Machine learning models for Parkinson’s disease detection and stage classification based on spatial-temporal gait parameters

BackgroundParkinson’s disease (PD) is a chronic and progressive neurodegenerative disease with no cure, presenting a challenging diagnosis and management. However, despite a significant number of criteria and guidelines have been proposed to improve the diagnosis of PD and to determine the PD stage, the gold standard for diagnosis and symptoms monitoring of PD is still mainly based on clinical evaluation, which includes several subjective factors. The use of machine learning (ML) algorithms in spatial-temporal gait parameters is an interesting advance with easy interpretation and objective factors that may assist in PD diagnostic and follow up.Research questionThis article studies ML algorithms for: i) distinguish people with PD vs. matched-healthy individuals; and ii) to discriminate PD stages, based on selected spatial-temporal parameters, including variability and asymmetry.MethodsGait data acquired from 63 people with PD with different levels of PD motor symptoms severity, and 63 matched-control group individuals, during self-selected walking speed, was study in the experiments.ResultsIn the PD diagnosis, a classification accuracy of 84.6 %, with a precision of 0.923 and a recall of 0.800, was achieved by the Naïve Bayes algorithm. We found four significant gait features in PD diagnosis: step length, velocity and width, and step width variability. As to the PD stage identification, the Random Forest outperformed the other studied ML algorithms, by reaching an Area Under the ROC curve of 0.786. We found two relevant gait features in identifying the PD stage: stride width variability and step double support time variability.SignificanceThe results showed that the studied ML algorithms have potential both to PD diagnosis and stage identification by analysing gait parameters.     

Analysis of Progression Patterns and Failure Sites of Patients With Metastatic Lung Adenocarcinoma With EGFR Mutations Receiving First-line Treatment of Tyrosine Kinase Inhibitors

BackgroundReliable prediction of progression patterns and failure sites for patients with stage IV lung adenocarcinoma is valuable for physicians to deliver personalized tyrosine kinase inhibitor (TKI) treatment.Patients and MethodsWe retrospectively enrolled 266 patients who had stage IV lung adenocarcinoma and received first-line TKI treatment from 2013 to 2017 in Shanghai Chest Hospital. The clinical characteristics at initial diagnosis, progression patterns, and failure sites were analyzed with the attempt to identify some predictive factors for progression patterns and failure sites.ResultsAmong all patients, 62.4% developed systemic progression, and 37.6% developed oligoprogression. Both cohorts had a median progression-free survival (PFS) of 9 months. The percentage of patients who developed original and distant failure was 39.1% and 60.9%, respectively. Patients with oligometastasis at initial diagnosis were more prone to develop oligoprogression (odds ratio [OR], 4.370; 95% confidence interval [CI], 1.881-10.151; P = .001), whereas pulmonary metastasis was negatively correlated with oligoprogression (OR, 0.567; 95% CI, 0.330-0.974; P = .04). Both oligometastasis diagnosis (OR, 2.959; 95% CI, 1.347-6.500; P = .007) and the maximum diameter of the primary lung lesion (threshold 3.25 cm: OR, 3.646; 95% CI, 2.041-6.515; P = .0001) were strong predictive factors for original failures. Osseous metastasis at initial diagnosis might be an indication for distant failure (OR, 0.536; 95% CI, 0.316-0.909; P = .021).ConclusionOver one-half of patients with stage IV lung adenocarcinoma receiving first-line TKI treatment developed systemic progression and distant failure. Metastasis patterns at initial diagnosis was the most important predictive factor for progression patterns and failure sites. The maximum diameter of the primary lung lesion and evidence of osseous metastasis were also found to be significant indicative factors for failure sites.     

miR-122 Inhibits Hepatocarcinoma Cell Progression by Targeting LMNB2

In the present study, we investigated the role of miR-122 in hepatocarcinoma progression and explored the mechanism. In hepatocarcinoma tissues and cells, we used qRT-PCR to validate the miR-122 expression level. Next, we used colony formation by crystal violet staining assay to compare cell proliferation ability, and we used scratch test or Transwell assay to compare cell migration or invasion ability. We then conducted bioinformatics or luciferase reporter gene assay to prove the regulation effect of miR-122 on lamin B2 (LMNB2), and the biological function of LMNB2 was analyzed. We used nude mouse tumorigenicity assay to test the inhibition effect of miR-122 ASO therapy against hepatocarcinoma. miR-122 was reduced in hepatocarcinoma tissues compared to the paracarcinoma tissues, which was relatively low or high in hepatocarcinoma cell line SMMC7721 or Hep3B, and overexpressed miR-122 inhibited proliferation, migration, and invasion in hepatocarcinoma cells. Additionally, some reports showed that LMNB2 was regulated by miR-122, which inhibited the expression of LMNB2. Moreover, LMNB2 functioned to promote cell proliferation, migration, and invasion. We could achieve the inhibition of hepatocarcinoma using miR-122 therapy through decreasing LMNB2 expression in vivo. Our data indicated that miR-122 could inhibit hepatocellular carcinoma cell progression by targeting LMNB2 and as a therapeutic target for hepatocarcinoma treatment.     

Focal segmental glomerulosclerosis

Over the last 2 decades, we have learnt that focal segmental glomerulosclerosis (FSGS) is a ubiquitous phenomenon underlying the progressive deterioration of many different types of renal diseases in both pediatric and adult populations. FSGS may also be the primary renal lesion, whether in new disease entities such as glycogen storage disease and human immunodeficiency virus infection, or in idiopathic FSGS. Although the mechanism which triggers the development of primary FSGS still remains unknown, laboratory and clinical studies have identified several key pathophysiological events leading to end-stage renal disease. While therapeutic modalities have not changed remarkably, a recent study, although uncontrolled, demonstrated an impressive efficacy of intravenous steroid pulse therapy in inducing remission. Nevertheless, it remains largely unknown whether such a forced remission decreases the overall risk of developing chronic renal failure. Studies have revealed an important pathophysiological role of angiotensin and the therapeutic efficacy of angiotensin converting enzyme inhibitors in progressive loss of renal function in diseases where glomerulosclerosis is secondary; however, it remains to be verified whether these results hold true in primary FSGS. As a result of the improvement in allograft survival rate, the benefit of renal transplant outweighs the risk of recurrence of FSGS, hence transplantation continues to be a vital therapy for FSGS patients who have reached renal failure. Thus, FSGS is not one disease, but rather a range of lesions seen in many settings. The type of lesions and the patient's unique genetic factors contribute to prognosis, and also may dictate choice of optimum therapy.     

Progression of amiodarone induced cataracts

Amiodarone hydrochloride is a potent antiarrhythmic agent recently approved for use by the Food and Drug Administration. Anterior subcapsular lens opacities were observed in seven of fourteen patients treated with moderate to high doses of amiodarone at the Veterans Administration Medical Center in San Francisco in 1982. The present report summarizes the present status of these same fourteen patients ten years later. Anterior subcapsular lens opacities developed or progressed in all patients continuing treatment with this antiarrhythmic agent during the following ten year interval. Although Snellen visual acuities are not decreased, subtle visual impairment is present as measured by contrast sensitivity measurements with and without glare. This decrease in visual acuity is not a contraindication for therapy with this potentially life saving drug.     

Do NSAIDs affect the progression of osteoarthritis?

NSAIDs are widely used to alleviate the symptoms of OA. It remains controversial as to what effects these agents have on the progression of OA. In vitro studies showed several types of NSAIDs (e.g., sodium salicylate, indomethacin) inhibited the synthesis of cartilage matrix component, but some types of NSAIDs (e.g., aceclofenac, meloxicam, nimesulide) increased the matrix component synthesis and protected the chondrocytes against apoptosis, while others (e.g., piroxicam) had no effects. Studies in animal models verified that NSAIDs had favourable or detrimental action on OA progression, even the same NSAID (e.g., naproxen, tiaprofenic acid) had reverse effects on articular cartilage in different studies. Preliminary clinical trials revealed some NSAIDs such as indomethacin had a negative influence on joint structure, other NSAIDs such as diclofenac and naproxen had no acceleration of radiographic damage to OA within 2-years of treatment. So far, there are no convincing data to show the widely used NSAIDs and recommended selective COX-2 inhibitor have favourable effects on cartilage. Therefore, it is necessary and valuable to clarify the effects of these NSAIDs on cartilage in patients with OA using validated non-invasive methods such as MRI.     

Altered chromatin landscape in circulating T follicular helper and regulatory cells following grass pollen subcutaneous and sublingual immunotherapy

1. Download : Download high-res image (285KB)
2. Download : Download full-size image

     

Lack of PTEN expression in endometrial intraepithelial neoplasia is correlated with cancer progression

We tested the hypothesis that PTEN inactivation may stratify cancer progression risk among putative endometrial hyperplasias, classified prognostically by means of the morphometric D score (DS). The DS, calculated from 3 morphometric variables measured in routine hematoxylin-eosin-stained endometrial biopsy slides, is the most sensitive and specific method of endometrial cancer risk prediction currently available. Clinical outcomes of 103 women with endometrial hyperplasia on biopsy were tallied according to the DS. Seven (7/103; 7%) patients with carcinoma during follow-up were all distributed within the high-risk prognostic group (ie, DS <1 = endometrial intraepithelial neoplasia [EIN]) (7/21; 33% progression). None of the 82 cases with a DS higher than 1 progressed. All cases that progressed were PTEN null, indicating that this genotype is capable of further stratifying cancer progression risk in hyperplasias irrespective of histological categorization. However, only 16% of the PTEN-null cases progressed. When PTEN expression pattern was combined with EIN, the prognostic power was greatly increased (specificity from 63% for PTEN and 85% for EIN to 93% when combined; positive predictive value from 16% and 33% to 50%). We conclude that loss of PTEN expression is the first biomarker in EIN that increases the accuracy of the prognostic DS to predict cancer progression risk. Unless endometrial hyperplasias are stratified by histological morphometric D-Score, PTEN has a low positive predictive value.     

Factores de riesgo de enfermedad residual en la re-RTU en una gran cohorte de pacientes con enfermedad T1G3

Introduction and objectivesThe goals of transurethral resection of a bladder tumor (TUR) are to completely resect the lesions and to make a correct diagnosis in order to adequately stage the patient. It is well known that the presence of detrusor muscle in the specimen is a prerequisite to minimize the risk of under staging.Persistent disease after resection of bladder tumors is not uncommon and is the reason why the European Guidelines recommended a re-TUR for all T1 tumors. It was recently published that when there is muscle in the specimen, re-TUR does not influence progression or cancer specific survival.We present here the patient and tumor factors that may influence the presence of residual disease at re-TUR.Material and methodsIn our retrospective cohort of 2451 primary T1G3 patients initially treated with BCG, pathology results for 934 patients (38.1%) who underwent re-TUR are available. 74% had multifocal tumors, 20% of tumors were more than 3 cm in diameter and 26% had concomitant CIS.In this subgroup of patients who underwent re-TUR, there was no residual disease in 267 patients (29%) and residual disease in 667 patients (71%): Ta in 378 (40%) and T1 in 289 (31%) patients. Age, gender, tumor status (primary/recurrent), previous intravesical therapy, tumor size, tumor multi-focality, presence of concomitant CIS, and muscle in the specimen were analyzed in order to evaluate risk factors of residual disease at re-TUR, both in univariate analyses and multivariate logistic regressions.ResultsThe following were not risk factors for residual disease: age, gender, tumor status and previous intravesical chemotherapy. The following were univariate risk factors for presence of residual disease: no muscle in TUR, multiple tumors, tumors > 3 cm, and presence of concomitant CIS. Due to the correlation between tumor multi-focality and tumor size, the multivariate model retained either the number of tumors or the tumor diameter (but not both), p < 0.001. The presence of muscle in the specimen was no longer significant, while the presence of CIS only remained significant in the model with tumor size, p < 0.001.ConclusionsThe most significant factors for a higher risk of residual disease at re-TUR in T1G3 patients are multifocal tumors and tumors more than 3 cm. Patients with concomitant CIS and those without muscle in the specimen also have a higher risk of residual disease.     

组蛋白去甲基化酶含有Jumonji结构域的蛋白质2D在胃癌组织的表达及其临床意义

目的观察含有Jumonji结构域的蛋白质2D(JMJD2D)在胃癌组织的表达并探讨其临床意义。方法收集2013年1月至2014年12月期间来自中国科学院大学附属肿瘤医院(浙江省肿瘤医院)手术治疗并经病理诊断证实的133例胃腺癌标本。采用免疫组织化学法检测133例胃癌组织及其配对的癌旁正常组织中JMJD2D的表达,应用SPSS-22统计软件分析其临床意义及与预后的关系,采用比例风险回归模型(proportional hazards model,Cox模型)多因素回归分析JMJD2D蛋白表达及其他病理参数对胃癌患者预后的预测价值。结果胃癌组织中JMJD2D的高表达率为75.9%(101/133),显著高于癌旁正常胃组织(高表达率2.3%,3/133,χ²=64.821,P<0.01),差异有统计学意义。肿瘤组织中JMJD2D高表达与患者幽门螺杆菌感染状态(χ²=22.163,P<0.01)、肿瘤分化程度(χ²=7.022,P<0.05)、浸润深度(χ²=5.061,P<0.05)、淋巴结转移状态(χ²=14.123,P<0.01)、临床TNM分期(χ²=23.194,P<0.01)显著相关,而与患者性别、肿瘤诊断时年龄、肿瘤部位和大小无相关(χ²=0.072、1.451、2.562、1.383,P值均>0.05)。普兰-迈耶(Kaplan-Meier)生存分析显示,JMJD2D高表达的胃癌患者与正常/低表达患者中位生存时间分别为34个月和65个月,两者差异有统计学意义(P<0.05)。比例风险回归模型(proportional hazards model,Cox模型)多因素回归分析表明JMJD2D高表达是胃癌患者独立预后因素[危险比(HR)=2.38,P<0.01]。结论JMJD2D在胃癌组织中高表达,且与胃癌进展及患者预后显著相关。