Decision making on the treatment of vestibular schwannoma (VS) is mainly based on the symptoms, tumor size, patient’s preference, and experience of the medical team. Here we provide objective tools to support the decision process by answering two questions: can a single checkup predict the need of active treatment?, and which attributes of VS development are important in decision making on active treatment? Using a machine-learning analysis of medical records of 93 patients, the objectives were addressed using two classification tasks: a time-independent case-based reasoning (CBR), where each medical record was treated as independent, and a personalized dynamic analysis (PDA), during which we analyzed the individual development of each patient’s state in time. Using the CBR method we found that Koos classification of tumor size, speech reception threshold, and pure tone audiometry, collectively predict the need for active treatment with approximately 90% accuracy; in the PDA task, only the increase of Koos classification and VS size were sufficient. Our results indicate that VS treatment may be reliably predicted using only a small set of basic parameters, even without the knowledge of individual development, which may help to simplify VS treatment strategies, reduce the number of examinations, and increase cause effectiveness.
PurposeThe traditional service market is composed of customers and service providers, interacting within a given structure and following market‐specific rules. These basic attributes are obvious and persistent. The fragile entity, which is essential for normally operating and self‐controlling market, is information. In this context the aim is to distinguish between a background noise, arising from comprehensive marketing campaigns, customer care activities or advertisement and data, advices or knowledge, necessary for any focused business decision. The straightforward example of prospective market suffering from information shortage is healthcare. For a normal patient it is almost impossible to select purposely a better doctor, hospital or therapy. Even providers of care are not always sure about the exact diagnosis, resulting in the extended length of patient's stay and its related costs.Design/methodology/approachFrom the knowledge engineering point of view, the national market of healthcare services is a platform where distributed micro behavior of patients interacts with centralized, systemic activities of medical care and insurance providers under the umbrella of governmental rules. Owing to the problem complexity, a significant portion of included subjectivity and natural heterogeneity of available knowledge, the authors have adopted a combined modeling platform as the most natural way of its formalization and processing. Typical groups of patients are represented as multi‐state agents, adjusting reactions and preferences quickly in accordance with time, changing environment and quality of accessible information. Hospitals, on the contrary, are considered as system dynamic enterprises with domain‐tailored processes both on operational and managerial levels.FindingsThe first interesting outcome is the clear experimental evidence, justifying the impossibility of purely market‐driven control and development of a national healthcare system. Furthermore, the paper presents a novelty heterogeneous model as a viable tool for analysis of emergent market behavior enabling evaluation of different public health policies.Practical implicationsThe developed model can serve both policy makers and hospital managers. To the former it can experimentally help to investigate the influence of parametric changes of overall market regulations. The latter can benefit especially from optimization of internal processes, leading both to performance and competitive advantage improvements. Moreover, due to its transparency and interactivity, the method of heterogeneous modeling is ideal for strategic planning, group decision making, capturing and sharing of organizational knowledge or organizational learning. Finally, the implementation flexibility and architectural scalability predetermines combined modeling as a convenient technique for rapid prototyping of complex problems.Originality/valueThis paper combines areas of health economics, enterprise management and computational economics in a challenging and innovative way. The value ...
Background: The aim of our study was to compare the analgesic/sedative effects of various fundus-related procedural pain management strategies on the risk of retinopathy in premature infants. Method: This was a prospective comparative study involving a total of 94 neonates randomized to three groups meeting the criteria for at-risk neonates. Ophthalmologic screening was performed to evaluate the outcome of three procedural pain management strategies. The intensity of pain over time during and after the screening examination was evaluated. At the same time, we also looked at the occurrence of vegetative symptoms and their influence by the chosen medication. Pain response was observed in all 94 neonates enrolled in the study. In group A, no pain treatment was given. Group B had a local anesthetic oxybuprocaine hydrochloride 0.4% introduced into both eyes immediately prior to the examination. Group C received oral clonidine. The study was conducted as a pilot project and aimed to clarify the problem so that a project with a higher proband representation could take place in the future. Consequently, we performed quantitative analysis of complete pain and vegetative functions, followed by a qualitative analysis of their internal components. Results: In our study, we identified the most considerable effects for all three groups, including NIPS (Neonatal Infant Pain Scale) responses immediately during and after the examination. The influence of vegetative functions is of a longer-term nature and increased values can be clearly demonstrated even six hours after the examination. Conclusion: The current results identify and quantify differences among all three methods of pain treatment on the level of single variables. Their internal structures, however, can be analysed only qualitatively because of the small size of the analysed sample.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.