Computer-interpretable guidelines: electronic tools to enhance the utility of thyroid nodule clinical practice guidelines and risk stratification tools.

Clinicians seeking guidance for evaluating and managing thyroid nodules currently have several resources. The principal ones are narrative clinical guidelines and clinical risk calculators. This paper will review the strengths and weaknesses of both. The paper will introduce a concept of computer interpretable guideline, a novel way of transforming narrative guidelines in to a clinical decision support tool that can provide patient specific recommendations at the point of care. The paper then describes an experience of developing an interactive web based computer interpretable guideline for thyroid nodule management, called Thyroid Nodule Management App (TNAPP). The advantages of this approach and the potential barriers for widespread adaptation are discussed.

American Association of Clinical Endocrinology And Associazione Medici Endocrinologi Thyroid Nodule Algorithmic Tool.

OBJECTIVE: The first edition of the American Association of Clinical Endocrinology/American College of Endocrinology/Associazione Medici Endocrinologi Guidelines for the Diagnosis and Management of Thyroid Nodules was published in 2006 and updated in 2010 and 2016. The American Association of Clinical Endocrinology/American College of Endocrinology/Associazione Medici Endocrinologi multidisciplinary thyroid nodules task force was charged with developing a novel interactive electronic algorithmic tool to evaluate thyroid nodules. METHODS: The Thyroid Nodule App (termed TNAPP) was based on the updated 2016 clinical practice guideline recommendations while incorporating recent scientific evidence and avoiding unnecessary diagnostic procedures and surgical overtreatment. This manuscript describes the algorithmic tool development, its data requirements, and its basis for decision making. It provides links to the web-based algorithmic tool and a tutorial. RESULTS: TNAPP and TI-RADS were cross-checked on 95 thyroid nodules with histology-proven diagnoses. CONCLUSION: TNAPP is a novel interactive web-based tool that uses clinical, imaging, cytologic, and molecular marker data to guide clinical decision making to evaluate and manage thyroid nodules. It may be used as a heuristic tool for evaluating and managing patients with thyroid nodules. It can be adapted to create registries for solo practices, large multispecialty delivery systems, regional and national databases, and research consortiums. Prospective studies are underway to validate TNAPP to determine how it compares with other ultrasound-based classification systems and whether it can improve the care of patients with clinically significant thyroid nodules while reducing the substantial burden incurred by those who do not benefit from further evaluation and treatment.

American Association of Clinical Endocrinology And Associazione Medici Endocrinologi Thyroid Nodule Algorithmic Tool.

OBJECTIVE: The first edition of the American Association of Clinical Endocrinology/American College of Endocrinology/Associazione Medici Endocrinologi Guidelines for the Diagnosis and Management of Thyroid Nodules was published in 2006 and updated in 2010 and 2016. The American Association of Clinical Endocrinology/American College of Endocrinology/Associazione Medici Endocrinologi multidisciplinary thyroid nodules task force was charged with developing a novel interactive electronic algorithmic tool to evaluate thyroid nodules. METHODS: The Thyroid Nodule App (termed TNAPP) was based on the updated 2016 clinical practice guideline recommendations while incorporating recent scientific evidence and avoiding unnecessary diagnostic procedures and surgical overtreatment. This manuscript describes the algorithmic tool development, its data requirements, and its basis for decision making. It provides links to the web-based algorithmic tool and a tutorial. RESULTS: TNAPP and TI-RADS were cross-checked on 95 thyroid nodules with histology-proven diagnoses. CONCLUSION: TNAPP is a novel interactive web-based tool that uses clinical, imaging, cytologic, and molecular marker data to guide clinical decision making to evaluate and manage thyroid nodules. It may be used as a heuristic tool for evaluating and managing patients with thyroid nodules. It can be adapted to create registries for solo practices, large multispecialty delivery systems, regional and national databases, and research consortiums. Prospective studies are underway to validate TNAPP to determine how it compares with other ultrasound-based classification systems and whether it can improve the care of patients with clinically significant thyroid nodules while reducing the substantial burden incurred by those who do not benefit from further evaluation and treatment.

Letrozole-induced necrotising leukocytoclastic small vessel vasculitis: First report of a case in the UK.

INTRODUCTION: Letrozole, an aromatase inhibitor, is a commonly used neo-adjuvant drug to treat hormone-sensitive breast cancer. There have been a few cases of aromatase inhibitor induced vasculitis but the first case of letrozole-induced vasculitis was reported from Switzerland in 2014 (Digklia et al.) [1]. PRESENTATION OF CASE: We report the case of a 72-year-old woman with a small breast cancer. She was started on pre-operative letrozole (2.5mg/d) whilst awaiting surgery. Ten days later she presented with burning pain and purpuric skin lesions which progressed to extensive ischaemic superficial necrosis of the lower limb skin, resolving over 3-4 months after local and systemic steroids. Histologically, it showed leucocytoclasis with evidence of eosinophilia consistent with a diagnosis of cutaneous leukocytoclastic small vessel vasculitis. DISCUSSION: The initial clinical presentation was severe burning pain around the ankles and a spreading violaceous rash. Letrozole was stopped. Wide local excision (lumpectomy) and sentinel node biopsy were postponed because of the accompanying pneumonitis and gastrointestinal upset, and were carried out 3.5 months later. Fortunately, the tumour size did not increase, but appeared to reduce, and axillary lymph nodes remained negative, i.e., this patient's cancer outcome does not seem to have been jeopardized. CONCLUSION: Leukocytoclastic vasculitis is a hypersensitivity reaction that is usually self-resolving, though our case needed systemic steroid treatment. Letrozole is a commonly used drug in clinical practice and prescribers should be aware of this rare side effect, which in our case delayed treatment without any apparent harm and possibly reduced tumour size.

A Computer-Interpretable Version of the AACE, AME, ETA Medical Guidelines for Clinical Practice for the Diagnosis and Management of Thyroid Nodules.

OBJECTIVE: Clinical practice guidelines (CPGs) could have a more consistent and meaningful impact on clinician behavior if they were delivered as electronic algorithms that provide patient-specific advice during patient-physician encounters. We developed a computer-interpretable algorithm for U.S. and European users for the purpose of diagnosis and management of thyroid nodules that is based on the "AACE, AME, ETA Medical Guidelines for Clinical Practice for the Diagnosis and Management of Thyroid Nodules," a narrative, evidence-based CPG. METHODS: We initially employed the guideline-modeling language GuideLine Interchange Format, version 3, known as GLIF3, which emphasizes the organization of a care algorithm into a flowchart. The flowchart specified the sequence of tasks required to evaluate a patient with a thyroid nodule. PROforma, a second guideline-modeling language, was then employed to work with data that are not necessarily obtained in a rigid flowchart sequence. Tallis-a user-friendly web-based "enactment tool"- was then used as the "execution engine" (computer program). This tool records and displays tasks that are done and prompts users to perform the next indicated steps. The development process was iteratively performed by clinical experts and knowledge engineers. RESULTS: We developed an interactive web-based electronic algorithm that is based on a narrative CPG. This algorithm can be used in a variety of regions, countries, and resource-specific settings. CONCLUSION: Electronic guidelines provide patient-specific decision support that could standardize care and potentially improve the quality of care. The "demonstrator" electronic thyroid nodule guideline that we describe in this report is available at http://demos.deontics.com/trace-review-app (username: reviewer; password: tnodule1). The demonstrator must be more extensively "trialed" before it is recommended for routine use.

Using computerised decision support to improve compliance of cancer multidisciplinary meetings with evidence-based guidance.

OBJECTIVES: The cancer multidisciplinary team (MDT) meeting (MDM) is regarded as the best platform to reduce unwarranted variation in cancer care through evidence-compliant management. However, MDMs are often overburdened with many different agendas and hence struggle to achieve their full potential. The authors developed an interactive clinical decision support system called MATE (Multidisciplinary meeting Assistant and Treatment sElector) to facilitate explicit evidence-based decision making in the breast MDMs. DESIGN: Audit study and a questionnaire survey. SETTING: Breast multidisciplinary unit in a large secondary care teaching hospital. PARTICIPANTS: All members of the breast MDT at the Royal Free Hospital, London, were consulted during the process of MATE development and implementation. The emphasis was on acknowledging the clinical needs and practical constraints of the MDT and fitting the system around the team's workflow rather than the other way around. Delegates, who attended MATE workshop at the England Cancer Networks' Development Programme conference in March 2010, participated in the questionnaire survey. OUTCOME MEASURES: The measures included evidence-compliant care, measured by adherence to clinical practice guidelines, and promoting research, measured by the patient identification rate for ongoing clinical trials. RESULTS: MATE identified 61% more patients who were potentially eligible for recruitment into clinical trials than the MDT, and MATE recommendations demonstrated better concordance with clinical practice guideline than MDT recommendations (97% of MATE vs 93.2% of MDT; N=984). MATE is in routine use in breast MDMs at the Royal Free Hospital, London, and wider evaluations are being considered. CONCLUSIONS: Sophisticated decision support systems can enhance the conduct of MDMs in a way that is acceptable to and valued by the clinical team. Further rigorous evaluations are required to examine cost-effectiveness and measure the impact on patient outcomes. The decision support technology used in MATE is generic and if found useful can be applied across medicine.

Cancer multidisciplinary team meetings: evidence, challenges, and the role of clinical decision support technology.

Multidisciplinary team (MDT) model in cancer care was introduced and endorsed to ensure that care delivery is consistent with the best available evidence. Over the last few years, regular MDT meetings have become a standard practice in oncology and gained the status of the key decision-making forum for patient management. Despite the fact that cancer MDT meetings are well accepted by clinicians, concerns are raised over the paucity of good-quality evidence on their overall impact. There are also concerns over lack of the appropriate support for this important but overburdened decision-making platform. The growing acceptance by clinical community of the health information technology in recent years has created new opportunities and possibilities of using advanced clinical decision support (CDS) systems to realise full potential of cancer MDT meetings. In this paper, we present targeted summary of the available evidence on the impact of cancer MDT meetings, discuss the reported challenges, and explore the role that a CDS technology could play in addressing some of these challenges.

From guidelines to careflows: modelling and supporting complex clinical processes.

Research on computer interpretable clinical guidelines has largely focused on individual points of care rather than processes of care. Whether we consider simple aids like clinical alerts and reminders or more sophisticated data interpretation and decision-making, guideline developers tend to focus on specific tasks rather than processes like care plans and pathways which are extended in time. In contrast, research on business process modelling has demonstrated notations and tools which deal directly with process modelling, but has not been concerned with problems like data interpretation and decision making. In this chapter we describe these two traditions, and compare some of their strengths and weaknesses. We also briefly discuss the distinct theoretical frameworks which have grown up around them, notably Petri nets for workflow modelling and mathematical logics for guidelines. We conclude that these offer complementary views of clinical processes and that a key research challenge is find a way of unifying them.

Clinical guidelines and care pathways: a case study applying PROforma decision support technology to the breast cancer care pathway.

PROforma is a formal language for modeling clinical processes that was developed by the Advanced Computation Laboratory of Cancer Research UK in 1996, together with associated tools, for creating decision support, care planning, clinical workflow management and other applications. The technology has been used to develop and evaluate a number of decision support applications in range of clinical settings. Clinical trials have been carried out and published for seven of these applications, all suggesting major positive benefits on a variety of outcome measures. The most recent and ongoing project called CREDO is an ambitious attempt to address the challenges in deploying sophisticated decision support systems in the intricate and convoluted management of chronic diseases, taking breast cancer as an example. In this chapter we describe the implementation of evidence based clinical guidelines within a complex care-pathway for patients with breast symptoms and analyse in detail the results of an evaluation study. Some important lessons learned during the process are shared and future directions are discussed.

Decision support for health care: the PROforma evidence base.

Cancer Research UK has developed PROforma, a formal language for modelling clinical processes, along with associated tools for creating decision support, care planning, clinical workflow management and other applications. The PROforma method has been evaluated in a variety of settings: in primary health care (prescribing, referral of suspected cancer patients, genetic risk assessment) and in specialist care of patients with breast cancer, leukaemia, HIV infection and other conditions. About nine years of experience have been gained with PROforma technologies. Seven trials of decision support applications have been published or are in preparation. Each of these has shown significant positive effects on a variety of measures of quality and/or outcomes of care. This paper reviews the evidence base for the clinical effectiveness of these PROforma applications, and previews the CREDO project -- a multi-centre trial of a complex PROforma application for supporting integrated breast cancer care across primary and secondary care settings.

An ontological approach to modelling tasks and goals.

Current approaches to modelling plans and processes in AI are limited by current understanding of "goals" and "intentions". We discuss this question in a medical context, viewing goals as clinical objectives and plans and processes as collections of tasks to achieve those objectives. The specific context for this discussion is the CREDO project, which aims to develop a comprehensive approach to supporting complex treatment plans and care pathways and provides an opportunity to carry out an extensive investigation of the key problem of formalising goals in medical informatics and AI generally. A review of 222 clinical services required in the management of breast cancer has yielded a systematic classification of tasks involved in breast cancer care and a similar classification of the clinical goals associated with these tasks. A six-component model of goal structure is proposed based on these ontological analyses. Although the model has been derived from a corpus of examples from medicine many of the issues encountered, and the solution proposed, appear to be relevant to other domains.