Learning classification models from multiple experts

Building classification models from clinical data using machine learning methods often relies on labeling of patient examples by human experts. Standard machine learning framework assumes the labels are assigned by a homogeneous process. However, in reality the labels may come from multiple experts and it may be difficult to obtain a set of class labels everybody agrees on; it is not uncommon that different experts have different subjective opinions on how a specific patient example should be classified. In this work we propose and study a new multi-expert learning framework that assumes the class labels are provided by multiple experts and that these experts may differ in their class label assessments. The framework explicitly models different sources of disagreements and lets us naturally combine labels from different human experts to obtain: (1) a consensus classification model representing the model the group of experts converge to, as well as, and (2) individual expert models. We test the proposed framework by building a model for the problem of detection of the Heparin Induced Thrombocytopenia (HIT) where examples are labeled by three experts. We show that our framework is superior to multiple baselines (including standard machine learning framework in which expert differences are ignored) and that our framework leads to both improved consensus and individual expert models.     

Impact of Guidelines for Antihypertensive Treatment on Clinical Practice

Many Guidelines and Consensus Statements were published in 1993 and 1994. The pressure to produce these guidelines comes from clinicians faced with rapid change, from a wish to provide an independent authoritative view rather than rely on commercial promotion of particular treatments, and from governments seeking assistance with the allocation of scarce resources.

Evaluation of the impact that guidelines exert on clinical practice is notoriously difficult, but has been attempted using the self-report questionnaire, or the more reliable but expensive analysis of actual practice data, before and after publication of the guidelines.     

Primary Prophylaxis of Invasive Fungal Diseases in Allogeneic Stem Cell Transplantation: Revised Recommendations from a Consensus Process by Gruppo Italiano Trapianto Midollo Osseo (GITMO)

This document updates and expands the recommendations on primary prophylaxis of invasive fungal diseases (IFD) in allogeneic hematopoietic stem cell transplantation (allo-HSCT) recipients, published in 2009 by the Gruppo Italiano Trapianto Midollo Osseo (GITMO). A consensus process was undertaken to describe and evaluate current information and practice regarding risk stratification and primary antifungal prophylaxis during the pre-engraftment and postengraftment phases after allo-HSCT. The revised recommendations were based on the evaluation of recent literature including a large, prospective, multicenter epidemiological study of allo-HSCT recipients conducted among the GITMO transplantation centers during the period of 2008 to 2010. It is intended as a guide for the identification of types and phases of transplantation at low, standard, and high risk for IFD, according to the underlying disease, transplantation, and post-transplantation factors. The risk stratification was the critical determinant of the primary antifungal approach for allo-HSCT recipients.     

Fracture-related infection: A consensus on definition from an international expert group

Fracture-related infection (FRI) is a common and serious complication in trauma surgery. Accurately estimating the impact of this complication has been hampered by the lack of a clear definition. The absence of a working definition of FRI renders existing studies difficult to evaluate or compare. In order to address this issue, an expert group comprised of a number of scientific and medical organizations has been convened, with the support of the AO Foundation, in order to develop a consensus definition.The process that led to this proposed definition started with a systematic literature review, which revealed that the majority of randomized controlled trials in fracture care do not use a standardized definition of FRI. In response to this conclusion, an international survey on the need for and key components of a definition of FRI was distributed amongst all registered AOTrauma users. Approximately 90% of the more than 2000 surgeons who responded suggested that a definition of FRI is required. As a final step, a consensus meeting was held with an expert panel. The outcome of this process led to a consensus definition of FRI.Two levels of certainty around diagnostic features were defined. Criteria could be confirmatory (infection definitely present) or suggestive. Four confirmatory criteria were defined: Fistula, sinus or wound breakdown; Purulent drainage from the wound or presence of pus during surgery; Phenotypically indistinguishable pathogens identified by culture from at least two separate deep tissue/implant specimens; Presence of microorganisms in deep tissue taken during an operative intervention, as confirmed by histopathological examination. Furthermore, a list of suggestive criteria was defined. These require further investigations in order to look for confirmatory criteria.In the current paper, an overview is provided of the proposed definition and a rationale for each component and decision. The intention of establishing this definition of FRI was to offer clinicians the opportunity to standardize clinical reports and improve the quality of published literature. It is important to note that the proposed definition was not designed to guide treatment of FRI and should be validated by prospective data collection in the future.     

Guidelines for time-to-event end-point definitions in trials for pancreatic cancer. Results of the DATECAN initiative (Definition for the Assessment of Time-to-event End-points in CANcer trials)

BackgroundUsing potential surrogate end-points for overall survival (OS) such as Disease-Free- (DFS) or Progression-Free Survival (PFS) is increasingly common in randomised controlled trials (RCTs). However, end-points are too often imprecisely defined which largely contributes to a lack of homogeneity across trials, hampering comparison between them. The aim of the DATECAN (Definition for the Assessment of Time-to-event End-points in CANcer trials)-Pancreas project is to provide guidelines for standardised definition of time-to-event end-points in RCTs for pancreatic cancer.MethodsTime-to-event end-points currently used were identified from a literature review of pancreatic RCT trials (2006–2009). Academic research groups were contacted for participation in order to select clinicians and methodologists to participate in the pilot and scoring groups (>30 experts). A consensus was built after 2 rounds of the modified Delphi formal consensus approach with the Rand scoring methodology (range: 1–9).ResultsFor pancreatic cancer, 14 time to event end-points and 25 distinct event types applied to two settings (detectable disease and/or no detectable disease) were considered relevant and included in the questionnaire sent to 52 selected experts. Thirty experts answered both scoring rounds. A total of 204 events distributed over the 14 end-points were scored. After the first round, consensus was reached for 25 items; after the second consensus was reached for 156 items; and after the face-to-face meeting for 203 items.ConclusionThe formal consensus approach reached the elaboration of guidelines for standardised definitions of time-to-event end-points allowing cross-comparison of RCTs in pancreatic cancer.     

脊柱结核并发HIV感染/AIDS患者诊断及治疗专家共识

脊柱结核并发HIV感染/AIDS患者因免疫功能低下,治疗的难度成倍增加。为规范脊柱结核并发HIV感染/AIDS患者的诊疗流程,使更多同行了解此类疾病治疗细节,并在治疗时有可靠依据,中国防痨协会骨关节结核专业分会、中国西部骨结核联盟、中国华北骨结核联盟、《中国防痨杂志》编辑委员会共同制定了《脊柱结核并发HIV感染/AIDS患者诊断及治疗专家共识》。本共识从脊柱结核并发HIV感染/AIDS患者的流行病学背景开始论述,对其常见临床表现、实验室检查、诊断标准、药物及手术治疗方法、手术治疗过程中的职业暴露和注意事项,以及研究方向等方面做了深入的阐述与讨论。     

阿达木单抗治疗强直性脊柱炎致播散性结核病一例并文献复习

目的 探讨应用阿达木单克隆抗体(简称“单抗”)治疗强直性脊柱炎致播散性结核病的临床特点、诊治要点和治疗转归。 方法 回顾性分析福建省福州肺科医院2019年6月10日收治的1例应用阿达木单抗治疗强直性脊柱炎致播散性结核病的临床资料、诊治经过及随访情况,并进行文献复习。以“adalimumab”和“disseminated tuberculosis”为检索词对PubMed数据库进行检索,以“阿达木单抗”和“播散性结核病”为检索词通过万方数据库和中国知网对中文文献进行检索,检索时间截止到2019年9月,经过筛选剔除,共获取相关文献34篇,其中中文文献0篇,英文文献34篇。删去重复的文献并剔除可能为阿达木单抗以外的肿瘤坏死因子α(TNF-α)致播散性结核病及TNF-α致其他播散性疾病的报道,共筛选出具备详细病例资料的文献8篇,共获得8例患者,结合本研究收集的患者,对其临床特征、诊断和治疗情况进行分析。 结果 本例患者为男性,28岁。因“强直性脊柱炎”接受阿达木单抗治疗,治疗2个月后出现咳嗽、气促、腹胀、发热,入院后经胸部CT、胸膜活检及支气管镜等检查,诊断为“播散性结核病(双肺、右侧支气管、胸腔、腹腔、心包、纵隔淋巴结、锁骨上淋巴结、腹腔淋巴结、盆腔淋巴结、脾)”。给予“3H-R-Z-E/9H-R-E”方案治疗,辅以异烟肼支气管局部雾化吸入,行抗结核药物治疗后症状改善。治疗第5个月,CT复查提示“肺部病变减少,纵隔内部分淋巴结肿大较前缩小,增厚的支气管管壁较前变薄,管腔较前通畅,胸、腹腔积液明显吸收。截止到2019年12月,患者仍处于规则的抗结核药物治疗中。文献检索后获得8例患者,加上本例,共9例患者。其中,男3例,女6例;年龄9~75岁,平均年龄(50.44±25.19)岁。9例患者中,5例开始使用阿达木单抗治疗之前的结核病筛查试验结果为阴性,1例既往有抗结核治疗史,1例曾进行过预防性抗结核治疗,3例有与结核病患者的密切接触史。诊断明确行抗结核药物治疗后,5例患者转归良好。3例转归差,其中1例病情持续进展,并发消化道出血;1例颅内病灶持续进展;1例出现急性呼吸窘迫综合征,最终死亡。1例转归不明。 结论 阿达木单抗可致播散性结核病,准备接受阿达木单抗治疗的患者均应在用药前进行结核病筛查,治疗过程中应该警惕潜伏性结核感染转为活动性结核病及新发结核感染,停用阿达木单抗和及时行抗结核药物治疗是预后良好的关键。     

Management of Lung Nodules and Lung Cancer Screening During the COVID-19 Pandemic: CHEST Expert Panel Report

BackgroundThe risks from potential exposure to coronavirus disease 2019 (COVID-19), and resource reallocation that has occurred to combat the pandemic, have altered the balance of benefits and harms that informed current (pre-COVID-19) guideline recommendations for lung cancer screening and lung nodule evaluation. Consensus statements were developed to guide clinicians managing lung cancer screening programs and patients with lung nodules during the COVID-19 pandemic.MethodsAn expert panel of 24 members, including pulmonologists (n = 17), thoracic radiologists (n = 5), and thoracic surgeons (n = 2), was formed. The panel was provided with an overview of current evidence, summarized by recent guidelines related to lung cancer screening and lung nodule evaluation. The panel was convened by video teleconference to discuss and then vote on statements related to 12 common clinical scenarios. A predefined threshold of 70% of panel members voting agree or strongly agree was used to determine if there was a consensus for each statement. Items that may influence decisions were listed as notes to be considered for each scenario.ResultsTwelve statements related to baseline and annual lung cancer screening (n = 2), surveillance of a previously detected lung nodule (n = 5), evaluation of intermediate and high-risk lung nodules (n = 4), and management of clinical stage I non–small-cell lung cancer (n = 1) were developed and modified. All 12 statements were confirmed as consensus statements according to the voting results. The consensus statements provide guidance about situations in which it was believed to be appropriate to delay screening, defer surveillance imaging of lung nodules, and minimize nonurgent interventions during the evaluation of lung nodules and stage I non–small-cell lung cancer.ConclusionsThere was consensus that during the COVID-19 pandemic, it is appropriate to defer enrollment in lung cancer screening and modify the evaluation of lung nodules due to the added risks from potential exposure and the need for resource reallocation. There are multiple local, regional, and patient-related factors that should be considered when applying these statements to individual patient care.