Toward a molecular classification of cancer

The diagnosis of cancer is typically made on the basis of clinical and histological criteria. However, molecular biology research over the past three decades has revealed that diagnoses based on clinical presentation and pathology evaluation are not always accurate. With the advent of molecularly targeted drugs, a reclassification of cancers, based on their underlying genetic defects, is becoming increasingly urgent.     

Early prediction of lung cancer based on the combination of trace element analysis in urine and an Adaboost algorithm

Early detection of cancer is the key to effective treatment and long-term survival. Lung cancer is one of the most frequently occurring cancers and its early detection is particularly of interest. This work investigates the feasibility of a combination of Adaboost (ensemble from machining learning) using decision stumps as weak classifier and trace element analysis for predicting early lung cancer. A dataset involving the determination of 9 trace elements of 122 urine samples is used for illustration. Kennard and Stone (KS) algorithm coupled with an alternate re-sampling was used to realize sample set partitioning. The whole dataset was split into equally sized training and test set, which were then reversed to yield a second operating case, we called them case A and case B, respectively. The prediction results based on the Adaboost were compared with those from Fisher discriminant analysis (FDA). On the test set, the final Adaboost classifiers achieved a sensitivity of 100% for both cases, a specificity of 93.8%, 95.7%, and an overall accuracy of 95.1%, 96.7%, for case A and case B, respectively. In either case, Adaboost always achieves better performance than FDA; also, it is less sensitive to the composition of the training set compared to FDA and easy to control over-fitting. It seems that Adaboost is superior to FDA in the present task, indicating that integrating Adaboost and trace element analysis of urine can serve as a useful tool for diagnosing early lung cancer in clinical practice.     

Using deep learning and electronic health records to detect Noonan syndrome in pediatric patients

PurposeThe variable expressivity and multisystem features of Noonan syndrome (NS) make it difficult for patients to obtain a timely diagnosis. Genetic testing can confirm a diagnosis, but underdiagnosis is prevalent owing to a lack of recognition and referral for testing. Our study investigated the utility of using electronic health records (EHRs) to identify patients at high risk of NS.MethodsUsing diagnosis texts extracted from Cincinnati Children’s Hospital’s EHR database, we constructed deep learning models from 162 NS cases and 16,200 putative controls. Performance was evaluated on 2 independent test sets, one containing patients with NS who were previously diagnosed and the other containing patients with undiagnosed NS.ResultsOur novel method performed significantly better than the previous method, with the convolutional neural network model achieving the highest area under the precision-recall curve in both test sets (diagnosed: 0.43, undiagnosed: 0.16).ConclusionThe results suggested the validity of using text-based deep learning methods to analyze EHR and showed the value of this approach as a potential tool to identify patients with features of rare diseases. Given the paucity of medical geneticists, this has the potential to reduce disease underdiagnosis by prioritizing patients who will benefit most from a genetics referral.     

疫情防控常态化背景下"互联网+"虚拟仿真教学在诊断学实训教学中的价值

目的探讨疫情防控常态化背景下"互联网+"虚拟仿真教学模式在诊断学实训教学中的应用价值。 方法选取甘肃中医药大学中医学本科2018级90名学生(对照组)和2019级88名学生(实验组)，实验组采用线上线下相结合混合式教学方法，对照组采用线下传统实训教学模式，比较两组诊断学成绩及满意度问卷调查结果。 结果实验组学生平时成绩[(89.53±7.58)分]和总评成绩[(78.72±9.01)分]均高于对照组平时成绩和总评成绩[(75.25±7.83)分，(65.71±8.87)分]，均差异有统计学意义(t＝－12.36，－9.71 ；均P<0.05)。实验组学生的期末理论成绩[(86.56±7.58)分]和期末实训技能成绩[(83.79±7.77)分]均高于对照组[(73.33±8.95)分，(69.45±7.93)分]，均差异有统计学意义(t＝－10.63，－12.18；均P<0.05)。问卷调查方面评分显示，实验组教学模式比对照组教学模式能够有效激发学习兴趣(89.77%，72.22%)、丰富教学渠道(93.18%，83.33%)、促进反复实践能力(89.77%，70.00%)、提升综合思维能力和临床诊疗思维能力(95.45%，73.33%)(χ²＝8.86，4.15，10.78，16.43，均P<0.05)。 结论疫情防控常态化背景下"互联网+"虚拟仿真教学的应用，可弥补疫情防控常态化背景下医学信息化教学存在的软硬件短板，丰富教学内容，提高学生动手操作能力，对于实践性很强的诊断学来说具有非常重要的意义。     

螺旋CT仿真内窥镜对儿童气道非金属异物的诊断价值

目的：评价螺旋CT仿真内窥镜对儿童气道异物的诊断价值及急诊处理的意义。方法：40例气管支气管非金属异物患者均进行了螺旋CT及仿真内窥镜检查,并经纤维支气管镜取出。其方法：将螺旋CT容积扫描的图像数据传输到独立工作站,利用仿真内窥镜的软件功能重建为三维支气管图像。通过鼠标和键盘的操作使光标进入气管腔进而进入支气管腔内。结果：40例患者中,气管异物8例,右主支气管异物23例,左主支气管异物9例。仿真内窥镜表现为气道内结节者24例,支气管阻塞12例,假阴性4例。结论：CT仿真支气管内窥镜是一种完全无创的诊断方法;可以直观地显示异物的部位、大小、形态、数量及与支气管黏膜的关系,为纤支镜取出异物提供依据和更多的信息;可用于患者的复查,避免反复纤支镜检查给患者带来更多的痛苦。     

The development,evaluation and performance of molecular diagnostics for detection of Mycobacterium tuberculosis

The unique pathogenesis of tuberculosis (TB) poses several barriers to the development of accurate diagnostics: a) the establishment of life-long latency by Mycobacterium tuberculosis (M.tb) after primary infection confounds the development of classical antibody or antigen based assays; b) our poor understanding of the molecular pathways that influence progression from latent to active disease; c) the intracellular nature of M.tb infection in tissues means that M.tb and/or its components, are not readily detectable in peripheral specimens; and d) the variable presence of M.tb bacilli in specimens from patients with extrapulmonary TB or children. The literature on the current portfolio of molecular diagnostics tests for TB is reviewed here and the developmental pipeline is summarized. Also reviewed are data from recently published operational research on the GeneXpert MTB/RIF assay and discussed are the lessons that can be taken forward for the design of studies to evaluate the impact of TB diagnostics.     

Induction of pluripotent stem cells from autopsy donor-derived somatic cells

Human induced pluripotent stem cells (iPSCs) have become an intriguing approach for neurological disease modeling, because neural lineage-specific cell types that retain the donors’ complex genetics can be established in vitro. The statistical power of these iPSC-based models, however, is dependent on accurate diagnoses of the somatic cell donors; unfortunately, many neurodegenerative diseases are commonly misdiagnosed in live human subjects. Postmortem histopathological examination of a donor's brain, combined with premortem clinical criteria, is often the most robust approach to correctly classify an individual as a disease-specific case or unaffected control. In this study, we describe iPSCs generated from a skin biopsy collected postmortem during the rapid autopsy of a 75-year-old male, whole body donor, defined as an unaffected neurological control by both clinical and histopathological criteria. These iPSCs were established in a feeder-free system by lentiviral transduction of the Yamanaka factors, Oct3/4, Sox2, Klf4, and c-Myc. Selected iPSC clones expressed both nuclear and surface antigens recognized as pluripotency markers of human embryonic stem cells (hESCs) and were able to differentiate in vitro into neurons and glia. Statistical analysis also demonstrated that fibroblast proliferation was significantly affected by biopsy site, but not donor age (within an elderly cohort). These results provide evidence that autopsy donor-derived fibroblasts can be successfully reprogrammed into iPSCs, and may provide an advantageous approach for generating iPSC-based neurological disease models.     

Comprehensive seroprofiling of sixteen B. burgdorferi OspC: Implications for Lyme disease diagnostics design

Early diagnosis of Lyme disease (LD) is critical to successful treatment. However, current serodiagnostic tests do not reliably detect antibodies during early infection. OspC induces a potent early immune response and is also one of the most diverse proteins in the Borrelia proteome. Yet, at least 70% of the amino acid sequence is conserved among all 21 known OspC types. We performed a series of comprehensive seroprofiling studies to select the OspC types that have the most cross-reactive immunodominant epitopes. We found that proteins belonging to seven OspC types detect antibodies from all three infected host species regardless of the OspC genotype of the infecting strain. Although no one OspC type identifies all seropositive human samples, combinations of as few as two OspC proteins identified all patients that had anti-OspC antibodies.