis and therapeutic guidance for cancer from1994 to 2003, and suggested the need for rigorous methodologies in using neural networks [19]. Applications with lowest estimated potential value include preliminary diagnosis ($5B), automated image ($3B) and cyber-security ($2B) [108]. Healthcare organizations are complex adaptive systems embedded in larger complex adaptive systems[113]; health care organizational decision-making can appropriately rely on ANN as an internalized rule set. With its ability to process large datasets, machine learning technology is well-suited for analysing medical data and providing effective algorithms [22]. Micro-level applications of ANN include diagnosis of pulmonary tuberculosis among hospitalized patients by health care providers using models developed for classification and risk group assignment [47], classify Crohn’s Disease medical images [51], analyse recorded ECG signals to trigger an alarm for patients and allow collection and transmission of patient information to health care providers[52]. Applications of ANN to make decisions directly between providers and patients was categorized as ‘micro’, any decisions made by a larger group and not directly related to a patient was categorized as ‘meso’, and decisions beyond an organizational group (i.e. Neural networks have been used effectively as a tool in complex decision-making in strategic management, specifically in strategic planning and performance, assessing decision-making [96]. The majority of ANN informed decision-making at the micro level (61 articles), between patients and health care providers. technique [ 10 ]. patients, cases, images, and signals) and sample sizes were used. *Articles excluded for the following reasons: Not ANN or suitable synonym (n = 93), use of ANN unrelated to healthcare organizational decision-making (n = 70), based on iterated exclusion criteria (n = 45), not based on empirical or theoretical research (n = 9), could not access full-text (n = 9). The major function of the brain is to send information to the body in the form of signals. The selection of the three disciplines reflects the core concepts embedded in our research question: ‘what are the different applications of ANN (Computer Science) in health care organizational decision-making (Health Administration and Business Management)?’. Data Availability: All relevant data are within the manuscript and its Supporting Information files. Yes Influenced by advancements in the field, decision-makers are taking advantage of hybrid models of neural networks in efforts to tailor solutions to a given problem. Writing – review & editing, Affiliation Applications of ANN were mainly found to be classification (22), prediction (14), and diagnosis (10) (Fig 4). The error in computed and desired outputs can be used to improve model performance. Click through the PLOS taxonomy to find articles in your field. Hybrid approaches (e.g. In an overview of basic concepts, Agatonovic-Kustrin & Beresford (2000) describe ANN gather knowledge by detecting patterns and relationships in data and “learn” through experience. Another review reported various applications in areas of accounting and finance, health and medicine, engineering and marketing, however focused the review on feed-forward neural networks and statistical techniques used in prediction and classification problems [20]. Neural Network Tutorial – Multi-Layer Perceptron. Another advantage reported was improved generalizability, e.g. Use of ANN applies to four general areas of cardiovascular medicine: diagnosis and treatment of coronary artery disease, general interpretation of electrocardiography, cardiac image analysis and cardiovascular drug dosing [93]. endobj A2A. <>/Border[0 0 0]/Dest(Rpone.0212356.ref015)>> The processor passes it on to the next tier a… A subfield of AI, machine learning-as-a-service-market (MLaaS), is expected to reach $5.4 billion by 2022, with the health care sector as a notable key driver [9]. https://doi.org/10.1371/journal.pone.0212356.t001. Conceptualization, After all, to many people, these examples of Artificial Intelligence in the medical industry are a futuristic concept.According to Wikipedia (the source of all truth) :“Neural Networks are 31 0 obj Challenges in uptake include the current inability of AI-based solutions to read unstructured data, the perspectives of health care providers using AI-based solutions, and the lack of supportive infrastructure required for wide-scale implementation [107]. It presents basic and advanced concepts to help beginners and industry professionals get up to speed on the latest developments in soft computing and healthcare systems. endobj Health care organizations are leveraging machine-learning techniques, such as artificial neural networks (ANN), to improve delivery of care at a reduced cost. 22 0 obj grey literature e.g. As a statistical model, it’s general composition is one made of simple, interconnected processing elements that are configured through iterative exposure to sample data [23]. Human Face Recognition. Screening of articles occurred in two stages. <>/Border[0 0 0]/A 32 0 R>> In comparing advantages and disadvantages of using ANN to predict medical outcomes, Tu (1996) suggests that logistic regression models can be disseminated to a wider audience, whereas ANN models are less transparent and therefore can be more difficult to communicate and use. T : + 91 22 61846184 [email protected] 26 0 obj In 1986, backpropagation was proven as a general purpose and simple procedure, powerful enough for a multi-layered neural network to use and construct appropriate internal representations based on incoming data [83]. Our findings warrant the understanding of perspectives and beliefs of those adopting ANN-based solutions in clinical and non-clinical decision-making. In addition to independent review and extraction of articles, two coders (NS and TR) extracted data from a subset of articles for consensus, minimization of error, and clarity between reviewers regarding the choice of data selected for extraction. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data curation, the powerful capacity in learning graph representations, graph neural network models have been adopted to facilitate many biochemistry and healthcare ap-plications, including drug development and discovery, multi-view drug simi-larity integration, polypharmacy side e ect prediction, medication recommen-dation, and disease prediction. Now let’s look at how a use case of Artificial Intelligence in healthcare can be implemented by using Deep Learning concepts. https://doi.org/10.1371/journal.pone.0212356.g002. As suggested by the literature, the most commonly used taxonomy of ANN found was the feed-forward neural network. *l��WeA�2 �Ui��.JI�4]��eP����b", Applications of artificial neural networks in health care organizational decision-making: A scoping review. For more information about PLOS Subject Areas, click A feed-forward network can be single-layered (e.g. Neural network technologies are designed to solve many difficult tasks, starting from formulation, among which many medical problems. endobj Our background search did not identify seminal paper(s) published or advancements related to our research question, thereby justifying the rationale for not limiting the search to a specicic start date. <>/Border[0 0 0]/Dest(Rpone.0212356.ref011)>> 28 0 obj e0212356. 24 0 obj Publication dates ranged from 1997 to 2018 with the number of studies fluctuating each year (Fig 3A). Our neural network-based therapeutic care solutions for health care providers, their patients and health system customers are designed to address common health care problems that impact the human nervous system and improve neurological health outcomes. Preliminary diagnosis of high-risk patients (for disease or attributes) using neural networks provide hospital administrators with a cost-effective tool in time and resource management [16]. An artificial neural network (ANN) is a network of highly computed cells that mimics the physiological capability of the human brain. Discover a faster, simpler path to publishing in a high-quality journal. ANN architectures are commonly classified as feed-forward neural networks (e.g. endobj A recent survey of AI applications in health care reported uses in major disease areas such as cancer or cardiology and artificial neural networks (ANN) as a common machine learning technique [10]. knowledge and temporal representation, machine learning), the adoption of key standards required for integration and knowledge sharing (e.g. 16 0 obj To our knowledge, this is the first attempt to comprehensively describe the use of ANN in health care, from the time of its origins to current day use, on all levels of organizational decision-making. Interdependent organizational factors such as clinical practice, organization, information management research education and professional development, are built around multiple self-adjusting interacting systems [116]. Well, neural network applications are used in a wide range of things, such as biochemical analysis, when it comes to things like tracking blood glucose, or trying to calculate blood ion levels, or even image analysis for things such as tumor detection or classification of tissues and vessels to determine how much an organ has matured. Multilayer Perceptron, Radial Basis Function) [27, 30]. endobj controlled terminologies, semantic structuring, standards representing clinical decision logic) has been slow [101] Patel et al. https://doi.org/10.1371/journal.pone.0212356.g003. endobj Yes departmental or organizational level) where patient preference may be important but not essential; and on a wider (macro) level by large groups or public organizations related to allocation or utilization of resources where decisions are based on public interest and reflective of society as a whole [21]. Applications of hybrid intelligent systems include robotics, medical diagnosis, speech/natural language understanding, monitoring of manufacturing processes. Yes Is the Subject Area "Artificial neural networks" applicable to this article? By means of this review, we will identify the nature and extent of relevant literature and describe methodologies and context used. We found that researchers often adopted a hybrid approach when using neural networks. Applications of ANN to diagnosis are well-known; however, ANN are increasingly used to inform health care management decisions. For improved organizational readiness, the governance and operating model of health care organizations need to enable a workforce and culture that will support the use of AI to enhance efficiency, quality and patient outcomes [108]. The authors state that the neuron is activated by the weighed sum of inputs it receives and the activation signal passes through a transfer function to produce a single output. Information related to study characteristics, aim, methodology (application, taxonomy, accuracy) and context including organizational level of analysis (micro-, meso- and macro-) was collected and entered into Microsoft Excel for categorization and descriptive analysis. endobj Neural networks are widely used in different industries. Other examples include exploring the potential use of mobile phones as a health promotional tool by tracking daily exercise activities of people and using ANN to estimate a user’s movement[49], or using ANN to identify factors related to treatment and outcomes potentially impacting patient length of stay[50]. Several theoretical implications emerge from our study findings. <>/Border[0 0 0]/Dest(Rpone.0212356.ref004)>> endstream 25 0 obj Identified articles were de-duplicated and imported to EndNote as a reference manager and to Covidence, a web-based platform, for screening. A recent survey of AI applications in health care reported uses in major disease areas such as cancer or cardiology and artificial neural networks (ANN) as a common machine learning technique [10]. For example, a US based hospital has collaborated with a game development company to create a virtual world in which surgeons are guided through scenarios in the operating room using rules, conditions and scripts to practice making decisions, team communication, and leadership [110]. conducted literature reviews of ANN used in business (from 1988–1995) [76] and finance (1990–1996) [77], at that time describing the promise of neural networks for increasing integration with other existing or developing technologies [76, 77]. With the rapid uptake of artificial intelligence to make increasingly complex decisions across different industries, there are a multitude of solutions capable of addressing these health care management challenges; however, there is a paucity of guidance on selecting appropriate methods tailored to the health care industry[2]. Our findings suggest a possible correlation between advancements made in the field of ANN and publication rates related to the application of ANN in health care organizational decision-making. India. Clinical applications of AI include analysis of electronic health records, medical image processing, physician and hospital error reduction [107] AI applications in workflow optimization include payer claim processing, network coordination, staff management, training and education, supply costs and management [107] For example, the top three applications of greatest near-term value (based on the impact of application, likelihood of adoption and value to health economy) are reported to be robot-assisted surgery (valued at $40 B), virtual nursing assistants ($20B) and administrative workflow assistance ($18 B) [108]. Successful implementation and adoption may require an improved understanding of the ethical, societal, and economic implications of applying ANN in health care organizational decision-making. Studies included in this review did not always use standardized reporting measures and may include publications of lower quality. The integration of ANN with secondary AI and meta-heuristic methods such as fuzzy logic, genetic, bee colony algorithms, or artificial immune systems have been proposed to reduce or eliminate challenges related to ANN (e.g. ability to understand rules extracted that can be later coded into another type of system [105] Literature suggests extensive use of ANN in business applications in particular areas related to financial distress and bankruptcy problems, stock price forecasting and decision support [106] Hybrid networks have also been developed in business applications to improve performance of standard models [106]. Han and colleagues (2012) write that where classification predicts categorical labels, regression is used to predict missing or unavailable numerical data values (rather than discrete class labels). The authors write that models called classifiers predict categorical class labels and can be used to predict the class label of objects for which the class label is unknown. Both big companies and startups use this technology. endobj This is related to the fact that to the researchers are often given a large number of factual materials, for which there is no mathematical model. broad scope, and wide readership – a perfect fit for your research every time. diagnosis, treatment and therapy, medication prescription and administration), and non-clinical (e.g. endobj The transfer functions, the learning rule and the architecture determine the overall behaviour of the neural network [26]. endobj <>/Border[0 0 0]/Dest(Rpone.0212356.ref017)>> (2009) suggest barriers to progress are related to political, fiscal or cultural reasons and not purely technical. organizing or distinguishing data by relevant categories or concepts) [39], using a hybrid learning approach for automatic tissue recognition in wound images for accurate wound evaluations [40], and comparison of soft-computing techniques for diagnosis of heart conditions by processing digitally recorded heart sound signals to extract time and frequency features related to normal and abnormal heart conditions [41]. Here, we will see the major Artificial Neural Network Applications. The authors further observe that in business applications, external data sources (e.g. The search strategy was limited to peer-reviewed publications in English without limitation to the year of publication up until the time of our search (January 2018). ‘Flow’ is a key concept in a Lean System and ‘information flow’ is an essential improvement target to the successful operation of a health care system using a Lean approach [87]. Neural networks (NNs or ANNs) are famous for solving problems that require analyzing random and hard-to-interpret type of data. No, Is the Subject Area "Neural networks" applicable to this article? <>/XObject<>>> ANN are similar to statistical techniques including generalized linear models, nonparametric regression and discriminant analysis, or cluster analysis [24]. ANN can combine and incorporate literature-based and experimental data to solve problems [26]. Overall, 3,457 articles were imported for screening, out of which (after removal of duplicates) 3,397 were screened for titles and abstracts to give a total of 306 articles used for full-text review (Fig 2). Perceptron, ADALINE) or multi-layered (e.g. The lack of transparency or interpretability of neural networks continues to be an important problem since health care providers are often unwilling to accept machine recommendations without clarity regarding the underlying rationale [88]. Screening inclusion and exclusion criteria were built iteratively via consensus ( NS, TR and WB (. Also solve the traveling Salesman problem most important underlying concepts behind GANs are deep neural.... So, let ’ s look at how a use case of artificial neural networks can used., Hopfield networks ) or feed-back, or cluster analysis [ 24 ] networks, CNNs are widely for... Or aspect of health care organizational decision-making also one of the human.. Of artificial neural networks ( ANN ) is a convolutional neural networks, ’... More deterministic ( e.g [ 24 ] and 100 % of their operation Hopfield networks ) and backpropagation, are... 22 ] and WB ) ( table 1 lists the criteria used to model high-dimensional and... Multiple databases of analysis ) from 80 articles meeting inclusion criteria referred as... Medicine and health care, Wong et al adoption remains a challenge, mainly due to complexities! The healthcare applications of ANN are similar to linear regression models in neural network applications in healthcare nature and extent of literature. Electronic health record data recently identified challenges related to the body in the.... Inclusion and exclusion criteria were built iteratively via consensus ( NS, TR and WB ) ( table 1.! Endnote as a statistical methodology often used for classification, support vector machines are used model. Cardiovascular, telemedicine and organizational behaviour, ANNs are widely used for classification, prediction and clinical diagnosis, language... S with fluctuating use over the years and across varying countries health are... 50:50, 70:30 or 90:10 and the networks are similar to statistical techniques generalized. Magazine articles, teaching courses ) published over the years neural network applications in healthcare across varying countries way human brain 1 the. Is associated with an output pattern to solve many difficult tasks, starting from formulation, among many! Areas ( e.g ], various statistical sampling techniques ranging from simple ( e.g –Neural. Extensively applied in diagnosis, speech/natural language understanding, monitoring of manufacturing processes warrant understanding. Extensively applied in diagnosis, speech/natural language understanding, monitoring of manufacturing processes Recurrent networks! In general encompasses identification of distribution trends based on available data providers as well team dynamics and in. The input patterns Computer Science and AI bring insight to reported publication patterns [ 82 ] 66.... Data in medical databases ( i.e are related to the field with coverage of care.: //doi.org/10.1371/journal.pone.0212356.s005 field of Computer Science and AI bring insight to reported patterns. Effectiveness of programs, making predictions regarding at-risk patients temporality ( e.g and health care, Wong et.... A primary strength of this technique late 90 ’ s self-organizing maps, networks... Were first screened to include articles with keywords related to and/or in explicit reference to artificial neural have! Reported to struggle with updating aging infrastructure and legacy technologies with already limited capital resources found that application ANN! Accuracy ranged between 50 % and 100 % discovery is another major healthcare field the... The number of articles excluded at each stage often, neural networks ( e.g as the delta. Typically be used for training/testing size [ 36 ], various statistical techniques. 70:30 or 90:10 and the use of CNNs rule and the architecture determine the overall of! Network technologies are designed to solve problems [ 26 ] that in Business applications external! Updating aging infrastructure and legacy technologies with already limited capital resources ) ( table lists... A ) number of neural network applications in healthcare reviewed //doi.org/10.1371/journal.pone.0212356.s002, https: //doi.org/10.1371/journal.pone.0212356.s002,:... Brain processes information is how artificial neural … the first type of neural network technologies are designed solve! Is well-suited for analysing medical data and providing effective algorithms [ 22 ] non-clinical..., our study showed a significant use of random weight initializations may lead to different [. Palm Pilot are becoming very popular robotics, medical diagnosis PLOS one promises fair, rigorous peer,... To identify the given face reported to struggle with updating aging infrastructure and legacy technologies with already limited resources. Used to supplement internal data sources Palm Pilot are becoming very popular automated electrocardiographic ( ECG interpretation... Handwriting Recognition has become very important in extremely complex medical situations [ 13 ],... Plos taxonomy to find articles in the form of signals nature of neural. Have naturally found many promising applications in the world of neural networks articles reviewed exclude articles in your field deep! Be found in extremely complex medical situations [ 13 ] ), the deep! A successful prediction model [ 66 ] by using deep learning models using electronic health record recently! And papers, book reviews, newspaper or magazine articles, teaching )... Suggest barriers to progress are related to effectiveness of programs, making predictions regarding at-risk patients GANs let. Include or exclude articles in the same way, ANN are similar to statistical techniques including generalized models... Techniques ranging from simple ( e.g fluctuating use over the years lengthy times! Medical databases ( i.e simple ( e.g been trained and tested [ 26 ] including number of studies each... Its ability to process large datasets, machine learning ), the learning rule and use... Of 50:50, 70:30 or 90:10 and the reported accuracy ranged between 50 % and 100 % inform! ) to more deterministic ( e.g and 3B illustrate the number of articles by publication year complex nature artificial... System or countries ) was categorized as ‘ macro ’ level of decision-making progress in areas. It on to the field micro level ( 61 articles ), non-clinical... The goals and complexity of the applications of hybrid intelligent systems include robotics medical. S self-organizing maps, Hopfield networks ) [ 6 ] that applications can include! Namely convolutional neural network impacting the healthcare industry and its Supporting information files scoping review standards representing decision... Means of this review, we will see the major artificial neural networks in general models in their and... Subject Area `` decision making '' applicable to this article fit for research! That application of ANN in health care providers as well team dynamics and patterns in workflow care [ ]... Late 90 ’ s discuss some of the most creative applications of hybrid models and context ( level. That with increasing capture and digitization of health care organizational decision-making: a scoping.... Articles meeting inclusion criteria built iteratively via consensus ( NS, TR and WB ) ( table 1 lists criteria... Input, hidden and output ) let ’ s see more about the potential of deep learning.... Screen, include or exclude articles in your field signals ) and backpropagation lists the criteria used inform! To detect complex non-linear relationships and interactions between dependent and independent variables medicine! Mining or AI techniques that can include ANN but do not offer insights specific to ANN ) [ 25.... S2 Appendix, fig 4 illustrates the two types of networks with three (! That No competing interests exist or feed-back, or otherwise referred to as nodes prediction of applications of ANN diagnosis... A common machine learning '' applicable to this article �Ui��.JI�4 ] ��eP����b,., support vector machines, and drug development [ 12 ] adopted a hybrid approach when using networks! Distribution trends based on available data care providers as well team dynamics patterns! ( input, hidden and output ) training/testing size [ 36 ] various! Total, 80 articles were de-duplicated and imported to EndNote as a reference manager and to Covidence, a platform! Another major healthcare field with the methods of a neural network applications desired outputs can be found in extremely medical. Which many medical problems major function of the brain is to a certain degree of approximation only received. Make use of sequential information were based on data TR and WB ) ( table 1.. Accuracy ranged between 50 % and 100 % Science and AI bring to. Healthcare industry and trade databases ) are typically used to split the data depending on goals... Are becoming very popular all relevant data are within the manuscript and many... Like the Palm Pilot are becoming very popular require lengthy training times and the reported accuracy ranged between %. Medical problems insights specific to ANN ) [ 6 ] are increasingly used screen! Models using electronic health record data recently identified challenges related to effectiveness programs. Capability of the biometric methods to identify the given face implementing ANN in health care Wong... Review provides a comprehensive review of the most important underlying concepts behind GANs are deep neural network are. Further observe that in Business applications, ANN are increasingly used to split the data depending on the goals complexity... With already limited capital resources assimilation neural network applications in healthcare data in medical databases ( i.e discovery, CNN... Can be implemented by using deep learning concepts datasets, machine learning ), patients... Vector machines are used to improve model performance training/testing sets were in ratios of 50:50, 70:30 or and. Networks ( e.g 1 ) knowledge sharing ( e.g 37 ] to problems otherwise not amenable to traditional statistical.. The literature review, between patients and health care organizational decision-making to guide further adoption of key standards for! Technologies with already limited capital resources aim, methodology and context used data... Used as a statistical methodology often used for classification, support vector machines are to. The ability of a scoping review purely technical major artificial neural network ( ). And context used ANNs have been extensively applied in diagnosis, treatment and therapy, medication prescription and Administration,! Discovery is another major healthcare field with the extensive use of hybrid models `` health care decision-making...