-
The Lancet. Digital Health Jun 2022Skin cancers occur commonly worldwide. The prognosis and disease burden are highly dependent on the cancer type and disease stage at diagnosis. We systematically... (Review)
Review
Skin cancers occur commonly worldwide. The prognosis and disease burden are highly dependent on the cancer type and disease stage at diagnosis. We systematically reviewed studies on artificial intelligence and machine learning (AI/ML) algorithms that aim to facilitate the early diagnosis of skin cancers, focusing on their application in primary and community care settings. We searched MEDLINE, Embase, Scopus, and Web of Science (from Jan 1, 2000, to Aug 9, 2021) for all studies providing evidence on applying AI/ML algorithms to the early diagnosis of skin cancer, including all study designs and languages. The primary outcome was diagnostic accuracy of the algorithms for skin cancers. The secondary outcomes included an overview of AI/ML methods, evaluation approaches, cost-effectiveness, and acceptability to patients and clinicians. We identified 14 224 studies. Only two studies used data from clinical settings with a low prevalence of skin cancers. We reported data from all 272 studies that could be relevant in primary care. The primary outcomes showed reasonable mean diagnostic accuracy for melanoma (89·5% [range 59·7-100%]), squamous cell carcinoma (85·3% [71·0-97·8%]), and basal cell carcinoma (87·6% [70·0-99·7%]). The secondary outcomes showed a heterogeneity of AI/ML methods and study designs, with high amounts of incomplete reporting (eg, patient demographics and methods of data collection). Few studies used data on populations with a low prevalence of skin cancers to train and test their algorithms; therefore, the widespread adoption into community and primary care practice cannot currently be recommended until efficacy in these populations is shown. We did not identify any health economic, patient, or clinician acceptability data for any of the included studies. We propose a methodological checklist for use in the development of new AI/ML algorithms to detect skin cancer, to facilitate their design, evaluation, and implementation.
Topics: Algorithms; Artificial Intelligence; Early Detection of Cancer; Humans; Machine Learning; Primary Health Care; Skin Neoplasms
PubMed: 35623799
DOI: 10.1016/S2589-7500(22)00023-1 -
Journal of Ambient Intelligence and... 2023Artificial intelligence can assist providers in a variety of patient care and intelligent health systems. Artificial intelligence techniques ranging from machine...
Artificial intelligence can assist providers in a variety of patient care and intelligent health systems. Artificial intelligence techniques ranging from machine learning to deep learning are prevalent in healthcare for disease diagnosis, drug discovery, and patient risk identification. Numerous medical data sources are required to perfectly diagnose diseases using artificial intelligence techniques, such as ultrasound, magnetic resonance imaging, mammography, genomics, computed tomography scan, etc. Furthermore, artificial intelligence primarily enhanced the infirmary experience and sped up preparing patients to continue their rehabilitation at home. This article covers the comprehensive survey based on artificial intelligence techniques to diagnose numerous diseases such as Alzheimer, cancer, diabetes, chronic heart disease, tuberculosis, stroke and cerebrovascular, hypertension, skin, and liver disease. We conducted an extensive survey including the used medical imaging dataset and their feature extraction and classification process for predictions. Preferred reporting items for systematic reviews and Meta-Analysis guidelines are used to select the articles published up to October 2020 on the Web of Science, Scopus, Google Scholar, PubMed, Excerpta Medical Database, and Psychology Information for early prediction of distinct kinds of diseases using artificial intelligence-based techniques. Based on the study of different articles on disease diagnosis, the results are also compared using various quality parameters such as prediction rate, accuracy, sensitivity, specificity, the area under curve precision, recall, and F1-score.
PubMed: 35039756
DOI: 10.1007/s12652-021-03612-z -
The Cochrane Database of Systematic... Mar 2013An acute burn wound is a complex and evolving injury. Extensive burns produce systemic consequences, in addition to local tissue damage. Treatment of partial thickness... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
An acute burn wound is a complex and evolving injury. Extensive burns produce systemic consequences, in addition to local tissue damage. Treatment of partial thickness burn wounds is directed towards promoting healing and a wide variety of dressings are currently available. Improvements in technology and advances in understanding of wound healing have driven the development of new dressings. Dressing selection should be based on their effects on healing, but ease of application and removal, dressing change requirements, cost and patient comfort should also be considered.
OBJECTIVES
To assess the effects of burn wound dressings on superficial and partial thickness burns.
SEARCH METHODS
For this first update we searched The Cochrane Wounds Group Specialised Register (searched 8 November 2012); The Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library 2012, Issue 10); Ovid MEDLINE (2008 to October Week 4 2012); Ovid MEDLINE (In-Process & Other Non-Indexed Citations, November 07, 2012); Ovid EMBASE (2008 to 2012 Week 44); AND EBSCO CINAHL (1982 to 2 November 2012).
SELECTION CRITERIA
All randomised controlled trials (RCTs) that evaluated the effects of burn wound dressings on the healing of superficial and partial thickness burns.
DATA COLLECTION AND ANALYSIS
Two authors extracted the data independently using standardised forms. We assessed each trial for internal validity and resolved differences by discussion.
MAIN RESULTS
A total of 30 RCTs are included in this review. Overall both the quality of trial reporting and trial conduct were generally poor and meta analysis was largely precluded due to study heterogeneity or poor data reporting. In the context of this poor quality evidence, silver sulphadiazine (SSD) was consistently associated with poorer healing outcomes than biosynthetic (skin substitute) dressings, silver-containing dressings and silicon-coated dressings. Burns treated with hydrogel dressings appear to heal more quickly than those treated with usual care.
AUTHORS' CONCLUSIONS
There is a paucity of high-quality evidence regarding the effect of different dressings on the healing of superficial and partial thickness burn injuries. The studies summarised in this review evaluated a variety of interventions, comparators and clinical endpoints and all were at risk of bias. It is impossible to draw firm and confident conclusions about the effectiveness of specific dressings, however silver sulphadiazine was consistently associated with poorer healing outcomes than biosynthetic, silicon-coated and silver dressings whilst hydrogel-treated burns had better healing outcomes than those treated with usual care.
Topics: Bandages; Bandages, Hydrocolloid; Burns; Humans; Randomized Controlled Trials as Topic; Silicon Compounds; Silver Sulfadiazine; Skin, Artificial; Wound Healing
PubMed: 23543513
DOI: 10.1002/14651858.CD002106.pub4 -
Evidence Report/technology Assessment Aug 2007To review and synthesize the literature in the following areas: the association of specific circulating 25(OH)D concentrations with bone health outcomes in children,... (Review)
Review
OBJECTIVES
To review and synthesize the literature in the following areas: the association of specific circulating 25(OH)D concentrations with bone health outcomes in children, women of reproductive age, postmenopausal women and elderly men; the effect of dietary intakes (foods fortified with vitamin D and/or vitamin D supplementation) and sun exposure on serum 25(OH)D; the effect of vitamin D on bone mineral density (BMD) and fracture or fall risk; and the identification of potential harms of vitamin D above current reference intakes.
DATA SOURCES
MEDLINE(R) (1966-June Week 3 2006); Embase (2002-2006 Week 25); CINAHL (1982-June Week 4, 2006); AMED (1985 to June 2006); Biological Abstracts (1990-February 2005); and the Cochrane Central Register of Controlled Trials (2nd Quarter 2006).
REVIEW METHODS
Two independent reviewers completed a multi-level process of screening the literature to identify eligible studies (title and abstract, followed by full text review, and categorization of study design per key question). To minimize bias, study design was limited to randomized controlled trials (RCTs) wherever possible. Study criteria for question one were broadened to include observational studies due to a paucity of available RCTs, and question four was restricted to systematic reviews to limit scope. Data were abstracted in duplicate and study quality assessed. Differences in opinion were resolved through consensus or adjudication. If clinically relevant and statistically feasible, meta-analyses of RCTs on vitamin D supplementation and bone health outcomes were conducted, with exploration of heterogeneity. When meta-analysis was not feasible, a qualitative systematic review of eligible studies was conducted.
RESULTS
167 studies met our eligibility criteria (112 RCTs, 19 prospective cohorts, 30 case-controls and six before-after studies). The largest body of evidence on vitamin D status and bone health was in older adults with a lack of studies in premenopausal women and infants, children and adolescents. The quality of RCTs was highest in the vitamin D efficacy trials for prevention of falls and/or fractures in older adults. There was fair evidence of an association between low circulating 25(OH)D concentrations and established rickets. However, the specific 25(OH)D concentrations associated with rickets is uncertain, given the lack of studies in populations with dietary calcium intakes similar to North American diets and the different methods used to determine 25(OH)D concentrations. There was inconsistent evidence of an association of circulating 25(OH)D with bone mineral content in infants, and fair evidence that serum 25(OH)D is inversely associated with serum PTH. In adolescents, there was fair evidence for an association between 25(OH)D levels and changes in BMD. There were very few studies in pregnant and lactating women, and insufficient evidence for an association between serum 25(OH)D and changes in BMD during lactation, and fair evidence of an inverse correlation with PTH. In older adults, there was fair evidence that serum 25(OH)D is inversely associated with falls, fair evidence for a positive association with BMD, and inconsistent evidence for an association with fractures. The imprecision of 25(OH)D assays may have contributed to the variable thresholds of 25(OH)D below which the risk of fractures, falls or bone loss was increased. There was good evidence that intakes from vitamin D-fortified foods (11 RCTs) consistently increased serum 25(OH)D in both young and older adults. Eight randomized trials of ultraviolet (UV)-B radiation (artificial and solar exposure) were small and heterogeneous with respect to determination of the exact UV-B dose and 25(OH)D assay but there was a positive effect on serum 25(OH)D concentrations. It was not possible to determine how 25(OH)D levels varied by ethnicity, sunscreen use or latitude. Seventy-four trials examined the effect of vitamin D(3) or D(2) on 25(OH)D concentrations. Most trials used vitamin D(3), and the majority enrolled older adults. In three trials, there was a greater response of serum 25(OH)D concentrations to vitamin D(3) compared to vitamin D(2), which may have been due to more rapid clearance of vitamin D(2) in addition to other mechanisms. Meta-analysis of 16 trials of vitamin D(3) was consistent with a dose-response effect on serum 25(OH)D when comparing daily doses of <400 IU to doses >/= 400 IU. An exploratory analysis of the heterogeneity demonstrated a significant positive association comparable to an increase of 1 - 2 nmol/L in serum 25(OH)D for every 100 additional units of vitamin D although heterogeneity remained after adjusting for dose. Vitamin D(3) in combination with calcium results in small increases in BMD compared to placebo in older adults although quantitative synthesis was limited due to variable treatment durations and BMD sites. The evidence for fracture reduction with vitamin D supplementation was inconsistent across 15 trials. The combined results of trials using vitamin D(3) (700 - 800 IU daily) with calcium (500 - 1,200 mg) was consistent with a benefit on fractures although in a subgroup analysis by setting, benefit was primarily in elderly institutionalized women (fair evidence from two trials). There was inconsistent evidence across 14 RCTs of a benefit on fall risk. However, a subgroup analysis showed a benefit of vitamin D in postmenopausal women, and in trials that used vitamin D(3) plus calcium. In addition, there was a reduction in fall risk with vitamin D when six trials that adequately ascertained falls were combined. Limitations of the fall and fracture trials included poor compliance with vitamin D supplementation, incomplete assessment of vitamin D status and large losses to follow-up. We did not find any systematic reviews that addressed the question on the level of sunlight exposure that is sufficient to maintain serum 25(OH)D concentrations but minimizes risk of melanoma and non-melanoma skin cancer. There is little evidence from existing trials that vitamin D above current reference intakes is harmful. In most trials, reports of hypercalcemia and hypercalciuria were not associated with clinically relevant events. The Women's Health Initiative study did report a small increase in kidney stones in postmenopausal women aged 50 to 79 years whose daily vitamin D(3) intake was 400 IU (the reference intake for 50 to 70 years, and below the reference intake for > 70 years) combined with 1000 mg calcium. The increase in renal stones corresponded to 5.7 events per 10,000 person-years of exposure. The women in this trial had higher calcium intakes than is seen in most post-menopausal women.
CONCLUSIONS
The results highlight the need for additional high quality studies in infants, children, premenopausal women, and diverse racial or ethnic groups. There was fair evidence from studies of an association between circulating 25(OH)D concentrations with some bone health outcomes (established rickets, PTH, falls, BMD). However, the evidence for an association was inconsistent for other outcomes (e.g., BMC in infants and fractures in adults). It was difficult to define specific thresholds of circulating 25(OH)D for optimal bone health due to the imprecision of different 25(OH)D assays. Standard reference preparations are needed so that serum 25(OH)D can be accurately and reliably measured, and validated. In most trials, the effects of vitamin D and calcium could not be separated. Vitamin D(3) (>700 IU/day) with calcium supplementation compared to placebo has a small beneficial effect on BMD, and reduces the risk of fractures and falls although benefit may be confined to specific subgroups. Vitamin D intake above current dietary reference intakes was not reported to be associated with an increased risk of adverse events. However, most trials of higher doses of vitamin D were not adequately designed to assess long-term harms.
Topics: Adolescent; Aged; Bone Density; Bone Density Conservation Agents; Bone and Bones; Child; Child, Preschool; Dietary Supplements; Female; Fractures, Bone; Humans; Infant; Lactation; Male; Osteoporosis, Postmenopausal; Pregnancy; Rickets; Sunlight; Ultraviolet Rays; Vitamin D; Vitamin D Deficiency
PubMed: 18088161
DOI: No ID Found -
European Journal of Cancer (Oxford,... Sep 2021Gastrointestinal cancers account for approximately 20% of all cancer diagnoses and are responsible for 22.5% of cancer deaths worldwide. Artificial intelligence-based...
BACKGROUND
Gastrointestinal cancers account for approximately 20% of all cancer diagnoses and are responsible for 22.5% of cancer deaths worldwide. Artificial intelligence-based diagnostic support systems, in particular convolutional neural network (CNN)-based image analysis tools, have shown great potential in medical computer vision. In this systematic review, we summarise recent studies reporting CNN-based approaches for digital biomarkers for characterization and prognostication of gastrointestinal cancer pathology.
METHODS
Pubmed and Medline were screened for peer-reviewed papers dealing with CNN-based gastrointestinal cancer analyses from histological slides, published between 2015 and 2020.Seven hundred and ninety titles and abstracts were screened, and 58 full-text articles were assessed for eligibility.
RESULTS
Sixteen publications fulfilled our inclusion criteria dealing with tumor or precursor lesion characterization or prognostic and predictive biomarkers: 14 studies on colorectal or rectal cancer, three studies on gastric cancer and none on esophageal cancer. These studies were categorised according to their end-points: polyp characterization, tumor characterization and patient outcome. Regarding the translation into clinical practice, we identified several studies demonstrating generalization of the classifier with external tests and comparisons with pathologists, but none presenting clinical implementation.
CONCLUSIONS
Results of recent studies on CNN-based image analysis in gastrointestinal cancer pathology are promising, but studies were conducted in observational and retrospective settings. Large-scale trials are needed to assess performance and predict clinical usefulness. Furthermore, large-scale trials are required for approval of CNN-based prediction models as medical devices.
Topics: Deep Learning; Gastrointestinal Neoplasms; Humans; Treatment Outcome
PubMed: 34391053
DOI: 10.1016/j.ejca.2021.07.012 -
Clinical Oral Implants Research Sep 2009The aim of the present review was to systematically assess the dental literature in terms of soft tissue grafting techniques. The focused question was: is one method... (Meta-Analysis)
Meta-Analysis Review
AIM
The aim of the present review was to systematically assess the dental literature in terms of soft tissue grafting techniques. The focused question was: is one method superior over others for augmentation and stability of the augmented soft tissue in terms of increasing the width of keratinized tissue (part 1) and gain in soft tissue volume (part 2).
METHODS
A Medline search was performed for human studies focusing on augmentation of keratinized tissue and/or soft tissue volume, and complemented by additional hand searching. Relevant studies were identified and statistical results were reported for meta-analyses including the test minus control weighted mean differences with 95% confidence intervals, the I-squared statistic for tests of heterogeneity, and the number of significant studies.
RESULTS
Twenty-five (part 1) and three (part 2) studies met the inclusion criteria; 14 studies (part 1) were eligible for comparison using meta-analyses. An apically positioned flap/vestibuloplasty (APF/V) procedure resulted in a statistically significantly greater gain in keratinized tissue than untreated controls. APF/V plus autogenous tissue revealed statistically significantly more attached gingiva compared with untreated controls and a borderline statistical significance compared with APF/V plus allogenic tissue. Statistically significantly more shrinkage was observed for the APF/V plus allogenic graft compared with the APF/V plus autogenous tissue. Patient-centered outcomes did not reveal any of the treatment methods to be superior regarding postoperative complications. The three studies reporting on soft tissue volume augmentation could not be compared due to lack of homogeneity. The use of subepithelial connective tissue grafts (SCTGs) resulted in statistically significantly more soft tissue volume gain compared with free gingival grafts (FGGs).
CONCLUSIONS
APF/V is a successful treatment concept to increase the width of keratinized tissue or attached gingiva around teeth. The addition of autogenous tissue statistically significantly increases the width of attached gingiva. For soft tissue volume augmentation, only limited data are available favoring SCTGs over FGG.
Topics: Collagen; Connective Tissue; Gingiva; Gingivoplasty; Humans; Keratins; Skin, Artificial; Vestibuloplasty
PubMed: 19663961
DOI: 10.1111/j.1600-0501.2009.01784.x -
Diagnostics (Basel, Switzerland) Oct 2023Skin lesions are essential for the early detection and management of a number of dermatological disorders. Learning-based methods for skin lesion analysis have drawn... (Review)
Review
Skin lesions are essential for the early detection and management of a number of dermatological disorders. Learning-based methods for skin lesion analysis have drawn much attention lately because of improvements in computer vision and machine learning techniques. A review of the most-recent methods for skin lesion classification, segmentation, and detection is presented in this survey paper. The significance of skin lesion analysis in healthcare and the difficulties of physical inspection are discussed in this survey paper. The review of state-of-the-art papers targeting skin lesion classification is then covered in depth with the goal of correctly identifying the type of skin lesion from dermoscopic, macroscopic, and other lesion image formats. The contribution and limitations of various techniques used in the selected study papers, including deep learning architectures and conventional machine learning methods, are examined. The survey then looks into study papers focused on skin lesion segmentation and detection techniques that aimed to identify the precise borders of skin lesions and classify them accordingly. These techniques make it easier to conduct subsequent analyses and allow for precise measurements and quantitative evaluations. The survey paper discusses well-known segmentation algorithms, including deep-learning-based, graph-based, and region-based ones. The difficulties, datasets, and evaluation metrics particular to skin lesion segmentation are also discussed. Throughout the survey, notable datasets, benchmark challenges, and evaluation metrics relevant to skin lesion analysis are highlighted, providing a comprehensive overview of the field. The paper concludes with a summary of the major trends, challenges, and potential future directions in skin lesion classification, segmentation, and detection, aiming to inspire further advancements in this critical domain of dermatological research.
PubMed: 37835889
DOI: 10.3390/diagnostics13193147 -
NPJ Digital Medicine May 2024Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and... (Review)
Review
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.
PubMed: 38744955
DOI: 10.1038/s41746-024-01103-x -
European Journal of Cancer (Oxford,... May 2022Due to their ability to solve complex problems, deep neural networks (DNNs) are becoming increasingly popular in medical applications. However, decision-making by such... (Review)
Review
BACKGROUND
Due to their ability to solve complex problems, deep neural networks (DNNs) are becoming increasingly popular in medical applications. However, decision-making by such algorithms is essentially a black-box process that renders it difficult for physicians to judge whether the decisions are reliable. The use of explainable artificial intelligence (XAI) is often suggested as a solution to this problem. We investigate how XAI is used for skin cancer detection: how is it used during the development of new DNNs? What kinds of visualisations are commonly used? Are there systematic evaluations of XAI with dermatologists or dermatopathologists?
METHODS
Google Scholar, PubMed, IEEE Explore, Science Direct and Scopus were searched for peer-reviewed studies published between January 2017 and October 2021 applying XAI to dermatological images: the search terms histopathological image, whole-slide image, clinical image, dermoscopic image, skin, dermatology, explainable, interpretable and XAI were used in various combinations. Only studies concerned with skin cancer were included.
RESULTS
37 publications fulfilled our inclusion criteria. Most studies (19/37) simply applied existing XAI methods to their classifier to interpret its decision-making. Some studies (4/37) proposed new XAI methods or improved upon existing techniques. 14/37 studies addressed specific questions such as bias detection and impact of XAI on man-machine-interactions. However, only three of them evaluated the performance and confidence of humans using CAD systems with XAI.
CONCLUSION
XAI is commonly applied during the development of DNNs for skin cancer detection. However, a systematic and rigorous evaluation of its usefulness in this scenario is lacking.
Topics: Algorithms; Artificial Intelligence; Humans; Neural Networks, Computer; Skin Neoplasms
PubMed: 35390650
DOI: 10.1016/j.ejca.2022.02.025 -
Frontiers in Medicine 2023Skin cancer is one of the most common forms worldwide, with a significant increase in incidence over the last few decades. Early and accurate detection of this type of...
BACKGROUND
Skin cancer is one of the most common forms worldwide, with a significant increase in incidence over the last few decades. Early and accurate detection of this type of cancer can result in better prognoses and less invasive treatments for patients. With advances in Artificial Intelligence (AI), tools have emerged that can facilitate diagnosis and classify dermatological images, complementing traditional clinical assessments and being applicable where there is a shortage of specialists. Its adoption requires analysis of efficacy, safety, and ethical considerations, as well as considering the genetic and ethnic diversity of patients.
OBJECTIVE
The systematic review aims to examine research on the detection, classification, and assessment of skin cancer images in clinical settings.
METHODS
We conducted a systematic literature search on PubMed, Scopus, Embase, and Web of Science, encompassing studies published until April 4th, 2023. Study selection, data extraction, and critical appraisal were carried out by two independent reviewers. Results were subsequently presented through a narrative synthesis.
RESULTS
Through the search, 760 studies were identified in four databases, from which only 18 studies were selected, focusing on developing, implementing, and validating systems to detect, diagnose, and classify skin cancer in clinical settings. This review covers descriptive analysis, data scenarios, data processing and techniques, study results and perspectives, and physician diversity, accessibility, and participation.
CONCLUSION
The application of artificial intelligence in dermatology has the potential to revolutionize early detection of skin cancer. However, it is imperative to validate and collaborate with healthcare professionals to ensure its clinical effectiveness and safety.
PubMed: 38259845
DOI: 10.3389/fmed.2023.1305954