Artificial intelligence and machine learning algorithms for early detection of skin cancer in community and primary care settings: a systematic review

A Narrative Review: Opportunities and Challenges in Artificial Intelligence Skin Image Analyses Using Total Body Photography

Artificial intelligence (AI) algorithms for skin lesion classification have reported accuracy at par with and even outperformance of expert dermatologists in experimental settings. However, the majority of algorithms do not represent real-world clinical approach where skin phenotype and clinical background information are considered. We review the current state of AI for skin lesion classification and present opportunities and challenges when applied to total body photography (TBP). AI in TBP analysis presents opportunities for intrapatient assessment of skin phenotype and holistic risk assessment by incorporating patient-level metadata, although challenges exist for protecting patient privacy in algorithm development and improving explainable AI methods.

"Notification! You May Have Cancer." Could Smartphones and Wearables Help Detect Cancer Early?

This viewpoint paper considers the authors' perspectives on the potential role of smartphones, wearables, and other technologies in the diagnosis of cancer. We believe that these technologies could be valuable additions in the pursuit of early cancer diagnosis, as they offer solutions to the timely detection of signals or symptoms and monitoring of subtle changes in behavior that may otherwise be missed. In addition to signal detection, technologies could assist symptom interpretation and guide and facilitate access to health care. This paper aims to provide an overview of the scientific rationale as to why these technologies could be valuable for early cancer detection, as well as outline the next steps for research and development to drive investigation into the potential for smartphones and wearables in this context and optimize implementation. We draw attention to potential barriers to successful implementation, including the difficulty of the development of signals and sensors with sufficient utility and accuracy through robust research with the target group. There are regulatory challenges; the potential for innovations to exacerbate inequalities; and questions surrounding acceptability, uptake, and correct use by the intended target group and health care practitioners. Finally, there is potential for unintended consequences on individuals and health care services including unnecessary anxiety, increased symptom burden, overinvestigation, and inappropriate use of health care resources.

A systematic review and meta-analysis of artificial intelligence versus clinicians for skin cancer diagnosis

Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance.

Examining labelling guidelines for AI-based software as a medical device: A review and analysis of dermatology mobile applications in Australia

In recent years, there has been a surge in the development of AI-based Software as a Medical Device (SaMD), particularly in visual specialties such as dermatology. In Australia, the Therapeutic Goods Administration (TGA) regulates AI-based SaMD to ensure its safe use. Proper labelling of these devices is crucial to ensure that healthcare professionals and the general public understand how to use them and interpret results accurately. However, guidelines for labelling AI-based SaMD in dermatology are lacking, which may result in products failing to provide essential information about algorithm development and performance metrics. This review examines existing labelling guidelines for AI-based SaMD across visual medical specialties, with a specific focus on dermatology. Common recommendations for labelling are identified and applied to currently available dermatology AI-based SaMD mobile applications to determine usage of these labels. Of the 21 AI-based SaMD mobile applications identified, none fully comply with common labelling recommendations. Results highlight the need for standardized labelling guidelines. Ensuring transparency and accessibility of information is essential for the safe integration of AI into health care and preventing potential risks associated with inaccurate clinical decisions.

Predicting systemic diseases in fundus images: systematic review of setting, reporting, bias, and models' clinical availability in deep learning studies

BACKGROUND

Analyzing fundus images with deep learning techniques is promising for screening systematic diseases. However, the quality of the rapidly increasing number of studies was variable and lacked systematic evaluation.

OBJECTIVE

To systematically review all the articles that aimed to predict systemic parameters and conditions using fundus image and deep learning, assessing their performance, and providing suggestions that would enable translation into clinical practice.

METHODS

Two major electronic databases (MEDLINE and EMBASE) were searched until August 22, 2023, with keywords 'deep learning' and 'fundus'. Studies using deep learning and fundus images to predict systematic parameters were included, and assessed in four aspects: study characteristics, transparent reporting, risk of bias, and clinical availability. Transparent reporting was assessed by the TRIPOD statement, while the risk of bias was assessed by PROBAST.

RESULTS

4969 articles were identified through systematic research. Thirty-one articles were included in the review. A variety of vascular and non-vascular diseases can be predicted by fundus images, including diabetes and related diseases (19%), sex (22%) and age (19%). Most of the studies focused on developed countries. The models' reporting was insufficient in determining sample size and missing data treatment according to the TRIPOD. Full access to datasets and code was also under-reported. 1/31(3.2%) study was classified as having a low risk of bias overall, whereas 30/31(96.8%) were classified as having a high risk of bias according to the PROBAST. 5/31(16.1%) of studies used prospective external validation cohorts. Only two (6.4%) described the study's calibration. The number of publications by year increased significantly from 2018 to 2023. However, only two models (6.5%) were applied to the device, and no model has been applied in clinical.

CONCLUSION

Deep learning fundus images have shown great potential in predicting systematic conditions in clinical situations. Further work needs to be done to improve the methodology and clinical application.

Reporting guidelines in medical artificial intelligence: a systematic review and meta-analysis

BACKGROUND

The field of Artificial Intelligence (AI) holds transformative potential in medicine. However, the lack of universal reporting guidelines poses challenges in ensuring the validity and reproducibility of published research studies in this field.

METHODS

Based on a systematic review of academic publications and reporting standards demanded by both international consortia and regulatory stakeholders as well as leading journals in the fields of medicine and medical informatics, 26 reporting guidelines published between 2009 and 2023 were included in this analysis. Guidelines were stratified by breadth (general or specific to medical fields), underlying consensus quality, and target research phase (preclinical, translational, clinical) and subsequently analyzed regarding the overlap and variations in guideline items.

RESULTS

AI reporting guidelines for medical research vary with respect to the quality of the underlying consensus process, breadth, and target research phase. Some guideline items such as reporting of study design and model performance recur across guidelines, whereas other items are specific to particular fields and research stages.

CONCLUSIONS

Our analysis highlights the importance of reporting guidelines in clinical AI research and underscores the need for common standards that address the identified variations and gaps in current guidelines. Overall, this comprehensive overview could help researchers and public stakeholders reinforce quality standards for increased reliability, reproducibility, clinical validity, and public trust in AI research in healthcare. This could facilitate the safe, effective, and ethical translation of AI methods into clinical applications that will ultimately improve patient outcomes.

Performance of Commercial Dermatoscopic Systems That Incorporate Artificial Intelligence for the Identification of Melanoma in General Practice: A Systematic Review

BACKGROUND

Cutaneous melanoma remains an increasing global public health burden, particularly in fair-skinned populations. Advancing technologies, particularly artificial intelligence (AI), may provide an additional tool for clinicians to help detect malignancies with a more accurate success rate. This systematic review aimed to report the performance metrics of commercially available convolutional neural networks (CNNs) tasked with detecting MM.

METHODS

A systematic literature search was performed using CINAHL, Medline, Scopus, ScienceDirect and Web of Science databases.

RESULTS

A total of 16 articles reporting MM were included in this review. The combined number of melanomas detected was 1160, and non-melanoma lesions were 33,010. The performance of market-approved technology and clinician performance for classifying melanoma was highly heterogeneous, with sensitivity ranging from 16.4 to 100.0%, specificity between 40.0 and 98.3% and accuracy between 44.0 and 92.0%. Less heterogeneity was observed when clinicians worked in unison with AI, with sensitivity ranging between 83.3 and 100.0%, specificity between 83.7 and 87.3%, and accuracy between 86.4 and 86.9%.

CONCLUSION

Instead of focusing on the performance of AI versus clinicians for classifying melanoma, more consistent performance has been obtained when clinicians' work is supported by AI, facilitating management decisions and improving health outcomes.

Prognostic and immunotherapeutic potential of regulatory T cell-associated signature in ovarian cancer

Tumour-induced immunosuppressive microenvironments facilitate oncogenesis, with regulatory T cells (Tregs) serving as a crucial component. The significance of Treg-associated genes within the context of ovarian cancer (OC) remains elucidated insufficiently. Utilizing single-cell RNA sequencing (scRNA-Seq) for the identification of Treg-specific biomarkers, this investigation employed single-sample gene set enrichment analysis (ssGSEA) for the derivation of a Treg signature score. Weighted gene co-expression network analysis (WGCNA) facilitated the identification of Treg-correlated genes. Machine learning algorithms were employed to determine an optimal prognostic model, subsequently exploring disparities across risk strata in terms of survival outcomes, immunological infiltration, pathway activation and responsiveness to immunotherapy. Through WGCNA, a cohort of 365 Treg-associated genes was discerned, with 70 implicated in the prognostication of OC. A Tregs-associated signature (TAS), synthesized from random survival forest (RSF) and Least Absolute Shrinkage and Selection Operator (LASSO) algorithms, exhibited robust predictive validity across both internal and external cohorts. Low TAS OC patients demonstrated superior survival outcomes, augmented by increased immunological cell infiltration, upregulated immune checkpoint expression, distinct pathway enrichment and differential response to immunotherapeutic interventions. The devised TAS proficiently prognosticates patient outcomes and delineates the immunological milieu within OC, offering a strategic instrument for the clinical stratification and selection of patients.

Transparent medical image AI via an image-text foundation model grounded in medical literature

Building trustworthy and transparent image-based medical artificial intelligence (AI) systems requires the ability to interrogate data and models at all stages of the development pipeline, from training models to post-deployment monitoring. Ideally, the data and associated AI systems could be described using terms already familiar to physicians, but this requires medical datasets densely annotated with semantically meaningful concepts. In the present study, we present a foundation model approach, named MONET (medical concept retriever), which learns how to connect medical images with text and densely scores images on concept presence to enable important tasks in medical AI development and deployment such as data auditing, model auditing and model interpretation. Dermatology provides a demanding use case for the versatility of MONET, due to the heterogeneity in diseases, skin tones and imaging modalities. We trained MONET based on 105,550 dermatological images paired with natural language descriptions from a large collection of medical literature. MONET can accurately annotate concepts across dermatology images as verified by board-certified dermatologists, competitively with supervised models built on previously concept-annotated dermatology datasets of clinical images. We demonstrate how MONET enables AI transparency across the entire AI system development pipeline, from building inherently interpretable models to dataset and model auditing, including a case study dissecting the results of an AI clinical trial.

Optimizing time prediction and error classification in early melanoma detection using a hybrid RCNN-LSTM model

Skin cancer is a terrifying disorder that affects all individuals. Due to the significant increase in the rate of melanoma skin cancer, early detection of skin cancer is now more critical than ever before. Malignant melanoma is one of the most serious forms of skin cancer, and it is caused by abnormal melanocyte cell growth. In recent years, skin cancer predictive categorization has become more accurate and predictive due to multiple deep learning algorithms. Malignant melanoma is diagnosed using the Recurrent Convolution Neural Network-Long Short-Term Memory (RCNN-LSTM), which is one of the deep learning classification approaches. Using the International Skin Image Collection and the RCNN-LSTM, the data are categorized and analyzed to gain a better understanding of skin cancer. The method begins with data preprocessing, which prepares the dataset for classification. Additionally, the RCNN is employed to extract the features that are vital to the prediction process. The LSTM is accountable for the final step, classification. There are further factors to examine, such as the precision of 94.60%, the sensitivity of 95.67%, and the F1-score of 95.13%. Other benefits of the suggested study include shorter prediction durations of 95.314, 122.530, and 131.205 s and lower model loss of 0.25%, 0.19%, and 0.15% for input sizes 10, 15, and 20, respectively. Three datasets had a reduced categorization error of 5.11% and an accuracy of 95.42%. In comparison to previous approaches, the work discussed here produces superior outcomes. RESEARCH HIGHLIGHTS: Recurrent convolutional neural network (RCNN) deep learning approach for optimizing time prediction and error classification in early melanoma detection. It extracts a high number of specific features from the skin disease image, making the classification process easier and more accurate. To reduce classification errors in accurately detecting melanoma, context dependency is considered in this work. By accounting for context dependency, the deprivation state is avoided, preventing performance degradation in the model. To minimize melanoma detection model loss, a skin disease image augmentation or regularization process is performed in this work. This strategy improves the accuracy of the model when applied to fresh, previously unobserved data.

Symptomatic presentation of cancer in primary care: a scoping review of patients' experiences and needs during the cancer diagnostic pathway

OBJECTIVES

The objective was to map the experiences and needs of patients presenting with symptoms of suspected cancer in the primary care interval (from when they first present to primary care to their first appointment or referral to a secondary or tertiary level healthcare facility).

DESIGN

This was a scoping review.

INCLUSION CRITERIA

Studies or reports written in English which included primary data on the primary care interval experiences and/or needs of adult patients presenting with new symptoms of suspected cancer were eligible. Studies which only included patients with secondary or recurring cancer, conference abstracts and reviews were excluded. No date limits were applied.

METHODS

The Joanna Briggs Institute method for Scoping Reviews guided screening, report selection and data extraction. At least two independent reviewers contributed to each stage. Medline, CINAHL, PsychInfo, Embase and Web of Science were searched and several grey literature resources. Relevant quantitative findings were qualitised and integrated with qualitative findings. A thematic analysis was carried out.

RESULTS

Of the 4855 records identified in the database search, 18 were included in the review, along with 13 identified from other sources. The 31 included studies were published between 2002 and 2023 and most (n=17) were conducted in the UK. Twenty subthemes across four themes (patient experience, interpersonal, healthcare professional (HCP) skills, organisational) were identified. No studies included patient-reported outcome measures. Patients wanted (1) to feel heard and understood by HCPs, (2) a plan to establish what was causing their symptoms, and (3) information about the next stages of the diagnostic process.

CONCLUSIONS

Scoping review findings can contribute to service planning as the cancer diagnostic pathway for symptomatic presentation of cancer evolves. The effectiveness of this pathway should be evaluated not only in terms of clinical outcomes, but also patient-reported outcomes and experience, along with the perspectives of primary care HCPs.

DVFNet: A deep feature fusion-based model for the multiclassification of skin cancer utilizing dermoscopy images

Skin cancer is a common cancer affecting millions of people annually. Skin cells inside the body that grow in unusual patterns are a sign of this invasive disease. The cells then spread to other organs and tissues through the lymph nodes and destroy them. Lifestyle changes and increased solar exposure contribute to the rise in the incidence of skin cancer. Early identification and staging are essential due to the high mortality rate associated with skin cancer. In this study, we presented a deep learning-based method named DVFNet for the detection of skin cancer from dermoscopy images. To detect skin cancer images are pre-processed using anisotropic diffusion methods to remove artifacts and noise which enhances the quality of images. A combination of the VGG19 architecture and the Histogram of Oriented Gradients (HOG) is used in this research for discriminative feature extraction. SMOTE Tomek is used to resolve the problem of imbalanced images in the multiple classes of the publicly available ISIC 2019 dataset. This study utilizes segmentation to pinpoint areas of significantly damaged skin cells. A feature vector map is created by combining the features of HOG and VGG19. Multiclassification is accomplished by CNN using feature vector maps. DVFNet achieves an accuracy of 98.32% on the ISIC 2019 dataset. Analysis of variance (ANOVA) statistical test is used to validate the model's accuracy. Healthcare experts utilize the DVFNet model to detect skin cancer at an early clinical stage.

Artificial intelligence and skin cancer

Artificial intelligence is poised to rapidly reshape many fields, including that of skin cancer screening and diagnosis, both as a disruptive and assistive technology. Together with the collection and availability of large medical data sets, artificial intelligence will become a powerful tool that can be leveraged by physicians in their diagnoses and treatment plans for patients. This comprehensive review focuses on current progress toward AI applications for patients, primary care providers, dermatologists, and dermatopathologists, explores the diverse applications of image and molecular processing for skin cancer, and highlights AI's potential for patient self-screening and improving diagnostic accuracy for non-dermatologists. We additionally delve into the challenges and barriers to clinical implementation, paths forward for implementation and areas of active research.

Review of the application of the most current sophisticated image processing methods for the skin cancer diagnostics purposes

This paper presents the most current and innovative solutions applying modern digital image processing methods for the purpose of skin cancer diagnostics. Skin cancer is one of the most common types of cancers. It is said that in the USA only, one in five people will develop skin cancer and this trend is constantly increasing. Implementation of new, non-invasive methods plays a crucial role in both identification and prevention of skin cancer occurrence. Early diagnosis and treatment are needed in order to decrease the number of deaths due to this disease. This paper also contains some information regarding the most common skin cancer types, mortality and epidemiological data for Poland, Europe, Canada and the USA. It also covers the most efficient and modern image recognition methods based on the artificial intelligence applied currently for diagnostics purposes. In this work, both professional, sophisticated as well as inexpensive solutions were presented. This paper is a review paper and covers the period of 2017 and 2022 when it comes to solutions and statistics. The authors decided to focus on the latest data, mostly due to the rapid technology development and increased number of new methods, which positively affects diagnosis and prognosis.

Complications Following Body Contouring: Performance Validation of Bard, a Novel AI Large Language Model, in Triaging and Managing Postoperative Patient Concerns

INTRODUCTION

Large language models (LLM) have revolutionized the way humans interact with artificial intelligence (AI) technology, with marked potential for applications in esthetic surgery. The present study evaluates the performance of Bard, a novel LLM, in identifying and managing postoperative patient concerns for complications following body contouring surgery.

METHODS

The American Society of Plastic Surgeons' website was queried to identify and simulate all potential postoperative complications following body contouring across different acuities and severity. Bard's accuracy was assessed in providing a differential diagnosis, soliciting a history, suggesting a most-likely diagnosis, appropriate disposition, treatments/interventions to begin from home, and red-flag signs/symptoms indicating deterioration, or requiring urgent emergency department (ED) presentation.

RESULTS

Twenty-two simulated body contouring complications were examined. Overall, Bard demonstrated a 59% accuracy in listing relevant diagnoses on its differentials, with a 52% incidence of incorrect or misleading diagnoses. Following history-taking, Bard demonstrated an overall accuracy of 44% in identifying the most-likely diagnosis, and a 55% accuracy in suggesting the indicated medical dispositions. Helpful treatments/interventions to begin from home were suggested with a 40% accuracy, whereas red-flag signs/symptoms, indicating deterioration, were shared with a 48% accuracy. A detailed analysis of performance, stratified according to latency of postoperative presentation (<48hours, 48hours-1month, or >1month postoperatively), and according to acuity and indicated medical disposition, is presented herein.

CONCLUSIONS

Despite promising potential of LLMs and AI in healthcare-related applications, Bard's performance in the present study significantly falls short of accepted clinical standards, thus indicating a need for further research and development prior to adoption.

LEVEL OF EVIDENCE IV

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Artificial Intelligence in Skin Cancer Diagnosis: A Reality Check

The field of skin cancer detection offers a compelling use case for the application of artificial intelligence (AI) within the realm of image-based diagnostic medicine. Through the analysis of large datasets, AI algorithms have the capacity to classify clinical or dermoscopic images with remarkable accuracy. Although these AI-based applications can operate both autonomously and under human supervision, the best results are achieved through a collaborative approach that leverages the expertise of both AI and human experts. However, it is important to note that most studies focus on assessing the diagnostic accuracy of AI in artificial settings rather than in real-world scenarios. Consequently, the practical utility of AI-assisted diagnosis in a clinical environment is still largely unknown. Furthermore, there exists a knowledge gap concerning the optimal use cases and deployment settings for these AI systems as well as the practical challenges that may arise from widespread implementation. This review explores the advantages and limitations of AI in a variety of real-world contexts, with a specific focus on its value to consumers, general practitioners, and dermatologists.

The State of Artificial Intelligence in Skin Cancer Publications

BACKGROUND

Artificial intelligence (AI) in skin cancer is a promising research field to assist physicians and to provide support to patients remotely. Physicians' awareness to new developments in AI research is important to define the best practices and scope of integrating AI-enabled technologies within a clinical setting.

OBJECTIVES

To analyze the characteristics and trends of AI skin cancer publications from dermatology journals.

METHODS

AI skin cancer publications were retrieved in June 2022 from the Web of Science. Publications were screened by title, abstract, and keywords to assess eligibility. Publications were fully reviewed. Publications were divided between nonmelanoma skin cancer (NMSC), melanoma, and skin cancer studies. The primary measured outcome was the number of citations. The secondary measured outcomes were articles' general characteristics and features related to AI.

RESULTS

A total of 168 articles were included: 25 on NMSC, 77 on melanoma, and 66 on skin cancer. The most common types of skin cancers were melanoma (134, 79.8%), basal cell carcinoma (61, 36.3%), and squamous cell carcinoma (45, 26.9%). All articles were published between 2000 and 2022, with 49 (29.2%) of them being published in 2021. Original studies that developed or assessed an algorithm predominantly used supervised learning (66, 97.0%) and deep neural networks (42, 67.7%). The most used imaging modalities were standard dermoscopy (76, 45.2%) and clinical images (39, 23.2%).

CONCLUSIONS

Most publications focused on developing or assessing screening technologies with mainly deep neural network algorithms. This indicates the eminent need for dermatologists to label or annotate images used by novel AI systems.

Patient-derived melanoma models

Melanoma is a very aggressive, rapidly metastasizing tumor that has been studied intensively in the past regarding the underlying genetic and molecular mechanisms. More recently developed treatment modalities have improved response rates and overall survival of patients. However, the majority of patients suffer from secondary treatment resistance, which requires in depth analyses of the underlying mechanisms. Here, melanoma models based on patients-derived material may play an important role. Consequently, a plethora of different experimental techniques have been developed in the past years. Among these are 3D and 4D culture techniques, organotypic skin reconstructs, melanoma-on-chip models and patient-derived xenografts, Every technique has its own strengths but also weaknesses regarding throughput, reproducibility, and reflection of the human situation. Here, we provide a comprehensive overview of currently used techniques and discuss their use in different experimental settings.

Transformer guided self-adaptive network for multi-scale skin lesion image segmentation

BACKGROUND

In recent years, skin lesion has become a major public health concern, and the diagnosis and management of skin lesions depend heavily on the correct segmentation of the lesions. Traditional convolutional neural networks (CNNs) have demonstrated promising results in skin lesion segmentation, but they are limited in their ability to capture distant connections and intricate features. In addition, current medical image segmentation algorithms rarely consider the distribution of different categories in different regions of the image and do not consider the spatial relationship between pixels.

OBJECTIVES

This study proposes a self-adaptive position-aware skin lesion segmentation model SapFormer to capture global context and fine-grained detail, better capture spatial relationships, and adapt to different positional characteristics. The SapFormer is a multi-scale dynamic position-aware structure designed to provide a more flexible representation of the relationships between skin lesion characteristics and lesion distribution. Additionally, it increases skin lesion segmentation accuracy and decreases incorrect segmentation of non-lesion areas.

INNOVATIONS

SapFormer designs multiple hybrid transformers for multi-scale feature encoding of skin images and multi-scale positional feature sensing of the encoded features using a transformer decoder to obtain fine-grained features of the lesion area and optimize the regional feature distribution. The self-adaptive feature framework, built upon the transformer decoder module, dynamically and automatically generates parameterizations with learnable properties at different positions. These parameterizations are derived from the multi-scale encoding characteristics of the input image. Simultaneously, this paper utilizes the cross-attention network to optimize the features of the current region according to the features of other regions, aiming to increase skin lesion segmentation accuracy.

MAIN RESULTS

The ISIC-2016, ISIC-2017, and ISIC-2018 datasets for skin lesions are used as the basis for the experiment. On these datasets, the proposed model has accuracy values of 97.9 %, 94.3 %, and 95.7 %, respectively. The proposed model's IOU values are, in order, 93.2 %, 86.4 %, and 89.4 %. The proposed model's DSC values are 96.4 %, 92.6 %, and 94.3 %, respectively. All three metrics surpass the performance of the majority of state-of-the-art (SOTA) models. SapFormer's metrics on these datasets demonstrate that it can precisely segment skin lesions. Notably, our approach exhibits remarkable noise resistance in non-lesion areas, while simultaneously conducting finer-grained regional feature extraction on the skin lesion image.

CONCLUSIONS

In conclusion, the integration of a transformer-guided position-aware network into semantic skin lesion segmentation results in a notable performance boost. The ability of our proposed network to capture spatial relationships and fine-grained details proves beneficial for effective skin lesion segmentation. By enhancing lesion localization, feature extraction, quantitative analysis, and classification accuracy, the proposed segmentation model improves the diagnostic efficiency of skin lesion analysis on dermoscopic images. It assists dermatologists in making more accurate and efficient diagnoses, ultimately leading to better patient care and outcomes. This research paves the way for advances in diagnosing and treating skin lesions, promoting better understanding and decision-making in the clinical setting.

Machine learning identifies SLC6A14 as a novel biomarker promoting the proliferation and metastasis of pancreatic cancer via Wnt/β-catenin signaling

Pancreatic cancer (PC) has the poorest prognosis compared to other common cancers because of its aggressive nature, late detection, and resistance to systemic treatment. In this study, we aimed to identify novel biomarkers for PC patients and further explored their function in PC progression. We analyzed GSE62452 and GSE28735 datasets, identifying 35 differentially expressed genes (DEGs) between PC specimens and non-tumors. Based on 35 DEGs, we performed machine learning and identified eight diagnostic genes involved in PC progression. Then, we further screened three critical genes (CTSE, LAMC2 and SLC6A14) using three GEO datasets. A new diagnostic model was developed based on them and showed a strong predictive ability in screen PC specimens from non-tumor specimens in GEO, TCGA datasets and our cohorts. Then, clinical assays based on TCGA datasets indicated that the expression of LAMC2 and SLC6A14 was associated with advanced clinical stage and poor prognosis. The expressions of LAMC2 and SLC6A14, as well as the abundances of a variety of immune cells, exhibited a significant positive association with one another. Functionally, we confirmed that SLC6A14 was highly expressed in PC and its knockdown suppressed the proliferation, migration, invasion and EMT signal via regulating Wnt/β-catenin signaling pathway. Overall, our findings developed a novel diagnostic model for PC patients. SLC6A14 may promote PC progression via modulating Wnt/β-catenin signaling. This work offered a novel and encouraging new perspective that holds potential for further illuminating the clinicopathological relevance of PC as well as its molecular etiology.

Evaluation of an artificial intelligence-based decision support for detection of cutaneous melanoma in primary care - a prospective, real-life, clinical trial

BACKGROUND

Use of artificial intelligence, or machine learning, to assess dermoscopic images of skin lesions to detect melanoma has in several retrospective studies shown high levels of diagnostic accuracy on par with, or even outperforming, experienced dermatologists. However, the enthusiasm around these algorithms has not yet been matched by prospective clinical trials performed in authentic clinical settings. In several European countries, including Sweden, the initial clinical assessment of suspected skin cancer is principally conducted in the primary health care setting by primary care physicians; with or without access to teledermoscopic support from dermatology clinics.

OBJECTIVE

To determine the diagnostic performance of an artificial intelligence-based clinical decision support tool for cutaneous melanoma detection, operated by a smartphone application (app), when used prospectively by primary care physicians to assess skin lesions of concern due to some degree of melanoma suspicion.

METHODS

This prospective, multicentre, clinical trial was conducted at 36 primary care centres in Sweden. The physicians used the smartphone app on skin lesions of concern by photographing them dermoscopically, which resulted in a dichotomous decision support text regarding evidence for melanoma. Regardless of the app outcome, all lesions underwent standard diagnostic procedure, by surgical excision or referral to dermatologist. After completed investigation, lesion diagnoses were collected from the patients' medical records and compared to app outcome and other lesion data.

RESULTS

In total, 253 lesions of concern in 228 patients were included, of which 21 proved to be melanomas, with 11 thin invasive melanomas and 10 melanomas in situ. The app's accuracy (95% confidence interval) in identifying melanomas was reflected in an area under the receiver operating characteristic (AUROC) curve of 0.960 (0.928-0.980), corresponding to a maximum sensitivity and specificity of 95.2% and 84.5%, respectively. For invasive melanomas alone, the AUROC was 0.988 (0.965-0.997), corresponding to a maximum sensitivity and specificity of 100% and 92.6%, respectively.

CONCLUSIONS

The clinical decision support tool evaluated in this investigation showed high diagnostic accuracy when used prospectively on primary care patients, which could add significant clinical value for primary care physicians in assessing skin lesions to detect melanoma. ClinicalTrials.gov Identifier: NCT05172232.

Challenges of artificial intelligence in medicine and dermatology

Artificial intelligence (AI) in medicine and dermatology brings additional challenges related to bias, transparency, ethics, security, and inequality. Bias in AI algorithms can arise from biased training data or decision-making processes, leading to disparities in health care outcomes. Addressing bias requires careful examination of the data used to train AI models and implementation of strategies to mitigate bias during algorithm development. Transparency is another critical challenge, as AI systems often operate as black boxes, making it difficult to understand how decisions are reached. Ensuring transparency in AI algorithms is vital to gaining trust from both patients and health care providers. Ethical considerations arise when using AI in health care, including issues such as informed consent, privacy, and the responsibility for the decisions made by AI systems. It is essential to establish clear guidelines and frameworks that govern the ethical use of AI, including maintaining patient autonomy and protecting sensitive health information. Security is a significant concern in AI systems, as they rely on vast amounts of sensitive patient data. Protecting these data from unauthorized access, breaches, or malicious attacks is paramount to maintaining patient privacy and trust in AI technologies. Lastly, the potential for inequality arises if AI technologies are not accessible to all populations, leading to a digital divide in health care. Efforts should be made to ensure that AI solutions are affordable, accessible, and tailored to the needs of diverse communities, mitigating the risk of exacerbating existing health care disparities. Addressing these challenges is crucial for AI's responsible and equitable integration in medicine and dermatology.

Automated Identification of Cutaneous Leishmaniasis Lesions Using Deep-Learning-Based Artificial Intelligence

The polymorphism of cutaneous leishmaniasis (CL) complicates diagnosis in health care services because lesions may be confused with other dermatoses such as sporotrichosis, paracocidiocomycosis, and venous insufficiency. Automated identification of skin diseases based on deep learning (DL) has been applied to assist diagnosis. In this study, we evaluated the performance of AlexNet, a DL algorithm, to identify pictures of CL lesions in patients from Midwest Brazil. We used a set of 2458 pictures (up to 10 of each lesion) obtained from patients treated between 2015 and 2022 in the Leishmaniasis Clinic at the University Hospital of Brasilia. We divided the picture database into training (80%), internal validation (10%), and testing sets (10%), and trained and tested AlexNet to identify pictures of CL lesions. We performed three simulations and trained AlexNet to differentiate CL from 26 other dermatoses (e.g., chromomycosis, ecthyma, venous insufficiency). We obtained an average accuracy of 95.04% (Confidence Interval 95%: 93.81-96.04), indicating an excellent performance of AlexNet in identifying pictures of CL lesions. We conclude that automated CL identification using AlexNet has the potential to assist clinicians in diagnosing skin lesions. These results contribute to the development of a mobile application to assist in the diagnosis of CL in health care services.

Use of artificial intelligence for decision-support to avoid high-risk behaviors during laparoscopic cholecystectomy

INTRODUCTION

Bile duct injuries (BDIs) are a significant source of morbidity among patients undergoing laparoscopic cholecystectomy (LC). GoNoGoNet is an artificial intelligence (AI) algorithm that has been developed and validated to identify safe ("Go") and dangerous ("No-Go") zones of dissection during LC, with the potential to prevent BDIs through real-time intraoperative decision-support. This study evaluates GoNoGoNet's ability to predict Go/No-Go zones during LCs with BDIs.

METHODS AND PROCEDURES

Eleven LC videos with BDI (BDI group) were annotated by GoNoGoNet. All tool-tissue interactions, including the one that caused the BDI, were characterized in relation to the algorithm's predicted location of Go/No-Go zones. These were compared to another 11 LC videos with cholecystitis (control group) deemed to represent "safe cholecystectomy" by experts. The probability threshold of GoNoGoNet annotations were then modulated to determine its relationship to Go/No-Go predictions. Data is shown as % difference [99% confidence interval].

RESULTS

Compared to control, the BDI group showed significantly greater proportion of sharp dissection (+ 23.5% [20.0-27.0]), blunt dissection (+ 32.1% [27.2-37.0]), and total interactions (+ 33.6% [31.0-36.2]) outside of the Go zone. Among injury-causing interactions, 4 (36%) were in the No-Go zone, 2 (18%) were in the Go zone, and 5 (45%) were outside both zones, after maximizing the probability threshold of the Go algorithm.

CONCLUSION

AI has potential to detect unsafe dissection and prevent BDIs through real-time intraoperative decision-support. More work is needed to determine how to optimize integration of this technology into the operating room workflow and adoption by end-users.

Recent Advances in the Field of Artificial Intelligence for Precision Medicine in Patients with a Diagnosis of Metastatic Cutaneous Melanoma

Standard-of-care medical imaging techniques such as CT, MRI, and PET play a critical role in managing patients diagnosed with metastatic cutaneous melanoma. Advancements in artificial intelligence (AI) techniques, such as radiomics, machine learning, and deep learning, could revolutionize the use of medical imaging by enhancing individualized image-guided precision medicine approaches. In the present article, we will decipher how AI/radiomics could mine information from medical images, such as tumor volume, heterogeneity, and shape, to provide insights into cancer biology that can be leveraged by clinicians to improve patient care both in the clinic and in clinical trials. More specifically, we will detail the potential role of AI in enhancing detection/diagnosis, staging, treatment planning, treatment delivery, response assessment, treatment toxicity assessment, and monitoring of patients diagnosed with metastatic cutaneous melanoma. Finally, we will explore how these proof-of-concept results can be translated from bench to bedside by describing how the implementation of AI techniques can be standardized for routine adoption in clinical settings worldwide to predict outcomes with great accuracy, reproducibility, and generalizability in patients diagnosed with metastatic cutaneous melanoma.

Establishment and application of TSDPSO-SVM model combined with multi-dimensional feature fusion method in the identification of fracture-related infection

Fracture-related infection (FRI) is one of the most common and intractable complications in orthopedic trauma surgery. This complication can impose severe psychological burdens and socio-economic impacts on patients. Although the definition of FRI has been proposed recently by an expert group, the diagnostic criteria for FRI are not yet standardized. A total of 4761 FRI patients and 4761 fracture patients (Non-FRI) were included in the study. The feature set of patients included imaging characteristics, demographic information, clinical symptoms, microbiological findings, and serum inflammatory markers, which were reduced by the Principal Component Analysis. To optimize the Support Vector Machine (SVM) model, the Traction Switching Delay Particle Swarm Optimization (TSDPSO) algorithm, a recognition method was proposed. Moreover, five machine learning models, including TSDPSO-SVM, were employed to distinguish FRI from Non-FRI. The Area under the Curve of TSDPSO-SVM was 0.91, at least 5% higher than that of other models. Compared with the Random Forest, Backpropagation Neural Network (BP), SVM and eXtreme Gradient Boosting (XGBoost), TSDPSO-SVM demonstrated remarkable accuracy in the test set ([Formula: see text]). The recall of TSDPSO-SVM was 98.32%, indicating a significant improvement ([Formula: see text]). Compared with BP and SVM, TSDPSO-SVM exhibited significantly superior specificity, false positive rate and precision ([Formula: see text]. The five models yielded consistent results in the training and testing of FRI patients across different age groups. TSDPSO-SVM is validated to have the maximum overall prediction ability and can effectively distinguish between FRI and Non-FRI. For the early diagnosis of FRI, TSDPSO-SVM may provide a reference basis for clinicians, especially those with insufficient experience. These results also lay a foundation for the intelligent diagnosis of FRI. Furthermore, these findings exhibit the application potential of this model in the diagnosis and classification of other diseases.

Automatic Skin Cancer Detection Using Clinical Images: A Comprehensive Review

Skin cancer has become increasingly common over the past decade, with melanoma being the most aggressive type. Hence, early detection of skin cancer and melanoma is essential in dermatology. Computational methods can be a valuable tool for assisting dermatologists in identifying skin cancer. Most research in machine learning for skin cancer detection has focused on dermoscopy images due to the existence of larger image datasets. However, general practitioners typically do not have access to a dermoscope and must rely on naked-eye examinations or standard clinical images. By using standard, off-the-shelf cameras to detect high-risk moles, machine learning has also proven to be an effective tool. The objective of this paper is to provide a comprehensive review of image-processing techniques for skin cancer detection using clinical images. In this study, we evaluate 51 state-of-the-art articles that have used machine learning methods to detect skin cancer over the past decade, focusing on clinical datasets. Even though several studies have been conducted in this field, there are still few publicly available clinical datasets with sufficient data that can be used as a benchmark, especially when compared to the existing dermoscopy databases. In addition, we observed that the available artifact removal approaches are not quite adequate in some cases and may also have a negative impact on the models. Moreover, the majority of the reviewed articles are working with single-lesion images and do not consider typical mole patterns and temporal changes in the lesions of each patient.

Principles, applications, and future of artificial intelligence in dermatology

This paper provides an overview of artificial-intelligence (AI), as applied to dermatology. We focus our discussion on methodology, AI applications for various skin diseases, limitations, and future opportunities. We review how the current image-based models are being implemented in dermatology across disease subsets, and highlight the challenges facing widespread adoption. Additionally, we discuss how the future of AI in dermatology might evolve and the emerging paradigm of large language, and multi-modal models to emphasize the importance of developing responsible, fair, and equitable models in dermatology.

A Multi-Stage Faster RCNN-Based iSPLInception for Skin Disease Classification Using Novel Optimization

Nowadays, skin cancer is considered a serious disorder in which early identification and treatment of the disease are essential to ensure the stability of the patients. Several existing skin cancer detection methods are introduced by employing deep learning (DL) to perform skin disease classification. Convolutional neural networks (CNNs) can classify melanoma skin cancer images. But, it suffers from an overfitting problem. Therefore, to overcome this problem and to classify both benign and malignant tumors efficiently, the multi-stage faster RCNN-based iSPLInception (MFRCNN-iSPLI) method is proposed. Then, the test dataset is used for evaluating the proposed model performance. The faster RCNN is employed directly to perform image classification. This may heavily raise computation time and network complications. So, the iSPLInception model is applied in the multi-stage classification. In this, the iSPLInception model is formulated using the Inception-ResNet design. For candidate box deletion, the prairie dog optimization algorithm is utilized. We have utilized two skin disease datasets, namely, ISIC 2019 Skin lesion image classification and the HAM10000 dataset for conducting experimental results. The methods' accuracy, precision, recall, and F1 score values are calculated, and the results are compared with the existing methods such as CNN, hybrid DL, Inception v3, and VGG19. With 95.82% accuracy, 96.85% precision, 96.52% recall, and 0.95% F1 score values, the output analysis of each measure verified the prediction and classification effectiveness of the method.

Genomic Biomarker Discovery in Disease Progression and Therapy Response in Bladder Cancer Utilizing Machine Learning

Cancer in all its forms of expression is a major cause of death. To identify the genomic reason behind cancer, discovery of biomarkers is needed. In this paper, genomic data of bladder cancer are examined for the purpose of biomarker discovery. Genomic biomarkers are indicators stemming from the study of the genome, either at a very low level based on the genome sequence itself, or more abstractly such as measuring the level of gene expression for different disease groups. The latter method is pivotal for this work, since the available datasets consist of RNA sequencing data, transformed to gene expression levels, as well as data on a multitude of clinical indicators. Based on this, various methods are utilized such as statistical modeling via logistic regression and regularization techniques (elastic-net), clustering, survival analysis through Kaplan-Meier curves, and heatmaps for the experiments leading to biomarker discovery. The experiments have led to the discovery of two gene signatures capable of predicting therapy response and disease progression with considerable accuracy for bladder cancer patients which correlates well with clinical indicators such as Therapy Response and T-Stage at surgery with Disease Progression in a time-to-event manner.

Systematic review of deep learning image analyses for the diagnosis and monitoring of skin disease

Skin diseases affect one-third of the global population, posing a major healthcare burden. Deep learning may optimise healthcare workflows through processing skin images via neural networks to make predictions. A focus of deep learning research is skin lesion triage to detect cancer, but this may not translate to the wider scope of >2000 other skin diseases. We searched for studies applying deep learning to skin images, excluding benign/malignant lesions (1/1/2000-23/6/2022, PROSPERO CRD42022309935). The primary outcome was accuracy of deep learning algorithms in disease diagnosis or severity assessment. We modified QUADAS-2 for quality assessment. Of 13,857 references identified, 64 were included. The most studied diseases were acne, psoriasis, eczema, rosacea, vitiligo, urticaria. Deep learning algorithms had high specificity and variable sensitivity in diagnosing these conditions. Accuracy of algorithms in diagnosing acne (median 94%, IQR 86-98; n = 11), rosacea (94%, 90-97; n = 4), eczema (93%, 90-99; n = 9) and psoriasis (89%, 78-92; n = 8) was high. Accuracy for grading severity was highest for psoriasis (range 93-100%, n = 2), eczema (88%, n = 1), and acne (67-86%, n = 4). However, 59 (92%) studies had high risk-of-bias judgements and 62 (97%) had high-level applicability concerns. Only 12 (19%) reported participant ethnicity/skin type. Twenty-four (37.5%) evaluated the algorithm in an independent dataset, clinical setting or prospectively. These data indicate potential of deep learning image analysis in diagnosing and monitoring common skin diseases. Current research has important methodological/reporting limitations. Real-world, prospectively-acquired image datasets with external validation/testing will advance deep learning beyond the current experimental phase towards clinically-useful tools to mitigate rising health and cost impacts of skin disease.

Looking into the Skin in Health and Disease: From Microscopy Imaging Techniques to Molecular Analysis

The skin is a complex organ that includes a wide variety of tissue types with different embryological origins [...].

Artificial intelligence and digital health in improving primary health care service delivery in LMICs: A systematic review

AIM

Technology including artificial intelligence (AI) may play a key role to strengthen primary health care services in resource-poor settings. This systematic review aims to explore the evidence on the use of AI and digital health in improving primary health care service delivery.

METHODS

Three electronic databases were searched using a comprehensive search strategy without providing any restriction in June 2023. Retrieved articles were screened independently using the "Rayyan" software. Data extraction and quality assessment were conducted independently by two review authors. A narrative synthesis of the included interventions was conducted.

RESULTS

A total of 4596 articles were screened, and finally, 48 articles were included from 21 different countries published between 2013 and 2021. The main focus of the included studies was noncommunicable diseases (n = 15), maternal and child health care (n = 11), primary care (n = 8), infectious diseases including tuberculosis, leprosy, and HIV (n = 7), and mental health (n = 6). Included studies considered interventions using AI, and digital health of which mobile-phone-based interventions were prominent. m-health interventions were well adopted and easy to use and improved the record-keeping, service deliver, and patient satisfaction.

CONCLUSION

AI and the application of digital technologies improve primary health care service delivery in resource-poor settings in various ways. However, in most of the cases, the application of AI and digital health is implemented through m-health. There is a great scope to conduct further research exploring the interventions on a large scale.

Implementation of artificial intelligence for the detection of cutaneous melanoma within a primary care setting: prevalence and types of skin cancer in outdoor enthusiasts

Background

There is enthusiasm for implementing artificial intelligence (AI) to assist clinicians detect skin cancer. Performance metrics of AI from dermoscopic images have been promising, with studies documenting sensitivity and specificity values equal to or superior to specialists for the detection of malignant melanomas (MM). Early detection rates would particularly benefit Australia, which has the worlds highest incidence of MM per capita. The detection of skin cancer may be delayed due to late screening or the inherent difficulty in diagnosing early skin cancers which often have a paucity of clinical features and may blend into sun damaged skin. Individuals who participate in outdoor sports and recreation experience high levels of intermittent ultraviolet radiation (UVR), which is associated with the development of skin cancer, including MM. This research aimed to assess the prevalence of skin cancer in individuals who regularly participate in activities outdoors and to report the performance parameters of a commercially available AI-powered software to assess the predictive risk of MM development.

Methods

Cross-sectional study design incorporating a survey, total body skin cancer screening and AI-embedded software capable of predictive scoring of queried MM.

Results

A total of 423 participants consisting of surfers (n = 108), swimmers (n = 60) and walkers/runners (n = 255) participated. Point prevalence for MM was highest for surfers (6.48%), followed by walkers/runners (4.3%) and swimmers (3.33%) respectively. When compared to the general Australian population, surfers had the highest odds ratio (OR) for MM (OR 119.8), followed by walkers/runners (OR 79.74), and swimmers (OR 61.61) rounded out the populations. Surfers and swimmers reported comparatively lower lifetime hours of sun exposure (5,594 and 5,686, respectively) but more significant amounts of activity within peak ultraviolet index compared with walkers/runners (9,554 h). A total of 48 suspicious pigmented lesions made up of histopathology-confirmed MM (n = 15) and benign lesions (n = 33) were identified. The performance of the AI from this clinical population was found to have a sensitivity of 53.33%, specificity of 54.44% and accuracy of 54.17%.

Conclusions

Rates of both keratinocyte carcinomas and MM were notably higher in aquatic and land-based enthusiasts compared to the general Australian population. These findings further highlight the clinical importance of sun-safe protection measures and regular skin screening in individuals who spend significant time outdoors. The use of AI in the early identification of MM is promising. However, the lower-than-expected performance metrics of the AI software used in this study indicated reservations should be held before recommending this particular version of this AI software as a reliable adjunct for clinicians in skin imaging diagnostics in patients with potentially sun damaged skin.

Deep learning for AI-based diagnosis of skin-related neglected tropical diseases: A pilot study

BACKGROUND

Deep learning, which is a part of a broader concept of artificial intelligence (AI) and/or machine learning has achieved remarkable success in vision tasks. While there is growing interest in the use of this technology in diagnostic support for skin-related neglected tropical diseases (skin NTDs), there have been limited studies in this area and fewer focused on dark skin. In this study, we aimed to develop deep learning based AI models with clinical images we collected for five skin NTDs, namely, Buruli ulcer, leprosy, mycetoma, scabies, and yaws, to understand how diagnostic accuracy can or cannot be improved using different models and training patterns.

METHODOLOGY

This study used photographs collected prospectively in Côte d'Ivoire and Ghana through our ongoing studies with use of digital health tools for clinical data documentation and for teledermatology. Our dataset included a total of 1,709 images from 506 patients. Two convolutional neural networks, ResNet-50 and VGG-16 models were adopted to examine the performance of different deep learning architectures and validate their feasibility in diagnosis of the targeted skin NTDs.

PRINCIPAL FINDINGS

The two models were able to correctly predict over 70% of the diagnoses, and there was a consistent performance improvement with more training samples. The ResNet-50 model performed better than the VGG-16 model. A model trained with PCR confirmed cases of Buruli ulcer yielded 1-3% increase in prediction accuracy across all diseases, except, for mycetoma, over a model which training sets included unconfirmed cases.

CONCLUSIONS

Our approach was to have the deep learning model distinguish between multiple pathologies simultaneously-which is close to real-world practice. The more images used for training, the more accurate the diagnosis became. The percentages of correct diagnosis increased with PCR-positive cases of Buruli ulcer. This demonstrated that it may be better to input images from the more accurately diagnosed cases in the training models also for achieving better accuracy in the generated AI models. However, the increase was marginal which may be an indication that the accuracy of clinical diagnosis alone is reliable to an extent for Buruli ulcer. Diagnostic tests also have their flaws, and they are not always reliable. One hope for AI is that it will objectively resolve this gap between diagnostic tests and clinical diagnoses with the addition of another tool. While there are still challenges to be overcome, there is a potential for AI to address the unmet needs where access to medical care is limited, like for those affected by skin NTDs.

Privacy-Aware Collaborative Learning for Skin Cancer Prediction

Cancer, including the highly dangerous melanoma, is marked by uncontrolled cell growth and the possibility of spreading to other parts of the body. However, the conventional approach to machine learning relies on centralized training data, posing challenges for data privacy in healthcare systems driven by artificial intelligence. The collection of data from diverse sensors leads to increased computing costs, while privacy restrictions make it challenging to employ traditional machine learning methods. Researchers are currently confronted with the formidable task of developing a skin cancer prediction technique that takes privacy concerns into account while simultaneously improving accuracy. In this work, we aimed to propose a decentralized privacy-aware learning mechanism to accurately predict melanoma skin cancer. In this research we analyzed federated learning from the skin cancer database. The results from the study showed that 92% accuracy was achieved by the proposed method, which was higher than baseline algorithms.

Using multiple indicators to predict the risk of surgical site infection after ORIF of tibia fractures: a machine learning based study

Objective

Surgical site infection (SSI) are a serious complication that can occur after open reduction and internal fixation (ORIF) of tibial fractures, leading to severe consequences. This study aimed to develop a machine learning (ML)-based predictive model to screen high-risk patients of SSI following ORIF of tibial fractures, thereby aiding in personalized prevention and treatment.

Methods

Patients who underwent ORIF of tibial fractures between January 2018 and October 2022 at the Department of Emergency Trauma Surgery at Ganzhou People's Hospital were retrospectively included. The demographic characteristics, surgery-related variables and laboratory indicators of patients were collected in the inpatient electronic medical records. Ten different machine learning algorithms were employed to develop the prediction model, and the performance of the models was evaluated to select the best predictive model. Ten-fold cross validation for the training set and ROC curves for the test set were used to evaluate model performance. The decision curve and calibration curve analysis were used to verify the clinical value of the model, and the relative importance of features in the model was analyzed.

Results

A total of 351 patients who underwent ORIF of tibia fractures were included in this study, among whom 51 (14.53%) had SSI and 300 (85.47%) did not. Of the patients with SSI, 15 cases were of deep infection, and 36 cases were of superficial infection. Given the initial parameters, the ET, LR and RF are the top three algorithms with excellent performance. Ten-fold cross-validation on the training set and ROC curves on the test set revealed that the ET model had the best performance, with AUC values of 0.853 and 0.866, respectively. The decision curve analysis and calibration curves also showed that the ET model had the best clinical utility. Finally, the performance of the ET model was further tested, and the relative importance of features in the model was analyzed.

Conclusion

In this study, we constructed a multivariate prediction model for SSI after ORIF of tibial fracture through ML, and the strength of this study was the use of multiple indicators to establish an infection prediction model, which can better reflect the real situation of patients, and the model show great clinical prediction performance.

Fostering transparent medical image AI via an image-text foundation model grounded in medical literature

Building trustworthy and transparent image-based medical AI systems requires the ability to interrogate data and models at all stages of the development pipeline: from training models to post-deployment monitoring. Ideally, the data and associated AI systems could be described using terms already familiar to physicians, but this requires medical datasets densely annotated with semantically meaningful concepts. Here, we present a foundation model approach, named MONET (Medical cONcept rETriever), which learns how to connect medical images with text and generates dense concept annotations to enable tasks in AI transparency from model auditing to model interpretation. Dermatology provides a demanding use case for the versatility of MONET, due to the heterogeneity in diseases, skin tones, and imaging modalities. We trained MONET on the basis of 105,550 dermatological images paired with natural language descriptions from a large collection of medical literature. MONET can accurately annotate concepts across dermatology images as verified by board-certified dermatologists, outperforming supervised models built on previously concept-annotated dermatology datasets. We demonstrate how MONET enables AI transparency across the entire AI development pipeline from dataset auditing to model auditing to building inherently interpretable models.

Advances in cutaneous squamous cell carcinoma

Human malignancies arise predominantly in tissues of epithelial origin, where the stepwise transformation from healthy epithelium to premalignant dysplasia to invasive neoplasia involves sequential dysregulation of biological networks that govern essential functions of epithelial homeostasis. Cutaneous squamous cell carcinoma (cSCC) is a prototype epithelial malignancy, often with a high tumour mutational burden. A plethora of risk genes, dominated by UV-induced sun damage, drive disease progression in conjunction with stromal interactions and local immunomodulation, enabling continuous tumour growth. Recent studies have identified subpopulations of SCC cells that specifically interact with the tumour microenvironment. These advances, along with increased knowledge of the impact of germline genetics and somatic mutations on cSCC development, have led to a greater appreciation of the complexity of skin cancer pathogenesis and have enabled progress in neoadjuvant immunotherapy, which has improved pathological complete response rates. Although measures for the prevention and therapeutic management of cSCC are associated with clinical benefit, the prognosis remains poor for advanced disease. Elucidating how the genetic mechanisms that drive cSCC interact with the tumour microenvironment is a current focus in efforts to understand, prevent and treat cSCC.

Assessing the Effectiveness of Artificial Intelligence Models for Detecting Alveolar Bone Loss in Periodontal Disease: A Panoramic Radiograph Study

The assessment of alveolar bone loss, a crucial element of the periodontium, plays a vital role in the diagnosis of periodontitis and the prognosis of the disease. In dentistry, artificial intelligence (AI) applications have demonstrated practical and efficient diagnostic capabilities, leveraging machine learning and cognitive problem-solving functions that mimic human abilities. This study aims to evaluate the effectiveness of AI models in identifying alveolar bone loss as present or absent across different regions. To achieve this goal, alveolar bone loss models were generated using the PyTorch-based YOLO-v5 model implemented via CranioCatch software, detecting periodontal bone loss areas and labeling them using the segmentation method on 685 panoramic radiographs. Besides general evaluation, models were grouped according to subregions (incisors, canines, premolars, and molars) to provide a targeted evaluation. Our findings reveal that the lowest sensitivity and F1 score values were associated with total alveolar bone loss, while the highest values were observed in the maxillary incisor region. It shows that artificial intelligence has a high potential in analytical studies evaluating periodontal bone loss situations. Considering the limited amount of data, it is predicted that this success will increase with the provision of machine learning by using a more comprehensive data set in further studies.

Integrating multiple machine learning methods to construct glutamine metabolism-related signatures in lung adenocarcinoma

Background

Glutamine metabolism (GM) is known to play a critical role in cancer development, including in lung adenocarcinoma (LUAD), although the exact contribution of GM to LUAD remains incompletely understood. In this study, we aimed to discover new targets for the treatment of LUAD patients by using machine learning algorithms to establish prognostic models based on GM-related genes (GMRGs).

Methods

We used the AUCell and WGCNA algorithms, along with single-cell and bulk RNA-seq data, to identify the most prominent GMRGs associated with LUAD. Multiple machine learning algorithms were employed to develop risk models with optimal predictive performance. We validated our models using multiple external datasets and investigated disparities in the tumor microenvironment (TME), mutation landscape, enriched pathways, and response to immunotherapy across various risk groups. Additionally, we conducted in vitro and in vivo experiments to confirm the role of LGALS3 in LUAD.

Results

We identified 173 GMRGs strongly associated with GM activity and selected the Random Survival Forest (RSF) and Supervised Principal Components (SuperPC) methods to develop a prognostic model. Our model's performance was validated using multiple external datasets. Our analysis revealed that the low-risk group had higher immune cell infiltration and increased expression of immune checkpoints, indicating that this group may be more receptive to immunotherapy. Moreover, our experimental results confirmed that LGALS3 promoted the proliferation, invasion, and migration of LUAD cells.

Conclusion

Our study established a prognostic model based on GMRGs that can predict the effectiveness of immunotherapy and provide novel approaches for the treatment of LUAD. Our findings also suggest that LGALS3 may be a potential therapeutic target for LUAD.

Explainable discovery of disease biomarkers: The case of ovarian cancer to illustrate the best practice in machine learning and Shapley analysis

OBJECTIVE

Ovarian cancer is a significant health issue with lasting impacts on the community. Despite recent advances in surgical, chemotherapeutic and radiotherapeutic interventions, they have had only marginal impacts due to an inability to identify biomarkers at an early stage. Biomarker discovery is challenging, yet essential for improving drug discovery and clinical care. Machine learning (ML) techniques are invaluable for recognising complex patterns in biomarkers compared to conventional methods, yet they can lack physical insights into diagnosis. eXplainable Artificial Intelligence (XAI) is capable of providing deeper insights into the decision-making of complex ML algorithms increasing their applicability. We aim to introduce best practice for combining ML and XAI techniques for biomarker validation tasks.

METHODS

We focused on classification tasks and a game theoretic approach based on Shapley values to build and evaluate models and visualise results. We described the workflow and apply the pipeline in a case study using the CDAS PLCO Ovarian Biomarkers dataset to demonstrate the potential for accuracy and utility.

RESULTS

The case study results demonstrate the efficacy of the ML pipeline, its consistency, and advantages compared to conventional statistical approaches.

CONCLUSION

The resulting guidelines provide a general framework for practical application of XAI in medical research that can inform clinicians and validate and explain cancer biomarkers.

Deep learning for AI-based diagnosis of skin-related neglected tropical diseases: a pilot study

Background

Deep learning, which is a part of a broader concept of artificial intelligence (AI) and/or machine learning has achieved remarkable success in vision tasks. While there is growing interest in the use of this technology in diagnostic support for skin-related neglected tropical diseases (skin NTDs), there have been limited studies in this area and fewer focused on dark skin. In this study, we aimed to develop deep learning based AI models with clinical images we collected for five skin NTDs, namely, Buruli ulcer, leprosy, mycetoma, scabies, and yaws, to understand how diagnostic accuracy can or cannot be improved using different models and training patterns.

Methodology

This study used photographs collected prospectively in Côte d'Ivoire and Ghana through our ongoing studies with use of digital health tools for clinical data documentation and for teledermatology. Our dataset included a total of 1,709 images from 506 patients. Two convolutional neural networks, ResNet-50 and VGG-16 models were adopted to examine the performance of different deep learning architectures and validate their feasibility in diagnosis of the targeted skin NTDs.

Principal findings

The two models were able to correctly predict over 70% of the diagnoses, and there was a consistent performance improvement with more training samples. The ResNet-50 model performed better than the VGG-16 model. Model trained with PCR confirmed cases of Buruli ulcer yielded 1-3% increase in prediction accuracy over training sets including unconfirmed cases.

Conclusions

Our approach was to have the deep learning model distinguish between multiple pathologies simultaneously - which is close to real-world practice. The more images used for training, the more accurate the diagnosis became. The percentages of correct diagnosis increased with PCR-positive cases of Buruli ulcer. This demonstrated that it may be better to input images from the more accurately diagnosed cases in the training models also for achieving better accuracy in the generated AI models. However, the increase was marginal which may be an indication that the accuracy of clinical diagnosis alone is reliable to an extent for Buruli ulcer. Diagnostic tests also have its flaws, and they are not always reliable. One hope for AI is that it will objectively resolve this gap between diagnostic tests and clinical diagnoses with addition of another tool. While there are still challenges to be overcome, there is a potential for AI to address the unmet needs where access to medical care is limited, like for those affected by skin NTDs.

AUTHOR SUMMARY

The diagnosis of skin diseases depends in large part, though not exclusively on visual inspection. The diagnosis and management of these diseases is thus particularly amenable to teledermatology approaches. The widespread availability of cell phone technology and electronic information transfer provides new potential for access to health care in low-income countries, yet there are limited efforts targeting these neglected populations with dark skin and consequently limited availability of tools. In this study, we leveraged a collection of skin images gathered through a system of teledermatology in the West African countries of Côte d'Ivoire and Ghana, and applied deep learning, a form of artificial intelligence (AI) - to see if deep learning models can distinguish between different diseases and support their diagnosis. Skin-related neglected tropical diseases, or skin NTDs, prevail in these regions and were our target conditions: Buruli ulcer, leprosy, mycetoma, scabies, and yaws. The accuracy of prediction depended on the number of images that were fed into the model for training with marginal improvement using laboratory confirmed cases in training. Using more images and greater efforts in this area, it is possible that AI can help address the unmet needs where access to medical care is limited.

Development and validation of machine learning models to predict survival of patients with resected stage-III NSCLC

Objective

To compare the performance of three machine learning algorithms with the tumor, node, and metastasis (TNM) staging system in survival prediction and validate the individual adjuvant treatment recommendations plan based on the optimal model.

Methods

In this study, we trained three machine learning madel and validated 3 machine learning survival models-deep learning neural network, random forest and cox proportional hazard model- using the data of patients with stage-al3 NSCLC patients who received resection surgery from the National Cancer Institute Surveillance, Epidemiology, and End Results (SEER) database from 2012 to 2017,the performance of survival predication from all machine learning models were assessed using a concordance index (c-index) and the averaged c-index is utilized for cross-validation. The optimal model was externally validated in an independent cohort from Shaanxi Provincial People’s Hospital. Then we compare the performance of the optimal model and TNM staging system. Finally, we developed a Cloud-based recommendation system for adjuvant therapy to visualize survival curve of each treatment plan and deployed on the internet.

Results

A total of 4617 patients were included in this study. The deep learning network performed more stably and accurately in predicting stage-iii NSCLC resected patients survival than the random survival forest and Cox proportional hazard model on the internal test dataset (C-index=0.834 vs. 0.678 vs. 0.640) and better than TNM staging system (C-index=0.820 vs. 0.650) in the external validation. The individual patient who follow the reference from recommendation system had superior survival compared to those who did not. The predicted 5-year-survival curve for each adjuvant treatment plan could be accessed in the recommender system via the browser.

Conclusion

Deep learning model has several advantages over linear model and random forest model in prognostic predication and treatment recommendations. This novel analytical approach may provide accurate predication on individual survival and treatment recommendations for resected Stage-iii NSCLC patients.

A deep-learning algorithm to classify skin lesions from mpox virus infection

Undetected infection and delayed isolation of infected individuals are key factors driving the monkeypox virus (now termed mpox virus or MPXV) outbreak. To enable earlier detection of MPXV infection, we developed an image-based deep convolutional neural network (named MPXV-CNN) for the identification of the characteristic skin lesions caused by MPXV. We assembled a dataset of 139,198 skin lesion images, split into training/validation and testing cohorts, comprising non-MPXV images (n = 138,522) from eight dermatological repositories and MPXV images (n = 676) from the scientific literature, news articles, social media and a prospective cohort of the Stanford University Medical Center (n = 63 images from 12 patients, all male). In the validation and testing cohorts, the sensitivity of the MPXV-CNN was 0.83 and 0.91, the specificity was 0.965 and 0.898 and the area under the curve was 0.967 and 0.966, respectively. In the prospective cohort, the sensitivity was 0.89. The classification performance of the MPXV-CNN was robust across various skin tones and body regions. To facilitate the usage of the algorithm, we developed a web-based app by which the MPXV-CNN can be accessed for patient guidance. The capability of the MPXV-CNN for identifying MPXV lesions has the potential to aid in MPXV outbreak mitigation.

Artificial Intelligence and Cancer Control: Toward Prioritizing Justice, Equity, Diversity, and Inclusion (JEDI) in Emerging Decision Support Technologies

PURPOSE FOR REVIEW

This perspective piece has two goals: first, to describe issues related to artificial intelligence-based applications for cancer control as they may impact health inequities or disparities; and second, to report on a review of systematic reviews and meta-analyses of artificial intelligence-based tools for cancer control to ascertain the extent to which discussions of justice, equity, diversity, inclusion, or health disparities manifest in syntheses of the field's best evidence.

RECENT FINDINGS

We found that, while a significant proportion of existing syntheses of research on AI-based tools in cancer control use formal bias assessment tools, the fairness or equitability of models is not yet systematically analyzable across studies. Issues related to real-world use of AI-based tools for cancer control, such as workflow considerations, measures of usability and acceptance, or tool architecture, are more visible in the literature, but still addressed only in a minority of reviews. Artificial intelligence is poised to bring significant benefits to a wide range of applications in cancer control, but more thorough and standardized evaluations and reporting of model fairness are required to build the evidence base for AI-based tool design for cancer and to ensure that these emerging technologies promote equitable healthcare.