Medical Device Software Development Research Articles

Development of medical device software for the screening and assessment of depression severity using data collected from a wristband-type wearable device: SWIFT study protocol.

Few biomarkers can be used clinically to diagnose and assess the severity of depression. However, a decrease in activity and sleep efficiency can be observed in depressed patients, and recent technological developments have made it possible to measure these changes. In addition, physiological changes, such as heart rate variability, can be used to distinguish depressed patients from normal persons; these parameters can be used to improve diagnostic accuracy. The proposed research will explore and construct machine learning models capable of detecting depressive episodes and assessing their severity using data collected from wristband-type wearable devices. Patients with depressive symptoms and healthy subjects will wear a wristband-type wearable device for 7 days; data on triaxial acceleration, pulse rate, skin temperature, and ultraviolet light will be collected. On the seventh day of wearing, the severity of depressive episodes will be assessed using Structured Clinical Interview for DSM-5 (SCID-5), Hamilton Depression Rating Scale (HAMD), and other scales. Data for up to five 7-day periods of device wearing will be collected from each subject. Using wearable device data associated with clinical symptoms as supervisory data, we will explore and build a machine learning model capable of identifying the presence or absence of depressive episodes and predicting the HAMD scores for an unknown data set. Our machine learning model could improve the clinical diagnosis and management of depression through the use of a wearable medical device. [https://jrct.niph.go.jp/latest-detail/jRCT1031210478], identifier [jRCT1031210478].

The EU medical device regulation: Implications for artificial intelligence-based medical device software in medical physics.

Medical device manufacturers are increasingly applying artificial intelligence (AI) to innovate their products and to improve patient outcomes. Health institutions are also developing their own algorithms, to address specific needs for which no commercial product exists. Although AI-based algorithms offer good prospects for improving patient outcomes, their wide adoption in clinical practice is still limited. The most significant barriers to the trust required for wider implementation are safety and clinical performance assurance . Qualified medical physicist experts (MPEs) play a key role in safety and performance assessment of such tools, before and during integration in clinical practice. As AI methods drive clinical decision-making, their quality should be assured and tested. Occasionally, an MPE may be also involved in the in-house development of such an AI algorithm. It is therefore important for MPEs to be well informed about the current regulatory framework for Medical Devices. The new European Medical Device Regulation (EU MDR), with date of application set for 26 of May 2021, imposes stringent requirements that need to be met before such tools can be applied in clinical practice. The objective of this paper is to give MPEs perspective on how the EU MDR affects the development of AI-based medical device software. We present our perspective regarding how to implement a regulatory roadmap, from early-stage consideration through design and development, regulatory submission, and post-market surveillance. We have further included an explanation of how to set up a compliant quality management system to ensure reliable and consistent product quality, safety, and performance .

Research on Medical Device Software Development and Design Based on CMMI Model

Research on Medical Device Software Development and Design Based on CMMI Model

To what extent the medical device software regulations can be achieved with agile software development methods? XP—DSDM—Scrum

For medical device software development organizations, it is very challenging to maintain both conformance to the strict regulatory requirements enforced by the safety-critical nature of the domain and achieve efficiency in software development. Agile software development methods provide promising solutions to overcome the efficiency issues and the challenges of traditional software development approaches in the domain. Previously, we investigated to what extent the regulatory requirements defined in MDevSPICE® (the software process assessment framework for medical device software development) are met through using eXtreme Programming (XP) and Scrum and what additional practices have to be performed to ensure safety and regulatory compliance in the medical device software development domain. In this paper, we extended the research to include the Dynamic Systems Development Method (DSDM) which covers the whole software development life cycle. Here, we provide a comprehensive and quantitative analysis of XP’s and DSDM’s suitability for medical device software development and briefly discuss Scrum from the same perspective. We provide the coverage ratios of processes and practices defined in MDevSPICE® when these agile software development methods are implemented.

Implementation of Kanban Practices with a Medical Device Software Development Lifecycle

The objective of this study is to provide a better understanding of the challenges faced by software developers when developing safety-critical medical device software by the use of a plan-driven SDLC and to resolve these shortcomings by the proposition of a mixed method SDLC (KV-model) to the development of software as medical device.

Taxonomy‐based testing and validation of a new defect classification for health software

AbstractDefect‐based testing is a powerful tool for finding errors in software. Many software manufacturers avoid this method because it requires a detailed defect taxonomy that is expensive to construct and difficult to validate. The Association for the Advancement of Medical Instrumentation is developing SW91, a defect taxonomy to be published as a standard for health software. This paper details three methods to validate SW91 for its comprehensiveness. The initial validations of SW91 were conducted via mapping vulnerabilities from the common weakness enumeration and a dataset from a medical device software development company in Ireland. Taxonomy‐based testing is another validation method proposed in this research, and its applicability was investigated using empirical data from a medical device software development company in Ireland. Finally, the paper details future plans to implement taxonomy‐based testing to improve software quality in medical device software and to validate SW91. This validation will focus on the efficiency, reliability, and ability to perform useful analyses and defect coverage of SW91.

A hybrid assessment approach for medical device software development companies

AbstractMedical device software development organizations are bound by regulatory requirements and constraints to ensure that developed medical devices will not harm patients. Medical devices have to be treated as complete systems and be evaluated in this manner. Instead of manufacturers having to ensure compliance to various regulatory standards individually, the authors previously developed a medical device software process assessment framework called MDevSPICE® that integrates the regulatory requirements from all the relevant medical device software standards. The MDevSPICE® was developed in a manner that suits plan‐driven software development. To improve the usability of MDevSPICE® in agile settings, we extended the assessment approach. The hybrid assessment approach described here combines the MDevSPICE®‐based process assessment method with steps for prioritization of improvement needs through value stream mapping and enabling process improvement through the use of KATA technique. This approach integrates agile methods into the medical device software development process while adhering to the requirements of the regulatory standards. This paper describes the implementation of the approach within 4 organizations that develop software in line with medical device regulations.

Mobile medical app development with a focus on traceability

AbstractToday, the growth of medical devices and mobile medical applications is increasing enormously, thanks to the efficiency and enhancement of new technology. When it comes to mobile medical apps, developers need to understand what is required when a mobile application fulfils the definition of a medical device. Such applications have to be developed in compliance with medical device regulations. This can be a challenge for mobile medical application developers, as medical device software is normally developed in a manner that will also ensure the production of regulatory documentation that is essential to market such devices. In this paper, we identify the need for a mobile medical application development framework, the key criteria for such a framework, and describe how the results were collected through performing a Medical Device Software Development workshop. Furthermore, we describe how MDevSPICE together with an agile software development approach can be tailored to support a mobile medical applications development framework. We detail one of the key criteria for mobile medical application development framework—traceability.

Approach to the development of a Unified Framework for Safety Critical Software Development

Software is increasingly being used to provide functionality in safety critical domains. The complexity involved in the development of software for these domains can bring challenges concerned with safety. International standards are published, providing information on practices which must be implemented in order to satisfy the regulations. This paper details an investigation of the relevant standards that companies need to implement in order to satisfy the regulatory requirements. A literature review was conducted which examines the relevant Quality Management System, Risk Management and Software Development standards across the safety critical domains; and examines the challenges faced by software development organizations with standard and multiple standard implementation. The existing approaches to standards consolidation, integration and harmonization were also examined. To investigate the challenges in implementing these standards, interviews were conducted with a medical device software development company having a Quality Management System in place and beginning to implement the relevant Software Development standards. In addition, an interview was conducted with a consultancy company who has experience in the implementation and maintenance of Quality Management Systems in small and medium enterprises. Following the literature review and interviews conducted, a comparison of the standards was conducted to investigate the similarities and differences in the structure of sections and subsections and to estimate the potential for the further consolidation of these standards. Following the results of the comparisons, a detailed mapping of standard requirements was conducted, mapping requirements of generic and domain specific Quality Management System standards. Future work will focus on the consolidation and integration of standards practices which need to be implemented by companies developing safety critical software and development of Unified Framework that incorporates all necessary requirements to comply with regulatory requirements.

Creation of an IEC 62304 compliant software development plan

AbstractOrganizations engaged in medical device software development are required to demonstrate compliance with a set of medical device standards and regulations before the device can be marketed. One such standard IEC 62304, Medical Device Software—Software Life Cycle Processes, defines the processes that are required in order to develop safe software. Demonstrating compliance with IEC 62304 can be problematic for organizations that are new to or have limited experience in the domain. The standard defines what processes must be carried out but does not state how. In a review of a number of such organizations, it was found that the development of a software development plan proved to be a difficult task. In this work we have created a software development plan template to assist organizations with this arduous task. The software development plan template will be validated with these organizations as part of the future work.

Development and benefits of MDevSPICE®, the medical device software process assessment framework

AbstractSoftware development companies moving into the medical device domain often find themselves overwhelmed by the number of regulatory requirements they need to satisfy before they can market their device. Several international standards and guidance documents have been developed to help companies on their road to regulatory compliance, but working their way through the various standards is a challenge in itself. In order to help software companies in the medical device domain, we have developed an integrated framework of medical device software development best practices called MDevSPICE®. This framework integrates generic software development best practices with medical device standards' requirements enabling consistent assessment of medical device processes. MDevSPICE® can be used by software companies evaluating their readiness for regulatory audits as well as by large medical device manufacturers for selecting suitable software suppliers.In this paper, we describe the development of the MDevSPICE® framework—its process reference model, process assessment model, assessment method and assessor training and certification scheme. We also illustrate the benefits and significance of the framework for the medical device‐manufacturing community as learned from the various MDevSPICE® assessments that we conducted to date. Copyright © 2016 John Wiley & Sons, Ltd.

Adopting Agile Practices when Developing Medical Device Software

Adopting Agile Practices when Developing Medical Device Software Agile methods are gaining momentum amongst the developers of non-safety critical software. They offer the ability to improve development time, increase quality and reduce development costs. Despite this, the rate of adoption of agile methods within safety critical domains remains low. On face value agile methods appear to be contradictory to regulatory requirements. However while they may appear contradictory, they align on key values such as the development of the highest quality software. To demonstrate that agile methods could in fact be adopted when developing regulatory compliant software they were implemented on a medical device software development project.

High-Confidence Medical Device Software Development

High-Confidence Medical Device Software Development

First experiences with the implementation of the European standard EN 62304 on medical device software for the quality assurance of a radiotherapy unit

BackgroundAccording to the latest amendment of the Medical Device Directive standalone software qualifies as a medical device when intended by the manufacturer to be used for medical purposes. In this context, the EN 62304 standard is applicable which defines the life-cycle requirements for the development and maintenance of medical device software. A pilot project was launched to acquire skills in implementing this standard in a hospital-based environment (in-house manufacture).MethodsThe EN 62304 standard outlines minimum requirements for each stage of the software life-cycle, defines the activities and tasks to be performed and scales documentation and testing according to its criticality. The required processes were established for the pre-existent decision-support software FlashDumpComparator (FDC) used during the quality assurance of treatment-relevant beam parameters. As the EN 62304 standard implicates compliance with the EN ISO 14971 standard on the application of risk management to medical devices, a risk analysis was carried out to identify potential hazards and reduce the associated risks to acceptable levels.ResultsThe EN 62304 standard is difficult to implement without proper tools, thus open-source software was selected and integrated into a dedicated development platform. The control measures yielded by the risk analysis were independently implemented and verified, and a script-based test automation was retrofitted to reduce the associated test effort. After all documents facilitating the traceability of the specified requirements to the corresponding tests and of the control measures to the proof of execution were generated, the FDC was released as an accessory to the HIT facility.ConclusionsThe implementation of the EN 62304 standard was time-consuming, and a learning curve had to be overcome during the first iterations of the associated processes, but many process descriptions and all software tools can be re-utilized in follow-up projects. It has been demonstrated that a standards-compliant development of small and medium-sized medical software can be carried out by a small team with limited resources in a clinical setting. This is of particular relevance as the upcoming revision of the Medical Device Directive is expected to harmonize and tighten the current legal requirements for all European in-house manufacturers.

Medical device standards' requirements for traceability during the software development lifecycle and implementation of a traceability assessment model

Developing safety critical software is a complex process. Due to the fact that medical device software failure can lead to catastrophic consequences, numerous standards have been developed which govern software development in the medical device domain. Risk management has an important role in medical device software development as it is important to ensure that safe software is developed. Demonstrating traceability of requirements right throughout the medical device software development and maintenance lifecycles is an important part of demonstrating that ‘safe’ software has been produced through adopting defined processes. Consequently, medical device standards and guidelines emphasise the need for traceability.This paper outlines the extent and diversity of traceability requirements within medical device standards and guidelines, and identifies the requirements for traceability through each phase of the software development lifecycle. The paper also summarises the findings obtained when a lightweight assessment method (Med-Trace), which we created, based upon the traceability practices within these standards, was implemented in two SME organisations. Finally we highlight how the findings indicate a lack of guidance as to what is required when implementing and maintaining a traceability process.

Human Factors and IT Medical Device Standards at AAMI

Human Factors and IT Medical Device Standards at AAMI

Software process improvement to assist medical device software development organisations to comply with the amendments to the medical device directive

A recent revision to the European Medical Device Directive (MDD) 2007/47/EC made 14 amendments to the original directive (93/42/EEC). A number of these changes directly affect the development of software for use in healthcare. The most significant change in relation to medical device software development is that stand-alone software is now seen as an active medical device and should be developed following state-of-the-art medical device software development processes. State-of-the-art medical device software processes are understood within the industry as developing software in accordance with IEC 62304 and standards that are aligned with it. This study identifies how changes to the MDD affect medical device software development companies and recommendations are made as to how medical device software development companies can conform to the latest regulatory requirements. Additionally, the study provides an overview of how Medi SPICE is currently being developed to provide organisations with a single point of reference for the practices that should be implemented in order to produce regulatory compliant medical device software.

A lightweight traceability assessment method for medical device software

SUMMARYTraceability is central to medical device software development and essential for regulatory approval. For compliance to be achieved, an effective traceability process needs to be in place. This process must ensure the need for clear linkages and traceability from software requirements – including risks – through the different stages of the software development and maintenance lifecycles. This is difficult to achieve because of the lack of specific guidance within the medical device standards and documentation. This has resulted in many medical device companies employing inefficient software traceability processes. In this paper, we outline the development and implementation of Med‐Trace, a lightweight software traceability process assessment and improvement method developed specifically for the medical device industry. We also present and discuss findings from two industry‐based Med‐Trace assessments. Copyright © 2011 John Wiley & Sons, Ltd.

Risk management capability model for the development of medical device software

Failure of medical device (MD) software can have potentially catastrophic effects, leading to injury of patients or even death. Therefore, regulators penalise MD manufacturers who do not demonstrate that sufficient attention is devoted to the areas of hazard analysis and risk management (RM) throughout the software lifecycle. This paper has two main objectives. The first objective is to compare how thorough current MD regulations are with relation to the Capability Maturity Model Integration (CMMI®) in specifying what RM practices MD companies should adopt when developing software. The second objective is to present a Risk Management Capability Model (RMCM) for the MD software industry, which is geared towards improving software quality, safety and reliability. Our analysis indicates that 42 RM sub-practices would have to be performed in order to satisfy MD regulations and that only an additional 8 sub-practices would be required in order to satisfy all the CMMI® level 1 requirements. Additionally, MD companies satisfying the CMMI® goals of the RM process area by performing the CMMI® RM practices will not meet the requirements of the MD software RM regulations as an additional 20 MD-specific sub-practices have to be added to meet the objectives of RMCM.

High-Confidence Medical Device Software and Systems

Given the shortage of caregivers and the increase in an aging US population, the future of US healthcare quality does not look promising and definitely is unlikely to be cheaper. Advances in health information systems and healthcare technology offer a tremendous opportunity for improving the quality of care while reducing costs. The development and production of medical device software and systems is a crucial issue, both for the US economy and for ensuring safe advances in healthcare delivery. As devices become increasingly smaller in physical terms but larger in software terms, the design, testing, and eventual Food and Drug Administration (FDA) device approval is becoming much more expensive for medical device manufacturers both in terms of time and cost. Furthermore, the number of devices that have recently been recalled due to software and hardware problems is increasing at an alarming rate. As medical devices are becoming increasingly networked, ensuring even the same level of health safety seems a challenge.