Background Recent advances in machine and deep learning based on an increased availability of clinical data have fueled renewed interest in computerized clinical decision support systems (CDSSs). CDSSs have shown great potential to improve healthcare, increase patient safety and reduce costs. However, the use of CDSSs is not without pitfalls, as an inadequate or faulty CDSS can potentially deteriorate the quality of healthcare and put patients at risk. In addition, the adoption of a CDSS might fail because its intended users ignore the output of the CDSS due to lack of trust, relevancy or actionability. Aim In this article, we provide guidance based on literature for the different aspects involved in the adoption of a CDSS with a special focus on machine and deep learning based systems: selection, acceptance testing, commissioning, implementation and quality assurance. Results A rigorous selection process will help identify the CDSS that best fits the preferences and requirements of the local site. Acceptance testing will make sure that the selected CDSS fulfills the defined specifications and satisfies the safety requirements. The commissioning process will prepare the CDSS for safe clinical use at the local site. An effective implementation phase should result in an orderly roll out of the CDSS to the well‐trained end‐users whose expectations have been managed. And finally, quality assurance will make sure that the performance of the CDSS is maintained and that any issues are promptly identified and solved. Conclusion We conclude that a systematic approach to the adoption of a CDSS will help avoid pitfalls, improve patient safety and increase the chances of success.

Non–small cell lung cancer contributes toward 85% of all lung cancer burden. Tumor histology (squamous cell carcinoma, large cell carcinoma, and adenocarcinoma and “not otherwise specified”) has prognostic significance, and it is therefore imperative to identify tumor histology for personalized medicine; however, biopsies are not always possible and carry significant risk of complications. Here, we have used Radiomics, which provides an exhaustive number of informative features, to aid in diagnosis and therapeutic outcome of tumor characteristics in a noninvasive manner. This study evaluated radiomic features of non–small cell lung cancer to identify tumor histopathology. We included 317 subjects and classified the underlying tumor histopathology into its 4 main subtypes. The performance of the current approach was determined to be 20% more accurate than that of an approach considering only the volumetric- and shape-based features.

Abstract-Radiotherapy plays an important role in the treatment of cancer patients. As part of clinical workflow, patient has to undergo through diagnostic imaging procedures, which are used to identify the tumor location and size. Enormous amounts of data are generated during this procedure. The volume of medical information is so large and complex that it becomes difficult to mine for relevant information. The Digital Imaging and Communications in Medicine (DICOM) standard is widely used in medicine for storing and transmitting medical information. The DICOM-RT is the extension to DICOM standard, and dedicated to radiotherapy. In this paper, we propose a technique to store clinical relevant features from DICOM files using semantic concepts. The proposed technique defines a novel method to delayer the hierarchy of DICOM-RT for storing the clinical relevant information into triples in Resource Description Framework (RDF) repository. The methodology also proposes different combinations for storing data such as DICOM-RT with tumor information, DICOM-RT with pathology details. The proposed method uses the Semantic Web Technology to store and represent the information from DICOM-RT files along with into RDF graph and a data mining approach. Natural Language processing technique is used for the retrieval of data. We have evaluated our methodology qualitatively for 20 patients including combinations such as RTSTRUCT, tumor size data along with CT data, pathology information, by producing 25 varieties of different queries. We have analyzed quantitatively with accuracy of 90% for different hypothetical conditions using our proposed methodology.Keywords-DICOM-RT, Semantic Web, RDF, SPARQL, Natural Language Processing. IntroductionRadiation therapy is one method of the cancer treatment, and plays an important role for patient during the course of the disease [1]. In this process, patients have to undergo diagnostic imaging procedures, which are performed to identify the tumor location and size. Data generated during this procedure contains large volume of information as well as complex structures, which makes it a challenging task for clinicians to query and retrieve relevant data The DICOM-RT objects provides information about patient related structures identified from diagnostic data known as radiotherapy structure set (RTSTRUCT), contains radiotherapy treatment plan information (RTPLAN) and also provides total dose distributions from the planning systemdose information (RTDOSE) [5]. The DICOM-RT objects are stored in hierarchal manner; this restricts the search path while traversing the DICOM modalities and the DICOM query model itself and current DICOM tools do not support this required traversing well [6]. The literature shows planning for dose to be received by a certain region of interest in a radiotherapy treatment is to find the region of interest (ROI) name and contour points in the RTSTRUCT object. The coordinates and slices are defined in the CT objects, the treatment information stored in RTPLAN object and dos...

No abstract

No abstract