首页 > 最新文献

medRxiv - Dermatology最新文献

英文 中文
Individualized melanoma risk prediction using machine learning with electronic health records 利用机器学习和电子健康记录进行个性化黑色素瘤风险预测
Pub Date : 2024-07-27 DOI: 10.1101/2024.07.26.24311080
Guihong Wan, Sara Khattab, Katie Roster, Nga Nguyen, Boshen Yan, Hannah Rashdan, Hossein Estiri, Yevgeniy R. Semenov
Background:Melanoma is a lethal form of skin cancer with a high propensity for metastasizing, making early detection crucial. This study aims to develop a machine learning model using electronic health record data to identify patients at high risk of developing melanoma to prioritize them for dermatology screening.Methods:This retrospective study included patients diagnosed with melanoma (cases), as well as matched patients without melanoma (controls), from Massachusetts General Hospital (MGH), Brigham and Women's Hospital (BWH), Dana-Farber Cancer Institute (DFCI), and other hospital centers within the Research Patient Data Registry at Mass General Brigham healthcare system between 1992 and 2022. Patient demographics, family history, diagnoses, medications, procedures, laboratory tests, reasons for visits, and allergy data six months prior to the date of first melanoma diagnosis or date of censoring were extracted. A machine learning framework for health outcomes (MLHO) was utilized to build the model. Performance was evaluated using five-fold cross-validation of the MGH cohort (internal validation) and by using the MGH cohort for model training and the non-MGH cohort for independent testing (external validation). The Area Under the Receiver Operating Characteristic Curve (AUC-ROC) and the Area Under the Precision-Recall Curve (AUC-PR), along with 95% Confidence Intervals (CIs), were computed. Results:This study identified 10,778 patients with melanoma and 10,778 matched patients without melanoma, including 8,944 from MGH and 1,834 from non-MGH hospitals in each cohort, both with an average follow-up duration of 9 years. In the internal and external validations, the model achieved AUC-ROC values of 0.826 (95% CI: 0.819-0.832) and 0.823 (95% CI: 0.809-0.837) and AUC-PR scores of 0.841 (95% CI: 0.834-0.848) and 0.822 (95% CI: 0.806-0.839), respectively. Important risk features included a family history of melanoma, a family history of skin cancer, and a prior diagnosis of benign neoplasm of skin. Conversely, medical examination without abnormal findings was identified as a protective feature.Conclusions:Machine learning techniques and electronic health records can be effectively used to predict melanoma risk, potentially aiding in identifying high-risk patients and enabling individualized screening strategies for melanoma.
背景:黑色素瘤是一种致命的皮肤癌,极易转移,因此早期发现至关重要。本研究旨在利用电子健康记录数据开发一种机器学习模型,以识别黑色素瘤高风险患者,并优先安排他们接受皮肤科筛查。方法:这项回顾性研究纳入了麻省总医院(MGH)、布里格姆妇女医院(BWH)、丹娜-法伯癌症研究所(DFCI)以及麻省总医院布里格姆医疗保健系统研究患者数据登记处的其他医院中心在1992年至2022年期间确诊为黑色素瘤的患者(病例)和未患黑色素瘤的匹配患者(对照)。我们提取了患者的人口统计学特征、家族史、诊断、用药、手术、实验室检查、就诊原因以及首次黑色素瘤诊断日期或剔除日期前六个月的过敏数据。利用健康结果机器学习框架(MLHO)来建立模型。通过对MGH队列进行五倍交叉验证(内部验证),以及使用MGH队列进行模型训练和非MGH队列进行独立测试(外部验证)来评估模型的性能。计算了接收者操作特征曲线下面积(AUC-ROC)和精确度-召回曲线下面积(AUC-PR)以及95%置信区间(CI)。结果:这项研究共发现了10778名黑色素瘤患者和10778名匹配的非黑色素瘤患者,每个队列中有8944人来自MGH,1834人来自非MGH医院,平均随访时间均为9年。在内部和外部验证中,该模型的AUC-ROC值分别为0.826(95% CI:0.819-0.832)和0.823(95% CI:0.809-0.837),AUC-PR值分别为0.841(95% CI:0.834-0.848)和0.822(95% CI:0.806-0.839)。重要的风险特征包括黑色素瘤家族史、皮肤癌家族史和曾被诊断为皮肤良性肿瘤。结论:机器学习技术和电子健康记录可有效用于预测黑色素瘤风险,从而帮助识别高危患者,实现黑色素瘤的个体化筛查策略。
{"title":"Individualized melanoma risk prediction using machine learning with electronic health records","authors":"Guihong Wan, Sara Khattab, Katie Roster, Nga Nguyen, Boshen Yan, Hannah Rashdan, Hossein Estiri, Yevgeniy R. Semenov","doi":"10.1101/2024.07.26.24311080","DOIUrl":"https://doi.org/10.1101/2024.07.26.24311080","url":null,"abstract":"Background:\u0000Melanoma is a lethal form of skin cancer with a high propensity for metastasizing, making early detection crucial. This study aims to develop a machine learning model using electronic health record data to identify patients at high risk of developing melanoma to prioritize them for dermatology screening.\u0000Methods:\u0000This retrospective study included patients diagnosed with melanoma (cases), as well as matched patients without melanoma (controls), from Massachusetts General Hospital (MGH), Brigham and Women's Hospital (BWH), Dana-Farber Cancer Institute (DFCI), and other hospital centers within the Research Patient Data Registry at Mass General Brigham healthcare system between 1992 and 2022. Patient demographics, family history, diagnoses, medications, procedures, laboratory tests, reasons for visits, and allergy data six months prior to the date of first melanoma diagnosis or date of censoring were extracted. A machine learning framework for health outcomes (MLHO) was utilized to build the model. Performance was evaluated using five-fold cross-validation of the MGH cohort (internal validation) and by using the MGH cohort for model training and the non-MGH cohort for independent testing (external validation). The Area Under the Receiver Operating Characteristic Curve (AUC-ROC) and the Area Under the Precision-Recall Curve (AUC-PR), along with 95% Confidence Intervals (CIs), were computed. Results:\u0000This study identified 10,778 patients with melanoma and 10,778 matched patients without melanoma, including 8,944 from MGH and 1,834 from non-MGH hospitals in each cohort, both with an average follow-up duration of 9 years. In the internal and external validations, the model achieved AUC-ROC values of 0.826 (95% CI: 0.819-0.832) and 0.823 (95% CI: 0.809-0.837) and AUC-PR scores of 0.841 (95% CI: 0.834-0.848) and 0.822 (95% CI: 0.806-0.839), respectively. Important risk features included a family history of melanoma, a family history of skin cancer, and a prior diagnosis of benign neoplasm of skin. Conversely, medical examination without abnormal findings was identified as a protective feature.\u0000Conclusions:\u0000Machine learning techniques and electronic health records can be effectively used to predict melanoma risk, potentially aiding in identifying high-risk patients and enabling individualized screening strategies for melanoma.","PeriodicalId":501385,"journal":{"name":"medRxiv - Dermatology","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141783247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Gut microbiome and lichen sclerosus: a two-sample bi-directional Mendelian randomization study 肠道微生物群与硬皮病:双样本双向孟德尔随机研究
Pub Date : 2024-07-24 DOI: 10.1101/2024.07.23.24310907
Jun Hu, Jiayan Chen, Peiyan Wang, Changji Xiao, Kalibinuer Kelaimu, Xianshu Gao, Xiaomei Li
(1) Background: Recent studies suggest a potential link between gut microbiomes (GMs) and inflammatory diseases, but the role of GMs in lichen sclerosus (LS) remains unclear. This study aims to investigate the causal relationship between GMs and LS, focusing on key GM taxa. (2) Methods: We utilized GWAS summary statistics for 211 GM taxa and their association with 2,445 LS patients and 353,088 healthy controls, employing Mendelian randomization (MR). GWAS data for GM taxa came from the MiBioGen consortium, and for LS from the FinnGen consortium. The primary analytical tools included the inverse-variance weighted (IVW) method, weighted MR, simple mode, weighted median, and MR-Egger methods. Sensitivity analyses included leave-one-out analysis, MR-Egger intercept test, MR-PRESSO global test, and Cochrane's Q-test. A reverse MR analysis was conducted on bacteria identified in the forward MR study. (3) Results: We identified one strong causal relationship: order Burkholderiales [odds ratio (OR) = 0.420, 95% confidence interval (CI): 0.230 - 0.765, p = 0.005], and three nominally significant relationships: phylum Cyanobacteria (OR = 0.585, 95% CI: 0.373 - 0.919, p = 0.020), class Betaproteobacteria (OR = 0.403, 95% CI: 0.189 - 0.857, p = 0.018), and genus Butyrivibrio (OR = 0.678, 95% CI: 0.507 - 0.907, p = 0.009). Moreover, this MR analysis was not impacted by horizontal pleiotropy, according to the MR-Egger intercept test and MR-PRESSO global test (p > 0.05). Remarkably, the reliability of our results was confirmed by leave-one-out analysis. Reverse MR analysis showed no significant causal relationship between LS and GM. (4) Conclusions: This MR study identifies specific gut flora linked to a lower risk of LS, offering new insights for disease treatment and prevention. Future research should incorporate metagenomics sequencing of extensive microbiome GWAS datasets.
(1) 背景:最近的研究表明,肠道微生物组(GMs)与炎症性疾病之间存在潜在联系,但GMs在扁平苔藓(LS)中的作用仍不清楚。本研究旨在调查肠道微生物组与扁平苔藓之间的因果关系,重点研究主要的肠道微生物类群。(2)方法:我们利用孟德尔随机化(MR)方法,对 211 个 GM 分类群及其与 2,445 名 LS 患者和 353,088 名健康对照的关系进行了 GWAS 统计汇总。GM 分类群的 GWAS 数据来自 MiBioGen 联盟,LS 的 GWAS 数据来自 FinnGen 联盟。主要分析工具包括反方差加权(IVW)法、加权 MR、简单模式、加权中位数和 MR-Egger 法。敏感性分析包括留一分析、MR-Egger 截距检验、MR-PRESSO 全局检验和 Cochrane Q 检验。对正向 MR 研究中发现的细菌进行了反向 MR 分析。(3)结果:我们确定了一个强因果关系:伯克霍尔德氏菌目[几率比(OR)= 0.420,95% 置信区间(CI):0.230 - 0.765,P = 0.005],以及三个名义上的显著关系:蓝藻门(OR = 0.585,95% CI:0.373 - 0.919,p = 0.020)、倍增菌类(OR = 0.403,95% CI:0.189 - 0.857,p = 0.018)和丁弧菌属(OR = 0.678,95% CI:0.507 - 0.907,p = 0.009)。此外,根据 MR-Egger 截距检验和 MR-PRESSO 全局检验(p > 0.05),该 MR 分析未受水平多效性的影响。值得注意的是,我们的结果的可靠性得到了撇除分析的证实。反向 MR 分析表明 LS 与 GM 之间没有明显的因果关系。(4) 结论:这项磁共振研究确定了与降低 LS 风险相关的特定肠道菌群,为疾病的治疗和预防提供了新的见解。未来的研究应结合元基因组学对广泛的微生物组 GWAS 数据集进行测序。
{"title":"Gut microbiome and lichen sclerosus: a two-sample bi-directional Mendelian randomization study","authors":"Jun Hu, Jiayan Chen, Peiyan Wang, Changji Xiao, Kalibinuer Kelaimu, Xianshu Gao, Xiaomei Li","doi":"10.1101/2024.07.23.24310907","DOIUrl":"https://doi.org/10.1101/2024.07.23.24310907","url":null,"abstract":"(1) Background: Recent studies suggest a potential link between gut microbiomes (GMs) and inflammatory diseases, but the role of GMs in lichen sclerosus (LS) remains unclear. This study aims to investigate the causal relationship between GMs and LS, focusing on key GM taxa. (2) Methods: We utilized GWAS summary statistics for 211 GM taxa and their association with 2,445 LS patients and 353,088 healthy controls, employing Mendelian randomization (MR). GWAS data for GM taxa came from the MiBioGen consortium, and for LS from the FinnGen consortium. The primary analytical tools included the inverse-variance weighted (IVW) method, weighted MR, simple mode, weighted median, and MR-Egger methods. Sensitivity analyses included leave-one-out analysis, MR-Egger intercept test, MR-PRESSO global test, and Cochrane's Q-test. A reverse MR analysis was conducted on bacteria identified in the forward MR study. (3) Results: We identified one strong causal relationship: order Burkholderiales [odds ratio (OR) = 0.420, 95% confidence interval (CI): 0.230 - 0.765, p = 0.005], and three nominally significant relationships: phylum Cyanobacteria (OR = 0.585, 95% CI: 0.373 - 0.919, p = 0.020), class Betaproteobacteria (OR = 0.403, 95% CI: 0.189 - 0.857, p = 0.018), and genus Butyrivibrio (OR = 0.678, 95% CI: 0.507 - 0.907, p = 0.009). Moreover, this MR analysis was not impacted by horizontal pleiotropy, according to the MR-Egger intercept test and MR-PRESSO global test (p > 0.05). Remarkably, the reliability of our results was confirmed by leave-one-out analysis. Reverse MR analysis showed no significant causal relationship between LS and GM. (4) Conclusions: This MR study identifies specific gut flora linked to a lower risk of LS, offering new insights for disease treatment and prevention. Future research should incorporate metagenomics sequencing of extensive microbiome GWAS datasets.","PeriodicalId":501385,"journal":{"name":"medRxiv - Dermatology","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141783248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A postzygotic GNA13 variant upregulates the RHOA/ROCK pathway and alters melanocyte function in a mosaic skin hypopigmentation syndrome 在马赛克皮肤色素沉着综合征中,后染色体 GNA13 变体会上调 RHOA/ROCK 通路并改变黑色素细胞的功能
Pub Date : 2024-07-24 DOI: 10.1101/2024.07.24.24310661
Rana El Masri, Alberto Iannuzzo, Paul Kuentz, Rachida Tacine, Marie Vincent, Sebastien Barbarot, Fanny Morice-Picard, Franck Boralevi, Naia Oillarburu, Juliette Mazereeuw-Hautier, Yannis Duffourd, Laurence Faivre, Arthur Sorlin, Pierre Vabres, Jerome Delon
The genetic bases of mosaic pigmentation disorders have increasingly been identified, but these conditions remain poorly characterised, and their pathophysiology is unclear. Here, we report in four unrelated patients that a recurrent postzygotic mutation in GNA13 is responsible for a recognizable syndrome with hypomelanosis of Ito associated with developmental anomalies. GNA13 encodes Galpha13, a subunit of alpha-beta-gamme heterotrimeric G proteins coupled to specific transmembrane receptors known as G-protein coupled receptors. In-depth functional investigations revealed that this R200K mutation provides a gain of function to Galpha13. Mechanistically, we show that this variant hyperactivates the RHOA/ROCK signalling pathway that consequently increases actin polymerisation and myosin light chains phosphorylation, and promotes melanocytes rounding. Our results also indicate that R200K Galpha13 hyperactivates the YAP signalling pathway. All these changes appear to affect cell migration and adhesion but not the proliferation. Our results suggest that hypopigmentation can result from a defect in melanosome transfer to keratinocytes due to cell shape alterations. These findings highlight the interaction between heterotrimeric G proteins and the RHOA pathway, and their role in melanocyte function.
马赛克色素沉着病的遗传基础已被越来越多地发现,但这些病症的特征仍不十分明确,其病理生理学也不清楚。在这里,我们报告了四名无血缘关系的患者,GNA13 的复发性杂交后突变是导致伊藤色素沉着与发育异常的可识别综合征的原因。GNA13 编码 Galpha13,它是α-β-甘氨酸异三聚 G 蛋白的一个亚基,与被称为 G 蛋白偶联受体的特定跨膜受体偶联。深入的功能研究发现,R200K 突变为 Galpha13 提供了功能增益。从机理上讲,我们发现这种变异会过度激活 RHOA/ROCK 信号通路,从而增加肌动蛋白的聚合和肌球蛋白轻链的磷酸化,促进黑色素细胞变圆。我们的研究结果还表明,R200K Galpha13 会过度激活 YAP 信号通路。所有这些变化似乎都会影响细胞迁移和粘附,但不会影响细胞增殖。我们的研究结果表明,色素沉着可能是由于细胞形状改变导致黑色素小体向角质形成细胞转移的缺陷造成的。这些发现突显了异三聚体 G 蛋白与 RHOA 通路之间的相互作用,以及它们在黑色素细胞功能中的作用。
{"title":"A postzygotic GNA13 variant upregulates the RHOA/ROCK pathway and alters melanocyte function in a mosaic skin hypopigmentation syndrome","authors":"Rana El Masri, Alberto Iannuzzo, Paul Kuentz, Rachida Tacine, Marie Vincent, Sebastien Barbarot, Fanny Morice-Picard, Franck Boralevi, Naia Oillarburu, Juliette Mazereeuw-Hautier, Yannis Duffourd, Laurence Faivre, Arthur Sorlin, Pierre Vabres, Jerome Delon","doi":"10.1101/2024.07.24.24310661","DOIUrl":"https://doi.org/10.1101/2024.07.24.24310661","url":null,"abstract":"The genetic bases of mosaic pigmentation disorders have increasingly been identified, but these conditions remain poorly characterised, and their pathophysiology is unclear. Here, we report in four unrelated patients that a recurrent postzygotic mutation in GNA13 is responsible for a recognizable syndrome with hypomelanosis of Ito associated with developmental anomalies. GNA13 encodes Galpha13, a subunit of alpha-beta-gamme heterotrimeric G proteins coupled to specific transmembrane receptors known as G-protein coupled receptors. In-depth functional investigations revealed that this R200K mutation provides a gain of function to Galpha13. Mechanistically, we show that this variant hyperactivates the RHOA/ROCK signalling pathway that consequently increases actin polymerisation and myosin light chains phosphorylation, and promotes melanocytes rounding. Our results also indicate that R200K Galpha13 hyperactivates the YAP signalling pathway. All these changes appear to affect cell migration and adhesion but not the proliferation. Our results suggest that hypopigmentation can result from a defect in melanosome transfer to keratinocytes due to cell shape alterations. These findings highlight the interaction between heterotrimeric G proteins and the RHOA pathway, and their role in melanocyte function.","PeriodicalId":501385,"journal":{"name":"medRxiv - Dermatology","volume":"55 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141786033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Radiation sensitivity and efficacy in aggressive and non-aggressive basal cell carcinoma (BCC) of the skin: Image Guided Superficial Radiation Therapy achieves high rate of local control in sclerosing, infiltrative, morpheaform and micronodular BCC subtypes as well as in non high risk BCCs, an analysis of 7994 BCC lesions. 侵袭性和非侵袭性皮肤基底细胞癌(BCC)的放射敏感性和疗效:对 7994 例 BCC 病变的分析显示,图像引导表层放射治疗对硬化性、浸润性、变形性和微小结节性 BCC 亚型以及非高危 BCC 均能实现较高的局部控制率。
Pub Date : 2024-07-18 DOI: 10.1101/2024.07.17.24310584
Lio Yu, Michael Kaczmarski, Clay Cockerell
Background High risk (HR) basal cell carcinoma (BCC) subtypes have been associated with high recurrence rates that is felt to be better managed surgically. Specifically, Mohs Micrographic Surgery (MMS) is considered most effective for aggressive HR BCCs and superior to traditional nonsurgical techniques, including radiation. Recently, superficial radiation therapy with high resolution ultrasound image guidance called Image Guided Superficial Radiation Therapy (IGSRT) displayed high local control (LC) rates and is an emerging non-surgical alternative to MMS for non-melanoma skin cancer (NMSC). Objectives We present the largest experience in the USA on treatment of BCCs using IGSRT and specifically evaluate if there are differences in LC between HR BCC versus non-HR subtypes using this technology. Methods A retrospective analysis was conducted on 7,994 BCC lesions treated with IGSRT in the continental United States. We compared the results of BCCs treated with IGSRT separated by HR vs non HR groups including 339 HR BCC lesions and 7655 non HR BCC lesions. High risk was defined as infiltrative, micronodular, morpheaform, and sclerosing subtypes. Non-HR BCC included superficial, nodular, and not otherwise specified (NOS) subtypes. Local control (LC) rates at two and five years were calculated with actuarial life-table and Kaplan-Meier methods and statistically compared using log rank tests. Results IGSRT treatment of the HR BCC group showed no recurrences with two and five-year actuarial and KM LC rates all at 100%. In comparison, the non-HR BCC cohort achieved similar two and five-year actuarial LC rates of 99.71% and 99.24% (KM LC at 99.5% and 99.23%), respectively. No statistical differences in LC rates between the two cohorts (p=0.278 each) resulted. Patients tolerated treatment well with little or rare high grade RTOG toxicity reported in both cohorts. Conclusion HR BCC may be treated just as effectively as low risk BCC using IGSRT and presents a viable alternative to MMS. The targeted approach using IGSRT, incorporating high resolution dermal ultrasound (HRDUS), appear to enhance treatment accuracy and effectiveness demonstrating high LC rates in all subtypes of BCC comparable to MMS and is a viable non-surgical option.
背景 高危(HR)基底细胞癌(BCC)亚型与高复发率有关,人们认为手术治疗效果更好。具体而言,莫氏显微放射手术(MMS)被认为对侵袭性高危基底细胞癌最有效,优于传统的非手术治疗技术,包括放射治疗。最近,在高分辨率超声图像引导下进行的表层放射治疗(称为图像引导表层放射治疗(IGSRT))显示出很高的局部控制率(LC),成为非黑色素瘤皮肤癌(NMSC)莫氏显微放射治疗的新兴非手术替代方法。目的 我们介绍了美国使用 IGSRT 治疗 BCC 的最大规模经验,并特别评估了使用该技术治疗 HR BCC 与非 HR 亚型的 LC 是否存在差异。方法 我们对美国大陆采用 IGSRT 治疗的 7994 例 BCC 病变进行了回顾性分析。我们比较了接受 IGSRT 治疗的 BCC 的结果,将其分为高危与非高危两组,包括 339 例高危 BCC 病变和 7655 例非高危 BCC 病变。高危定义为浸润型、微小结节型、病变型和硬化亚型。非高风险 BCC 包括浅表性、结节性和非特殊(NOS)亚型。采用精算生命表法和 Kaplan-Meier 法计算两年和五年的局部控制(LC)率,并采用对数秩检验进行统计比较。结果 HR BCC 组的 IGSRT 治疗无复发,两年和五年的精算 LC 率和 KM LC 率均为 100%。相比之下,非 HR BCC 组的两年和五年精算 LC 率分别为 99.71% 和 99.24%(KM LC 率分别为 99.5% 和 99.23%)。两组患者的 LC 率无统计学差异(P=0.278)。患者对治疗的耐受性良好,两组患者均报告了极少或罕见的 RTOG 高毒性。结论 使用 IGSRT 治疗高危 BCC 与低危 BCC 一样有效,是 MMS 的可行替代方案。使用 IGSRT 的靶向方法结合高分辨率真皮超声 (HRDUS) 似乎提高了治疗的准确性和有效性,在所有 BCC 亚型中均显示出与 MMS 相当的高 LC 率,是一种可行的非手术疗法。
{"title":"Radiation sensitivity and efficacy in aggressive and non-aggressive basal cell carcinoma (BCC) of the skin: Image Guided Superficial Radiation Therapy achieves high rate of local control in sclerosing, infiltrative, morpheaform and micronodular BCC subtypes as well as in non high risk BCCs, an analysis of 7994 BCC lesions.","authors":"Lio Yu, Michael Kaczmarski, Clay Cockerell","doi":"10.1101/2024.07.17.24310584","DOIUrl":"https://doi.org/10.1101/2024.07.17.24310584","url":null,"abstract":"Background High risk (HR) basal cell carcinoma (BCC) subtypes have been associated with high recurrence rates that is felt to be better managed surgically. Specifically, Mohs Micrographic Surgery (MMS) is considered most effective for aggressive HR BCCs and superior to traditional nonsurgical techniques, including radiation. Recently, superficial radiation therapy with high resolution ultrasound image guidance called Image Guided Superficial Radiation Therapy (IGSRT) displayed high local control (LC) rates and is an emerging non-surgical alternative to MMS for non-melanoma skin cancer (NMSC). Objectives We present the largest experience in the USA on treatment of BCCs using IGSRT and specifically evaluate if there are differences in LC between HR BCC versus non-HR subtypes using this technology. Methods A retrospective analysis was conducted on 7,994 BCC lesions treated with IGSRT in the continental United States. We compared the results of BCCs treated with IGSRT separated by HR vs non HR groups including 339 HR BCC lesions and 7655 non HR BCC lesions. High risk was defined as infiltrative, micronodular, morpheaform, and sclerosing subtypes. Non-HR BCC included superficial, nodular, and not otherwise specified (NOS) subtypes. Local control (LC) rates at two and five years were calculated with actuarial life-table and Kaplan-Meier methods and statistically compared using log rank tests. Results IGSRT treatment of the HR BCC group showed no recurrences with two and five-year actuarial and KM LC rates all at 100%. In comparison, the non-HR BCC cohort achieved similar two and five-year actuarial LC rates of 99.71% and 99.24% (KM LC at 99.5% and 99.23%), respectively. No statistical differences in LC rates between the two cohorts (p=0.278 each) resulted. Patients tolerated treatment well with little or rare high grade RTOG toxicity reported in both cohorts. Conclusion HR BCC may be treated just as effectively as low risk BCC using IGSRT and presents a viable alternative to MMS. The targeted approach using IGSRT, incorporating high resolution dermal ultrasound (HRDUS), appear to enhance treatment accuracy and effectiveness demonstrating high LC rates in all subtypes of BCC comparable to MMS and is a viable non-surgical option.","PeriodicalId":501385,"journal":{"name":"medRxiv - Dermatology","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141745290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Identification and characterization of collagen XXIII alpha 1 as a novel risk factor for eczema herpeticum 胶原蛋白 XXIII alpha 1 的鉴定和特征描述--它是疱疹性湿疹的新型风险因素
Pub Date : 2024-07-14 DOI: 10.1101/2024.07.13.24310236
Shruti Chopra, Lennart M. Roesner, Katinka Döhner, Jana Zeitvogel, Stephan Traidl, Elke Rodriguez, Inken Harder, Lieb Wolfgang, Stephan Weidinger, Thomas F. Schulz, Beate Sodeik, Thomas Werfel
Abstract Background:A subgroup of atopic dermatitis (AD) patients is prone to develop severe, disseminated cutaneous infection with herpes simplex virus (HSV), known as eczema herpeticum (EH). The occurrence of EH in a subset of AD patients and its frequent recurrence implies the importance of genetic factors in its pathogenesis. Objective:We aimed to identify novel genetic risk factors for EH and study their impact on HSV-1 infection. Methods:We performed whole exome sequencing on nine AD patients with (ADEH+) and without (ADEH-) a history of EH in comparison to healthy controls. We validated the finding of a variant of COL23A1 gene (encoding Collagen type XXIII alpha 1 chain) in ADEH in a larger cohort of 117 ADEH+, 117 ADEH- patients and 118 healthy controls by PCR. We studied the expression of COL23A1 in keratinocytes from ADEH+ and ADEH- patients, and the upregulated COL23A1 expression in primary keratinocytes and in the cell line HaCaT to study its role in HSV-1 infection. Results:We identified a single nucleotide polymorphism (SNP), rs2973744 in COL23A1, as a risk factor for EH observed in 5% of ADEH+ patients, 1.6% of healthy donors and 0% of ADEH- patients. Primary human keratinocytes from an ADEH+ patient with SNP rs2973744 expressed higher COL23A1 levels and were more susceptible to HSV-1 than keratinocytes from ADEH- patients. In functional assays we showed that HSV-1 gene expression and cell-to-cell spread was more efficient in keratinocytes with increased expression of COL23A1. Moreover, COL23A1 overexpression in HaCaT cells resulted in transcriptional downregulation of several genes that are involved in an effective immune response (IL1R1, IL32, TLR4, CFH, C3, S100A9, IRF1, and ADAM23) and a notable upregulation of TNC and SPINK5 that are associated with AD. Conclusion:Upregulation of COL23A1 promotes HSV-1 infection presumably by attenuating antiviral responses of keratinocytes. Among other markers, the COL23A1 SNP rs2973744 could be included in the screening of AD patients to identify patients at risk of EH, thus allowing early initiation of therapy.
摘要背景:特应性皮炎(AD)患者中有一个亚群容易感染单纯疱疹病毒(HSV),出现严重的播散性皮肤感染,即带状疱疹湿疹(EH)。EH发生在一部分AD患者中,而且经常复发,这意味着遗传因素在其发病机制中的重要性。目的:我们旨在确定EH的新型遗传风险因素,并研究其对HSV-1感染的影响。方法:我们对9名有(ADEH+)和无(ADEH-)EH病史的AD患者进行了全外显子组测序,并与健康对照组进行了比较。我们通过PCR方法在117名ADEH+、117名ADEH-患者和118名健康对照者中验证了ADEH中COL23A1基因(编码XXIII型胶原蛋白α1链)变异的发现。我们研究了 COL23A1 在 ADEH+ 和 ADEH- 患者角质细胞中的表达,以及 COL23A1 在原发性角质细胞和细胞系 HaCaT 中的上调表达,以研究其在 HSV-1 感染中的作用。结果:我们在5%的ADEH+患者、1.6%的健康供体和0%的ADEH-患者中发现了COL23A1中的单核苷酸多态性(SNP)rs2973744,它是EH的一个风险因素。与 ADEH- 患者的角朊细胞相比,带有 SNP rs2973744 的 ADEH+ 患者的原代人类角朊细胞表达更高的 COL23A1 水平,对 HSV-1 更易感。在功能测试中,我们发现在 COL23A1 表达量增加的角质细胞中,HSV-1 基因表达和细胞间传播的效率更高。此外,COL23A1在HaCaT细胞中的过表达导致参与有效免疫反应的多个基因(IL1R1、IL32、TLR4、CFH、C3、S100A9、IRF1和ADAM23)转录下调,而与AD相关的TNC和SPINK5则显著上调。结论:COL23A1的上调可能通过削弱角朊细胞的抗病毒反应来促进HSV-1感染。在其他标记中,COL23A1 SNP rs2973744可用于AD患者的筛查,以识别有EH风险的患者,从而及早开始治疗。
{"title":"Identification and characterization of collagen XXIII alpha 1 as a novel risk factor for eczema herpeticum","authors":"Shruti Chopra, Lennart M. Roesner, Katinka Döhner, Jana Zeitvogel, Stephan Traidl, Elke Rodriguez, Inken Harder, Lieb Wolfgang, Stephan Weidinger, Thomas F. Schulz, Beate Sodeik, Thomas Werfel","doi":"10.1101/2024.07.13.24310236","DOIUrl":"https://doi.org/10.1101/2024.07.13.24310236","url":null,"abstract":"Abstract Background:\u0000A subgroup of atopic dermatitis (AD) patients is prone to develop severe, disseminated cutaneous infection with herpes simplex virus (HSV), known as eczema herpeticum (EH). The occurrence of EH in a subset of AD patients and its frequent recurrence implies the importance of genetic factors in its pathogenesis. Objective:\u0000We aimed to identify novel genetic risk factors for EH and study their impact on HSV-1 infection. Methods:\u0000We performed whole exome sequencing on nine AD patients with (ADEH+) and without (ADEH-) a history of EH in comparison to healthy controls. We validated the finding of a variant of COL23A1 gene (encoding Collagen type XXIII alpha 1 chain) in ADEH in a larger cohort of 117 ADEH+, 117 ADEH- patients and 118 healthy controls by PCR. We studied the expression of COL23A1 in keratinocytes from ADEH+ and ADEH- patients, and the upregulated COL23A1 expression in primary keratinocytes and in the cell line HaCaT to study its role in HSV-1 infection. Results:\u0000We identified a single nucleotide polymorphism (SNP), rs2973744 in COL23A1, as a risk factor for EH observed in 5% of ADEH+ patients, 1.6% of healthy donors and 0% of ADEH- patients. Primary human keratinocytes from an ADEH+ patient with SNP rs2973744 expressed higher COL23A1 levels and were more susceptible to HSV-1 than keratinocytes from ADEH- patients. In functional assays we showed that HSV-1 gene expression and cell-to-cell spread was more efficient in keratinocytes with increased expression of COL23A1. Moreover, COL23A1 overexpression in HaCaT cells resulted in transcriptional downregulation of several genes that are involved in an effective immune response (IL1R1, IL32, TLR4, CFH, C3, S100A9, IRF1, and ADAM23) and a notable upregulation of TNC and SPINK5 that are associated with AD. Conclusion:\u0000Upregulation of COL23A1 promotes HSV-1 infection presumably by attenuating antiviral responses of keratinocytes. Among other markers, the COL23A1 SNP rs2973744 could be included in the screening of AD patients to identify patients at risk of EH, thus allowing early initiation of therapy.","PeriodicalId":501385,"journal":{"name":"medRxiv - Dermatology","volume":"37 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141719370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Gasdermin D-Mediated Neutrophil Pyroptosis drives Inflammation in Psoriasis 由 Gasdermin D 介导的中性粒细胞嗜热促进了牛皮癣的炎症反应
Pub Date : 2024-07-11 DOI: 10.1101/2024.07.10.24310231
Jian Liu, YuYing Jiang, ZiYue Diao, DanDan Chen, RuiYuan Xia, BingWei Wang, Shuo Yang, ZhiQiang Yin
Psoriasis is a multifactorial immune-mediated inflammatory disease. Its pathogenesis involves abnormal accumulation of neutrophils and T-cell related abnormalities. Pyroptosis is a type of regulated cell death associated with innate immunity, but its role in psoriasis is unclear. In this study, we found that gasdermin D (Gsdmd) is higher in human psoriatic skin than that in normal skin, and in imiquimod-induced psoriasis-like mouse skin, the expression of Gsdmd was most significantly altered in neutrophils and Il1b was also mainly expressed in neutrophils. Immunohistochemical staining of serial sections of skin lesions from psoriasis patients and healthy control also showed that GSDMD expression is higher in psoriasis lesion, especially in neutrophils. Gsdmd deficiency mitigates psoriasis-like inflammation in mice. GSDMD in neutrophils contributes to psoriasis-like inflammation, while Gsdmd depletion in neutrophils attenuates the development of skin inflammation in psoriasis and reduces the release of the inflammatory cytokines. We found that neutrophil pyroptosis is involved in and contributes to psoriasis inflammation, which provides new insights into the treatment of psoriasis by targeting neutrophil pyroptosis.
银屑病是一种多因素免疫介导的炎症性疾病。其发病机制包括中性粒细胞的异常聚集和与 T 细胞相关的异常。炭疽是一种与先天性免疫相关的调节性细胞死亡,但其在银屑病中的作用尚不清楚。本研究发现,人类银屑病皮肤中的gasdermin D(Gsdmd)高于正常皮肤,在咪喹莫特诱导的银屑病样小鼠皮肤中,Gsdmd的表达在中性粒细胞中发生了最显著的改变,Il1b也主要在中性粒细胞中表达。对银屑病患者和健康对照组皮损的连续切片进行免疫组化染色也显示,银屑病皮损中 GSDMD 的表达较高,尤其是在中性粒细胞中。Gsdmd 缺乏可减轻小鼠的银屑病样炎症。嗜中性粒细胞中的 GSDMD 会导致银屑病样炎症,而嗜中性粒细胞中的 Gsdmd 缺乏会减轻银屑病皮肤炎症的发展,并减少炎症细胞因子的释放。我们发现嗜中性粒细胞增殖参与并促成了银屑病炎症,这为通过靶向嗜中性粒细胞增殖治疗银屑病提供了新的思路。
{"title":"Gasdermin D-Mediated Neutrophil Pyroptosis drives Inflammation in Psoriasis","authors":"Jian Liu, YuYing Jiang, ZiYue Diao, DanDan Chen, RuiYuan Xia, BingWei Wang, Shuo Yang, ZhiQiang Yin","doi":"10.1101/2024.07.10.24310231","DOIUrl":"https://doi.org/10.1101/2024.07.10.24310231","url":null,"abstract":"Psoriasis is a multifactorial immune-mediated inflammatory disease. Its pathogenesis involves abnormal accumulation of neutrophils and T-cell related abnormalities. Pyroptosis is a type of regulated cell death associated with innate immunity, but its role in psoriasis is unclear. In this study, we found that<em> gasdermin</em><em> D</em><em> (Gsdmd)</em> is higher in human psoriatic skin than that in normal skin, and in imiquimod-induced psoriasis-like mouse skin, the expression of <em>Gsdmd</em> was most significantly altered in neutrophils and <em>Il1b</em> was also mainly expressed in neutrophils. Immunohistochemical staining of serial sections of skin lesions from psoriasis patients and healthy control also showed that GSDMD expression is higher in psoriasis lesion, especially in neutrophils. <em>Gsdmd</em> deficiency mitigates psoriasis-like inflammation in mice. GSDMD in neutrophils contributes to psoriasis-like inflammation, while <em>Gsdmd</em> depletion in neutrophils attenuates the development of skin inflammation in psoriasis and reduces the release of the inflammatory cytokines. We found that neutrophil pyroptosis is involved in and contributes to psoriasis inflammation, which provides new insights into the treatment of psoriasis by targeting neutrophil pyroptosis.","PeriodicalId":501385,"journal":{"name":"medRxiv - Dermatology","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141612645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Exploring Interaction Between Genetically Predicted Body Mass Index and Serum 25-hydroxyvitamin D Levels on the Odds for Psoriasis in UK Biobank and the HUNT Study: A Factorial Mendelian Randomisation Study 探索英国生物库和 HUNT 研究中遗传预测体重指数和血清 25- 羟维生素 D 水平对银屑病发病几率的交互作用:因子孟德尔随机研究
Pub Date : 2024-07-03 DOI: 10.1101/2024.07.01.24309489
Marita Jenssen, Nikhil Arora, Mari Loset, Bjorn Olav Asvold, Laurent Thomas, Ole-Jorgen Gangso Bekkevold, Xiao-Mei Mai, Yi-Qian Sun, Anne-Sofie Furberg, Rolf Jorde, Tom Wilsgaard, Kjersti Danielsen, Ben M Brumpton
Background: Mendelian randomisation (MR) studies show that higher body mass index (BMI) and lower 25-hydroxyvitamin D (25[OH]D) increase psoriasis risk. The combined effect of these factors has not been explored using factorial MR.Methods: Using cross-sectional data from UK Biobank (UKB, n=398 404) and the Troendelag Health Study (HUNT, n=86 648), we calculated polygenic risk scores for BMI and 25(OH)D to estimate odds ratios for psoriasis using 2x2 and continuous factorial MR. We quantified additive interaction by relative excess risk due to interaction (RERI)-estimates. We also performed traditional observational analyses in UKB. Results: There were 12 207 (3.1%) participants with psoriasis in UKB and 7794 (9.0%) in HUNT. In 2x2 factorial MR, we found no evidence of relative excess risk for psoriasis due to interaction between genetically predicted higher BMI and lower 25(OH)D, neither in UKB (RERI -0.01, 95% confidence interval (CI) -0.08, 0.07) nor in HUNT (RERI -0.04, 95% CI -0.14, 0.06). The same was observed in the continuous factorial MR and observational analyses.Conclusions: This study did not find evidence of interaction between BMI and 25(OH)D on the risk of psoriasis. Given minor differences in measured BMI and 25(OH)D between groups, small effects may have been undetected.
背景:孟德尔随机化(MR)研究表明,较高的体重指数(BMI)和较低的25-羟维生素D(25[OH]D)会增加银屑病风险。这些因素的综合影响尚未通过因子MR进行探讨:利用英国生物库(UKB,n=398 404)和特罗恩德拉格健康研究(HUNT,n=86 648)的横断面数据,我们计算了体重指数和25(OH)D的多基因风险评分,并使用2x2和连续因子MR估算了银屑病的几率比。我们通过交互作用导致的相对超额风险(RERI)估计值对交互作用进行了量化。我们还在英国广播公司进行了传统的观察分析。结果在 UKB 中有 12 207 人(3.1%)患有银屑病,在 HUNT 中有 7794 人(9.0%)患有银屑病。在2x2因子MR中,我们没有发现证据表明,在UKB(RERI为-0.01,95%置信区间(CI)为-0.08,0.07)和HUNT(RERI为-0.04,95%置信区间(CI)为-0.14,0.06)中,遗传预测的较高体重指数和较低25(OH)D之间的相互作用会导致银屑病的相对超额风险。在连续因子MR和观察分析中也观察到了同样的情况:本研究未发现体重指数和 25(OH)D 对银屑病风险有相互作用的证据。由于各组间测量的体重指数和 25(OH)D 的差异较小,因此可能未发现微小的影响。
{"title":"Exploring Interaction Between Genetically Predicted Body Mass Index and Serum 25-hydroxyvitamin D Levels on the Odds for Psoriasis in UK Biobank and the HUNT Study: A Factorial Mendelian Randomisation Study","authors":"Marita Jenssen, Nikhil Arora, Mari Loset, Bjorn Olav Asvold, Laurent Thomas, Ole-Jorgen Gangso Bekkevold, Xiao-Mei Mai, Yi-Qian Sun, Anne-Sofie Furberg, Rolf Jorde, Tom Wilsgaard, Kjersti Danielsen, Ben M Brumpton","doi":"10.1101/2024.07.01.24309489","DOIUrl":"https://doi.org/10.1101/2024.07.01.24309489","url":null,"abstract":"Background: Mendelian randomisation (MR) studies show that higher body mass index (BMI) and lower 25-hydroxyvitamin D (25[OH]D) increase psoriasis risk. The combined effect of these factors has not been explored using factorial MR.\u0000Methods: Using cross-sectional data from UK Biobank (UKB, n=398 404) and the Troendelag Health Study (HUNT, n=86 648), we calculated polygenic risk scores for BMI and 25(OH)D to estimate odds ratios for psoriasis using 2x2 and continuous factorial MR. We quantified additive interaction by relative excess risk due to interaction (RERI)-estimates. We also performed traditional observational analyses in UKB. Results: There were 12 207 (3.1%) participants with psoriasis in UKB and 7794 (9.0%) in HUNT. In 2x2 factorial MR, we found no evidence of relative excess risk for psoriasis due to interaction between genetically predicted higher BMI and lower 25(OH)D, neither in UKB (RERI -0.01, 95% confidence interval (CI) -0.08, 0.07) nor in HUNT (RERI -0.04, 95% CI -0.14, 0.06). The same was observed in the continuous factorial MR and observational analyses.\u0000Conclusions: This study did not find evidence of interaction between BMI and 25(OH)D on the risk of psoriasis. Given minor differences in measured BMI and 25(OH)D between groups, small effects may have been undetected.","PeriodicalId":501385,"journal":{"name":"medRxiv - Dermatology","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141547314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multimodal Image Dataset for AI-based Skin Cancer (MIDAS) Benchmarking 基于人工智能的皮肤癌多模态图像数据集(MIDAS)基准测试
Pub Date : 2024-06-28 DOI: 10.1101/2024.06.27.24309562
Albert S Chiou, Jesutofunmi A Omiye, Haiwen Gui, Susan M Swetter, Justin M Ko, Brian Gastman, Joshua Arbesman, Zhou Ran Cai, Olivier Gevaert, Chris Sadee, Veronica M Rotemberg, Seung Seog Han, Philipp Tschandl, Meghan Dickman, Elizabeth Bailey, Gordon H Bae, Philip Bailin, Jennifer Boldrick, Kiana Yekrang, Peter Caroline, Jackson Hanna, Nicholas R Kurtansky, Jochen Weber, Niki A See, Michelle Phung, Marianna Gallegos, Roxana Daneshjou, Roberto Novoa
With an estimated 3 billion people globally lacking access to dermatological care, technological solutions leveraging artificial intelligence (AI) have been proposed to improve access. Diagnostic AI algorithms, however, require high-quality datasets to allow development and testing, particularly those that enable evaluation of both unimodal and multimodal approaches. Currently, the majority of dermatology AI algorithms are built and tested on proprietary, siloed data, often from a single site and with only a single image type (i.e., clinical or dermoscopic). To address this, we developed and released the Melanoma Research Alliance Multimodal Image Dataset for AI-based Skin Cancer (MIDAS) dataset, the largest publicly available, prospectively-recruited, paired dermoscopic- and clinical image-based dataset of biopsy-proven and dermatopathology-labeled skin lesions. We explored model performance on real-world cases using four previously published state-of-the-art (SOTA) models and compared model-to-clinician diagnostic performance. We also assessed algorithm performance using clinical photography taken at different distances from the lesion to assess its influence across diagnostic categories. We prospectively enrolled 796 patients through an IRB-approved protocol with informed consent representing 1290 unique lesions and 3830 total images (including dermoscopic and clinical images taken at 15-cm and 30-cm distance). Images represented the diagnostic diversity of lesions seen in general dermatology, with malignant, benign, and inflammatory lesions that included melanocytic nevi (22%; n=234), invasive cutaneous melanomas (4%; n=46), and melanoma in situ (4%; n=47). When evaluating SOTA models using the MIDAS dataset, we observed performance reduction across all models compared to their previously published performance metrics, indicating challenges to generalizability of current SOTA algorithms. As a comparative baseline, the dermatologists performing biopsies were 79% accurate with their top-1 diagnosis at differentiating a malignant from benign lesion. For malignant lesions, algorithms performed better on images acquired at 15-cm compared to 30-cm distance while dermoscopic images yielded higher sensitivity compared to clinical images. Improving our understanding of the strengths and weaknesses of AI diagnostic algorithms is critical as these tools advance towards widespread clinical deployment. While many algorithms may report high performance metrics, caution should be taken due to the potential for overfitting to localized datasets. MIDAS's robust, multimodal, and diverse dataset allows researchers to evaluate algorithms on our real-world images and better assess their generalizability.
据估计,全球有 30 亿人无法获得皮肤病治疗,因此有人提出了利用人工智能(AI)的技术解决方案,以改善获得治疗的机会。然而,人工智能诊断算法需要高质量的数据集来进行开发和测试,特别是那些能够评估单模态和多模态方法的数据集。目前,大多数皮肤病学人工智能算法都是在专有、孤立的数据基础上构建和测试的,这些数据通常来自单一网站,且只有单一图像类型(即临床或皮肤镜)。为了解决这个问题,我们开发并发布了黑色素瘤研究联盟基于人工智能的皮肤癌多模态图像数据集(MIDAS)数据集,该数据集是最大的公开可用、前瞻性招募、基于皮肤镜和临床图像的活检证实和皮肤病理学标记的皮肤病变配对数据集。我们使用之前发布的四种最先进的(SOTA)模型探讨了模型在真实病例中的性能,并比较了模型与临床医生的诊断性能。我们还使用与皮损不同距离拍摄的临床照片评估了算法性能,以评估其对不同诊断类别的影响。我们通过获得知情同意的 IRB 批准方案前瞻性地招募了 796 名患者,代表了 1290 个独特的病变和 3830 张总图像(包括在 15 厘米和 30 厘米距离处拍摄的皮肤镜和临床图像)。图像代表了普通皮肤科病变诊断的多样性,包括恶性、良性和炎症性病变,其中包括黑素细胞痣(22%;n=234)、浸润性皮肤黑素瘤(4%;n=46)和原位黑素瘤(4%;n=47)。在使用MIDAS数据集评估SOTA模型时,我们发现与之前公布的性能指标相比,所有模型的性能都有所下降,这表明目前的SOTA算法的通用性面临挑战。作为比较基线,进行活组织检查的皮肤科医生在区分恶性和良性病变时,其 Top-1 诊断的准确率为 79%。对于恶性病变,算法在 15 厘米距离采集的图像上比在 30 厘米距离采集的图像上表现更好,而皮肤镜图像比临床图像的灵敏度更高。随着人工智能诊断算法在临床上的广泛应用,提高我们对这些算法优缺点的认识至关重要。虽然许多算法可能会报告较高的性能指标,但由于可能会过度拟合局部数据集,因此应谨慎行事。MIDAS 强大、多模态和多样化的数据集让研究人员能够在我们的真实世界图像上评估算法,并更好地评估其通用性。
{"title":"Multimodal Image Dataset for AI-based Skin Cancer (MIDAS) Benchmarking","authors":"Albert S Chiou, Jesutofunmi A Omiye, Haiwen Gui, Susan M Swetter, Justin M Ko, Brian Gastman, Joshua Arbesman, Zhou Ran Cai, Olivier Gevaert, Chris Sadee, Veronica M Rotemberg, Seung Seog Han, Philipp Tschandl, Meghan Dickman, Elizabeth Bailey, Gordon H Bae, Philip Bailin, Jennifer Boldrick, Kiana Yekrang, Peter Caroline, Jackson Hanna, Nicholas R Kurtansky, Jochen Weber, Niki A See, Michelle Phung, Marianna Gallegos, Roxana Daneshjou, Roberto Novoa","doi":"10.1101/2024.06.27.24309562","DOIUrl":"https://doi.org/10.1101/2024.06.27.24309562","url":null,"abstract":"With an estimated 3 billion people globally lacking access to dermatological care, technological solutions leveraging artificial intelligence (AI) have been proposed to improve access. Diagnostic AI algorithms, however, require high-quality datasets to allow development and testing, particularly those that enable evaluation of both unimodal and multimodal approaches. Currently, the majority of dermatology AI algorithms are built and tested on proprietary, siloed data, often from a single site and with only a single image type (i.e., clinical or dermoscopic). To address this, we developed and released the Melanoma Research Alliance Multimodal Image Dataset for AI-based Skin Cancer (MIDAS) dataset, the largest publicly available, prospectively-recruited, paired dermoscopic- and clinical image-based dataset of biopsy-proven and dermatopathology-labeled skin lesions. We explored model performance on real-world cases using four previously published state-of-the-art (SOTA) models and compared model-to-clinician diagnostic performance. We also assessed algorithm performance using clinical photography taken at different distances from the lesion to assess its influence across diagnostic categories. We prospectively enrolled 796 patients through an IRB-approved protocol with informed consent representing 1290 unique lesions and 3830 total images (including dermoscopic and clinical images taken at 15-cm and 30-cm distance). Images represented the diagnostic diversity of lesions seen in general dermatology, with malignant, benign, and inflammatory lesions that included melanocytic nevi (22%; n=234), invasive cutaneous melanomas (4%; n=46), and melanoma in situ (4%; n=47). When evaluating SOTA models using the MIDAS dataset, we observed performance reduction across all models compared to their previously published performance metrics, indicating challenges to generalizability of current SOTA algorithms. As a comparative baseline, the dermatologists performing biopsies were 79% accurate with their top-1 diagnosis at differentiating a malignant from benign lesion. For malignant lesions, algorithms performed better on images acquired at 15-cm compared to 30-cm distance while dermoscopic images yielded higher sensitivity compared to clinical images. Improving our understanding of the strengths and weaknesses of AI diagnostic algorithms is critical as these tools advance towards widespread clinical deployment. While many algorithms may report high performance metrics, caution should be taken due to the potential for overfitting to localized datasets. MIDAS's robust, multimodal, and diverse dataset allows researchers to evaluate algorithms on our real-world images and better assess their generalizability.","PeriodicalId":501385,"journal":{"name":"medRxiv - Dermatology","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141505162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Assessment of Ultraviolet and Infrared Radiations Transmission in Automobile Windshields and Side Windows 汽车挡风玻璃和侧窗的紫外线和红外线辐射传输评估
Pub Date : 2024-05-28 DOI: 10.1101/2024.05.27.24307977
Nouf Jubran AlQahtani, Ghada Naje AlEssa, Hoor Fayez AlDushaishi, Amnah Nabil Bukair, Syed Mehmood Ali
Background Although exposure to solar radiation is beneficial for humans, too much of it can cause severe health conditions, including sunburn and skin cancer. The biological effects of solar radiation vary enormously with wavelength and exposure time. Ultraviolet and infrared radiations are the two main invisible components of solar radiation, causing skin damage. People are becoming more aware of the significance of sun protection, though little attention is directed to the exposure of the skin to UV and IR radiations through car windows. According to a survey of 1293 participants, mainly from Saudi Arabia, the fact that UV radiation can penetrate through car windows is known by the majority, i.e., 82%. However, the capability of IR radiation to penetrate vehicle windows is unknown to most people. Even though car windows reduce the transmission of ultraviolet and infrared rays, drivers are not isolated from them completely. To the best of our knowledge, this is the first study that measures solar exposure in cars in the middle east region, which is famous for its hot and arid (dry) climate with temperatures reaching over 52°C. Specifically, this study aimed to determine the driver exposure to UV and IR radiations in Dammam, Saudi Arabia, and emphasize the need to take the necessary measures to avoid exposure to these rays.
背景 虽然太阳辐射对人类有益,但过多的太阳辐射会导致严重的健康问题,包括晒伤和皮肤癌。太阳辐射对生物的影响因波长和照射时间的不同而有很大差异。紫外线和红外线是太阳辐射中两种主要的不可见成分,会对皮肤造成伤害。人们越来越意识到防晒的重要性,但却很少关注皮肤通过车窗暴露在紫外线和红外线辐射下的问题。一项针对 1293 名参与者(主要来自沙特阿拉伯)的调查显示,大多数人(82%)都知道紫外线辐射可以透过车窗。然而,大多数人都不知道红外辐射能够穿透车窗。尽管车窗可以减少紫外线和红外线的穿透,但驾驶员并不能完全与之隔绝。据我们所知,这是第一项测量中东地区车内太阳辐射的研究,中东地区以炎热和干旱(干燥)气候著称,气温高达 52°C 以上。具体而言,本研究旨在确定沙特阿拉伯达曼市驾驶员暴露于紫外线和红外线辐射的情况,并强调采取必要措施避免暴露于这些射线的必要性。
{"title":"Assessment of Ultraviolet and Infrared Radiations Transmission in Automobile Windshields and Side Windows","authors":"Nouf Jubran AlQahtani, Ghada Naje AlEssa, Hoor Fayez AlDushaishi, Amnah Nabil Bukair, Syed Mehmood Ali","doi":"10.1101/2024.05.27.24307977","DOIUrl":"https://doi.org/10.1101/2024.05.27.24307977","url":null,"abstract":"<strong>Background</strong> Although exposure to solar radiation is beneficial for humans, too much of it can cause severe health conditions, including sunburn and skin cancer. The biological effects of solar radiation vary enormously with wavelength and exposure time. Ultraviolet and infrared radiations are the two main invisible components of solar radiation, causing skin damage. People are becoming more aware of the significance of sun protection, though little attention is directed to the exposure of the skin to UV and IR radiations through car windows. According to a survey of 1293 participants, mainly from Saudi Arabia, the fact that UV radiation can penetrate through car windows is known by the majority, i.e., 82%. However, the capability of IR radiation to penetrate vehicle windows is unknown to most people. Even though car windows reduce the transmission of ultraviolet and infrared rays, drivers are not isolated from them completely. To the best of our knowledge, this is the first study that measures solar exposure in cars in the middle east region, which is famous for its hot and arid (dry) climate with temperatures reaching over 52°C. Specifically, this study aimed to determine the driver exposure to UV and IR radiations in Dammam, Saudi Arabia, and emphasize the need to take the necessary measures to avoid exposure to these rays.","PeriodicalId":501385,"journal":{"name":"medRxiv - Dermatology","volume":"44 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141189333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhancing Healthcare Accessibility: A Comprehensive Usability Study of Pathpoint® eDerma Software 提高医疗保健的无障碍性:Pathpoint® eDerma 软件的全面可用性研究
Pub Date : 2024-05-18 DOI: 10.1101/2024.05.17.24307401
Balamurugan Subramaniyan, Atlas Naqvi, Muna Mohamud, Piyush Mahapatra
This research presents a comprehensive usability evaluation of Pathpoint® eDerma Software, conducted in accordance with IEC 62366-1:2015 standards. The study encompasses four diverse user groups, that includes administrators, medical photographers, dermatologists, and patients, ensuring a holistic assessment of the software’s usability and effectiveness. Through a combination of quantitative metrics and qualitative feedback, the study explores various aspects such as accessibility, navigation, safety, and user satisfaction. Potential risks to user experience and patient data security are identified and addressed to ensure compliance with safety standards. The findings highlight the software’s effectiveness in facilitating remote assessments, streamlining workflows, and improving patient care. This research contributes valuable insights to the ongoing refinement and optimisation of eDerma Software, aiming to enhance its usability, safety, and overall effectiveness in real-world healthcare settings.
本研究根据 IEC 62366-1:2015 标准对 Pathpoint® eDerma 软件进行了全面的可用性评估。研究涵盖四个不同的用户群体,包括管理员、医学摄影师、皮肤科医生和患者,确保对软件的可用性和有效性进行全面评估。通过定量指标和定性反馈相结合的方法,该研究探讨了可访问性、导航、安全性和用户满意度等各个方面。研究还发现并解决了用户体验和患者数据安全方面的潜在风险,以确保符合安全标准。研究结果强调了该软件在促进远程评估、简化工作流程和改善患者护理方面的有效性。这项研究为 eDerma 软件的不断完善和优化提供了宝贵的见解,旨在提高其在实际医疗环境中的可用性、安全性和整体有效性。
{"title":"Enhancing Healthcare Accessibility: A Comprehensive Usability Study of Pathpoint® eDerma Software","authors":"Balamurugan Subramaniyan, Atlas Naqvi, Muna Mohamud, Piyush Mahapatra","doi":"10.1101/2024.05.17.24307401","DOIUrl":"https://doi.org/10.1101/2024.05.17.24307401","url":null,"abstract":"This research presents a comprehensive usability evaluation of Pathpoint® eDerma Software, conducted in accordance with IEC 62366-1:2015 standards. The study encompasses four diverse user groups, that includes administrators, medical photographers, dermatologists, and patients, ensuring a holistic assessment of the software’s usability and effectiveness. Through a combination of quantitative metrics and qualitative feedback, the study explores various aspects such as accessibility, navigation, safety, and user satisfaction. Potential risks to user experience and patient data security are identified and addressed to ensure compliance with safety standards. The findings highlight the software’s effectiveness in facilitating remote assessments, streamlining workflows, and improving patient care. This research contributes valuable insights to the ongoing refinement and optimisation of eDerma Software, aiming to enhance its usability, safety, and overall effectiveness in real-world healthcare settings.","PeriodicalId":501385,"journal":{"name":"medRxiv - Dermatology","volume":"220 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141152149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
medRxiv - Dermatology
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1