Dataset Information

Augmenting the accuracy of trainee doctors in diagnosing skin lesions suspected of skin neoplasms in a real-world setting: A prospective controlled before-and-after study.

ABSTRACT:

Background

Although deep neural networks have shown promising results in the diagnosis of skin cancer, a prospective evaluation in a real-world setting could confirm these results. This study aimed to evaluate whether an algorithm (http://b2019.modelderm.com) improves the accuracy of nondermatologists in diagnosing skin neoplasms.

Methods

A total of 285 cases (random series) with skin neoplasms suspected of malignancy by either physicians or patients were recruited in two tertiary care centers located in South Korea. An artificial intelligence (AI) group (144 cases, mean [SD] age, 57.0 [17.7] years; 62 [43.1%] men) was diagnosed via routine examination with photographic review and assistance by the algorithm, whereas the control group (141 cases, mean [SD] age, 61.0 [15.3] years; 52 [36.9%] men) was diagnosed only via routine examination with a photographic review. The accuracy of the nondermatologists before and after the interventions was compared.

Results

Among the AI group, the accuracy of the first impression (Top-1 accuracy; 58.3%) after the assistance of AI was higher than that before the assistance (46.5%, P = .008). The number of differential diagnoses of the participants increased from 1.9 ± 0.5 to 2.2 ± 0.6 after the assistance (P < .001). In the control group, the difference in the Top-1 accuracy between before and after reviewing photographs was not significant (before, 46.1%; after, 51.8%; P = .19), and the number of differential diagnoses did not significantly increase (before, 2.0 ± 0.4; after, 2.1 ± 0.5; P = .57).

Conclusions

In real-world settings, AI augmented the diagnostic accuracy of trainee doctors. The limitation of this study is that the algorithm was tested only for Asians recruited from a single region. Additional international randomized controlled trials involving various ethnicities are required.

SUBMITTER: Kim YJ

PROVIDER: S-EPMC8782525 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Augmenting the accuracy of trainee doctors in diagnosing skin lesions suspected of skin neoplasms in a real-world setting: A prospective controlled before-and-after study.

Kim Young Jae YJ Na Jung-Im JI Han Seung Seog SS Won Chong Hyun CH Lee Mi Woo MW Shin Jung-Won JW Huh Chang-Hun CH Chang Sung Eun SE

PloS one 20220121 1

<h4>Background</h4>Although deep neural networks have shown promising results in the diagnosis of skin cancer, a prospective evaluation in a real-world setting could confirm these results. This study aimed to evaluate whether an algorithm (http://b2019.modelderm.com) improves the accuracy of nondermatologists in diagnosing skin neoplasms.<h4>Methods</h4>A total of 285 cases (random series) with skin neoplasms suspected of malignancy by either physicians or patients were recruited in two tertiary ...[more]

PMID: 35061692

Similar Datasets

Project description:In recent years, computerized biomedical imaging and analysis have become extremely promising, more interesting, and highly beneficial. They provide remarkable information in the diagnoses of skin lesions. There have been developments in modern diagnostic systems that can help detect melanoma in its early stages to save the lives of many people. There is also a significant growth in the design of computer-aided diagnosis (CAD) systems using advanced artificial intelligence. The purpose of the present research is to develop a system to diagnose skin cancer, one that will lead to a high level of detection of the skin cancer. The proposed system was developed using deep learning and traditional artificial intelligence machine learning algorithms. The dermoscopy images were collected from the PH2 and ISIC 2018 in order to examine the diagnose system. The developed system is divided into feature-based and deep leaning. The feature-based system was developed based on feature-extracting methods. In order to segment the lesion from dermoscopy images, the active contour method was proposed. These skin lesions were processed using hybrid feature extractions, namely, the Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) methods to extract the texture features. The obtained features were then processed using the artificial neural network (ANNs) algorithm. In the second system, the convolutional neural network (CNNs) algorithm was applied for the efficient classification of skin diseases; the CNNs were pretrained using large AlexNet and ResNet50 transfer learning models. The experimental results show that the proposed method outperformed the state-of-art methods for HP2 and ISIC 2018 datasets. Standard evaluation metrics like accuracy, specificity, sensitivity, precision, recall, and F-score were employed to evaluate the results of the two proposed systems. The ANN model achieved the highest accuracy for PH2 (97.50%) and ISIC 2018 (98.35%) compared with the CNN model. The evaluation and comparison, proposed systems for classification and detection of melanoma are presented.

Project description:IntroductionWorkplace bullying (WPB) among trainee doctors is a concerning problem in Malaysia. However, there is still limited understanding regarding the influence of trainee doctors' personality traits on WPB. Furthermore, the impact of contract employment status on WPB among trainee doctors is not yet well-defined. To address these gaps, this study was aimed to determine the prevalence of WPB among trainee doctors and to examine the association of sociodemographic characteristics, job characteristics, and personality traits with WPB among trainee doctors in Malaysia.MethodsA multi-center cross-sectional study was conducted with 264 trainee doctors in Selangor, Malaysia. Eligible participants were provided with sociodemographic characteristics questionnaire, job characteristics questionnaire, WPB questionnaire, and the Big Five Inventory-10 (BFI-10). Chi-square tests were used to examine the association between: (i) sociodemographic characteristics and WPB, (ii) job characteristics and WPB; and (iii) personality traits and WPB. Multivariate logistic regression was performed to evaluate the association between the significant independent variables (as determined from Chi-square tests) and WPB.ResultsThe prevalence of WPB was 45.1 %, with verbal abuse being the most common form of bullying (46.2 %). Chi-square test showed that only marital status and low agreeableness were significantly associated with WPB. Subsequently, multiple logistic regression demonstrated that being married (OR: 1.866; 95 % CI: 1.077-3.234) and low agreeableness (OR: 2.287; 95 % CI: 1.169-4.473) were significant predictors of WPB.ConclusionThe high prevalence of WPB among trainee doctors could be attributed by marriage and low agreeableness personality traits in this population. In order to minimise WPB and maximise workforce potential, it is essential for healthcare institutions and medical training programmes to recognise this vulnerabilities and take steps to protect and support trainee doctors who are married and/or with low agreeableness personality trait.

Project description:BackgroundThe amount of information needed by doctors has exploded. The nature of knowledge (explicit and tacit) and processes of knowledge acquisition and participation are complex. Aiming to assist workplace learning, Wales Deanery funded "iDoc", a project offering trainee doctors a Smartphone library of medical textbooks.MethodsData on trainee doctors' (Foundation Year 2) workplace information seeking practice was collected by questionnaire in 2011 (n = 260). iDoc baseline questionnaires (n = 193) collected data on Smartphone usage alongside other workplace information sources. Case reports (n = 117) detail specific instances of Smartphone use.ResultsMost frequently (daily) used information sources in the workplace: senior medical staff (80% F2 survey; 79% iDoc baseline); peers (70%; 58%); and other medical/nursing team staff (53% both datasets). Smartphones were used more frequently by males (p < 0.01). Foundation Year 1 (newly qualified) was judged the most useful time to have a Smartphone library because of increased responsibility and lack of knowledge/experience.Preferred information source varied by question type: hard copy texts for information-based questions; varied resources for skills queries; and seniors for more complex problems. Case reports showed mobile technology used for simple (information-based), complex (problem-based) clinical questions and clinical procedures (skills-based scenarios). From thematic analysis, the Smartphone library assisted: teaching and learning from observation; transition from medical student to new doctor; trainee doctors' discussions with seniors; independent practice; patient care; and this 'just-in-time' access to reliable information supported confident and efficient decision-making.ConclusionA variety of information sources are used regularly in the workplace. Colleagues are used daily but seniors are not always available. During transitions, constant access to the electronic library was valued. It helped prepare trainee doctors for discussions with their seniors, assisting the interchange between explicit and tacit knowledge.By supporting accurate prescribing and treatment planning, the electronic library contributed to enhanced patient care. Trainees were more rapidly able to medicate patients to reduce pain and more quickly call for specific assessments. However, clinical decision-making often requires dialogue: what Smartphone technology can do is augment, not replace, discussion with their colleagues in the community of practice.

Dataset Information

Augmenting the accuracy of trainee doctors in diagnosing skin lesions suspected of skin neoplasms in a real-world setting: A prospective controlled before-and-after study.

Background

Methods

Results

Conclusions

Publications

Augmenting the accuracy of trainee doctors in diagnosing skin lesions suspected of skin neoplasms in a real-world setting: A prospective controlled before-and-after study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets