Diagnostic capacity of skin tumor artificial intelligence-assisted decision-making software in real-world clinical settings

Background:Youzhi artificial intelligence(AI)software is the AI-assisted decision-making system for diagnosing skin tumors.The high diagnostic accuracy of Youzhi AI software was previously validated in specific datasets.The objective of this study was to compare the performance of diagnostic capacity between Youzhi AI software and dermatologists in real-world clinical settings.Methods:A total of 106 patients who underwent skin tumor resection in the Dermatology Department of China-Japan Friendship Hospital from July 2017 to June 2019 and were confirmed as skin tumors by pathological biopsy were selected.Dermoscopy and clinical images of 106 patients were diagnosed by Youzhi AI software and dermatologists at different dermoscopy diagnostic levels.The primary outcome was to compare the diagnostic accuracy of the Youzhi AI software with that of dermatologists and that measured in the laboratory using specific data sets.The secondary results included the sensitivity,specificity,positive predictive value,negative predictive value,F-measure,and Matthews correlation coefficient of Youzhi AI software in the real-world.Results:The diagnostic accuracy of Youzhi AI software in real-world clinical settings was lower than that of the laboratory data(P<0.001).The output result of Youzhi AI software has good stability after several tests.Youzhi AI software diagnosed benign and malignant diseases by recognizing dermoscopic images and diagnosed disease types with higher diagnostic accuracy than by recognizing clinical images(P=0.008,P=0.016,respectively).Compared with dermatologists,Youzhi AI software was more accurate in the diagnosis of skin tumor types through the recognition of dermoscopic images(P=0.01).By evaluating the diagnostic performance of dermatologists under different modes,the diagnostic accuracy of dermatologists in diagnosing disease types by matching dermoscopic and clinical images was significantly higher than that by identifying dermoscopic and clinical images in random sequence(P=0.022).The diagnostic accuracy of dermatologists in the diagnosis of benign and malignant diseases by recognizing dermoscopic images was significantly higher than that by recognizing clinical images(P=0.010).Conclusion:The diagnostic accuracy of Youzhi AI software for skin tumors in real-world clinical settings was not as high as that of using special data sets in the laboratory.However,there was no significant difference between the diagnostic capacity of Youzhi AI software and the average diagnostic capacity of dermatologists.It can provide assistant diagnostic decisions for dermatologists in the current state.

Skin diseases in the Da Qing Diabetes Study:a cross-sectional study

Background:The prevalence of skin diseases and diabetes mellitus(DM)are prominent around the world.The current scope of knowledge regarding the prevalence of skin diseases and comorbidities with type 2 DM(T2DM)is limited,leading to limited recognition of the correlations between skin diseases and T2DM.Methods:We collected 383 subjects from the Da Qing Diabetes Study during the period from July 9th to September 1st,2016.The subjects were categorized into three groups:Normal glucose tolerance(NGT),impaired glucose tolerance(IGT),and T2DM.The prevalence and clinical characteristics of skin diseases were recorded and investigated.Results:In this cross-sectional study,383 individuals with ages ranging from 53 to 89-year-old were recruited.The overall prevalence of skin diseases was 93.5%,and 75.7%of individuals had two or more kinds of skin diseases.Additionally,there were 47 kinds of comorbid skin diseases in patients with T2DM,of which eight kinds of skin diseases had a prevalence>10%.The prevalence of skin diseases in NGT,IGT,and T2DM groups were 93.3%,91.5%,and 96.6%,respectively;stratified analysis by categories showed a statistically significant difference in"disturbances of pigmentation"and"neurological and psychogenic dermatoses".The duration of T2DM also significantly associated with the prevalence of"disturbances of pigmentation"and"neurological and psychogenic dermatoses".Subsequently,the prevalence of"disturbances of pigmentation"was higher in males than females in NGT(P<0.01)and T2DM(P<0.01)groups.In addition,the difference in the prevalence of"disturbances of pigmentation"was also significant in NGT and T2DM groups(P<0.01).Conclusions:There was a high prevalence of skin diseases in the Da Qing Diabetes Study.To address the skin diseases in the Da Qing Diabetes Study,increased awareness and intervention measures should be implemented.

Accuracy of dermoscopic and reflectance confocal microscopic criteria for diagnosis of psoriasis

To the Editor:Psoriasis is a chronic inflammatory disease that is usually diagnosed on the basis of typical clinical features.However,ambiguous cases can exist at times and are sometimes mistaken for other erythematosquamous diseases.Although histopathologic diagnosis remains the gold standard in such cases,it is frequently bypassed to avoid damage to the lesion areas and reduce discomfort for patients.Because a biopsy cannot provide real-time monitoring,non-invasive techniques that are cost-effective,such as dermoscopy and reflectance confocal microscopy(RCM),have increasingly been used in clinical practice during the past few years.

Diagnostic value of dermoscopy combined with reflectance confocal microscopy for clinically equivocal blue nevus

Blue nevus(BN)is a benign,acquired pigmented lesion characterized by a bluish or dark-bluish pigmentation.Most lesions are benign and stable over time,sometimes developing into malignant blue nevus(MBN),a variant of malignant melanoma.The prognosis in MBN is at least as serious as in conventional melanoma.[1]Additionally,a differential diagnosis of BN including nodular melanoma,pigmented basal cell carcinoma,and cutaneous metastasis of melanoma may lead to excessive surgical excisions.

Present status and prospect of skin imaging equipment in some public hospitals in China

To the Editor:The continuous development and maturity of imaging science and technology have made skin imaging one of the essential subspecialties of dermatology.This has had an objective and comprehensive impact in changing the dermatology diagnosis mode.Thus,skin imaging has become one of the diagnostic skills that all dermatologists must master.Skin imaging equipment plays a crucial role in clinical and scientific research.It is not only a necessary aid to correct diagnose of skin diseases,but also a crucial link and hardware foundation for skin imaging capacity strengthening.Dermoscopy,reflectance confocal microscopy(RCM)and very high frequency(VHF)skin ultrasound imaging diagnostic system(VHF skin ultra-sound)have become skin imaging equipments commonly used in Chinese dermatological practice.In recent years,with the growing emphasis on dermatology in hospitals at all levels,investment in medical equipment has been increasing and skin imaging equipment has been continuously optimized.As far as we know,there is no literature report on the skin imaging equipment current status in Chinese public hospitals.This study intended to investigate and analyze the current status of skin imaging equipment in the country,and to provide an objective basis for further standardizing and strengthening the development of skin imaging equipment and dermatology construction.In this way,it is expected to lay the foundations to meet clinical needs and achieve the optimal allocation of medical resources.