RESUMEN

Introduction: An artificial intelligence as a medical device (AIaMD), built on convolutional neural networks, has demonstrated high sensitivity for melanoma. To be of clinical value, it needs to safely reduce referral rates. The primary objective of this study was to demonstrate that the AIaMD had a higher rate of correctly classifying lesions that did not need to be referred for biopsy or urgent face-to-face dermatologist review, compared to teledermatology standard of care (SoC), while achieving the same sensitivity to detect malignancy. Secondary endpoints included the sensitivity, specificity, positive and negative predictive values, and number needed to biopsy to identify one case of melanoma or squamous cell carcinoma (SCC) by both the AIaMD and SoC. Methods: This prospective, single-centre, single-arm, masked, non-inferiority, adaptive, group sequential design trial recruited patients referred to a teledermatology cancer pathway (clinicaltrials.gov NCT04123678). Additional dermoscopic images of each suspicious lesion were taken using a smartphone with a dermoscopic lens attachment. The images were assessed independently by a consultant dermatologist and the AIaMD. The outputs were compared with the final histological or clinical diagnosis. Results: A total of 700 patients with 867 lesions were recruited, of which 622 participants with 789 lesions were included in the per-protocol (PP) population. In total, 63.3% of PP participants were female; 89.0% identified as white, and the median age was 51 (range 18-95); and all Fitzpatrick skin types were represented including 25/622 (4.0%) type IV-VI skin. A total of 67 malignant lesions were identified, including 8 diagnosed as melanoma. The AIaMD sensitivity was set at 91 and 92.5%, to match the literature-defined clinician sensitivity (91.46%) as closely as possible. In both settings, the AIaMD identified had a significantly higher rate of identifying lesions that did not need a biopsy or urgent referral compared to SoC (p-value = 0.001) with comparable sensitivity for skin cancer. Discussion: The AIaMD identified significantly more lesions that did not need to be referred for biopsy or urgent face-to-face dermatologist review, compared to teledermatologists. This has the potential to reduce the burden of unnecessary referrals when used as part of a teledermatology service.

RESUMEN

The use of artificial intelligence as a medical device (AIaMD) in healthcare systems is increasing rapidly. In dermatology, this has been accelerated in response to increasing skin cancer referral rates, workforce shortages and backlog generated by the COVID-19 pandemic. Evidence regarding patient perspectives of AIaMD is currently lacking in the literature. Patient acceptability is fundamental if this novel technology is to be effectively integrated into care pathways and patients must be confident that it is implemented safely, legally, and ethically. A prospective, single-center, single-arm, masked, non-inferiority, adaptive, group sequential design trial, recruited patients referred to a teledermatology cancer pathway. AIaMD assessment of dermoscopic images were compared with clinical or histological diagnosis, to assess performance (NCT04123678). Participants completed an online questionnaire to evaluate their views regarding use of AIaMD in the skin cancer pathway. Two hundred and sixty eight responses were received between February 2020 and August 2021. The majority of respondents were female (57.5%), ranged in age between 18 and 93 years old, Fitzpatrick type I-II skin (81.3%) and all 6 skin types were represented. Overall, there was a positive sentiment regarding potential use of AIaMD in skin cancer pathways. The majority of respondents felt confident in computers being used to help doctors diagnose and formulate management plans (median = 70; interquartile range (IQR) = 50-95) and as a support tool for general practitioners when assessing skin lesions (median = 85; IQR = 65-100). Respondents were comfortable having their photographs taken with a mobile phone device (median = 95; IQR = 70-100), which is similar to other studies assessing patient acceptability of teledermatology services. To the best of our knowledge, this is the first comprehensive study evaluating patient perspectives of AIaMD in skin cancer pathways in the UK. Patient involvement is essential for the development and implementation of new technologies. Continued end-user feedback will allow refinement of services to ensure patient acceptability. This study demonstrates patient acceptability of the use of AIaMD in both primary and secondary care settings.

RESUMEN

Introduction: Identification of skin cancer by an Artificial Intelligence (AI)-based Digital Health Technology could help improve the triage and management of suspicious skin lesions. Methods: The DERM-003 study (NCT04116983) was a prospective, multi-center, single-arm, masked study that aimed to demonstrate the effectiveness of an AI as a Medical Device (AIaMD) to identify Squamous Cell Carcinoma (SCC), Basal Cell Carcinoma (BCC), pre-malignant and benign lesions from dermoscopic images of suspicious skin lesions. Suspicious skin lesions that were suitable for photography were photographed with 3 smartphone cameras (iPhone 6S, iPhone 11, Samsung 10) with a DL1 dermoscopic lens attachment. Dermatologists provided clinical diagnoses and histopathology results were obtained for biopsied lesions. Each image was assessed by the AIaMD and the output compared to the ground truth diagnosis. Results: 572 patients (49.5% female, mean age 68.5 years, 96.9% Fitzpatrick skin types I-III) were recruited from 4 UK NHS Trusts, providing images of 611 suspicious lesions. 395 (64.6%) lesions were biopsied; 47 (11%) were diagnosed as SCC and 184 (44%) as BCC. The AIaMD AUROC on images taken by iPhone 6S was 0.88 (95% CI: 0.83-0.93) for SCC and 0.87 (95% CI: 0.84-0.91) for BCC. For Samsung 10 the AUROCs were 0.85 (95% CI: 0.79-0.90) and 0.87 (95% CI, 0.83-0.90), and for the iPhone 11 they were 0.88 (95% CI, 0.84-0.93) and 0.89 (95% CI, 0.86-0.92) for SCC and BCC, respectively. Using pre-determined diagnostic thresholds on images taken on the iPhone 6S the AIaMD achieved a sensitivity and specificity of 98% (95% CI, 88-100%) and 38% (95% CI, 33-44%) for SCC; and 94% (95% CI, 90-97%) and 28% (95 CI, 21-35%) for BCC. All 16 lesions diagnosed as melanoma in the study were correctly classified by the AIaMD. Discussion: The AIaMD has the potential to support the timely diagnosis of malignant and premalignant skin lesions.

Asunto(s)

RESUMEN

BACKGROUND: Malignant melanoma can most successfully be cured when diagnosed at an early stage in the natural history. However, there is controversy over screening programs and many advocate screening only for high-risk individuals. OBJECTIVES: This study aimed to evaluate the accuracy of an artificial intelligence neural network (Deep Ensemble for Recognition of Melanoma [DERM]) to identify malignant melanoma from dermoscopic images of pigmented skin lesions and to show how this compared to doctors' performance assessed by meta-analysis. METHODS: DERM was trained and tested using 7,102 dermoscopic images of both histologically confirmed melanoma (24%) and benign pigmented lesions (76%). A meta-analysis was conducted of studies examining the accuracy of naked-eye examination, with or without dermoscopy, by specialist and general physicians whose clinical diagnosis was compared to histopathology. The meta-analysis was based on evaluation of 32,226 pigmented lesions including 3,277 histopathology-confirmed malignant melanoma cases. The receiver operating characteristic (ROC) curve was used to examine and compare the diagnostic accuracy. RESULTS: DERM achieved a ROC area under the curve (AUC) of 0.93 (95% confidence interval: 0.92-0.94), and sensitivity and specificity of 85.0% and 85.3%, respectively. Avoidance of false-negative results is essential, so different decision thresholds were examined. At 95% sensitivity DERM achieved a specificity of 64.1% and at 95% specificity the sensitivity was 67%. The meta-analysis showed primary care physicians (10 studies) achieve an AUC of 0.83 (95% confidence interval: 0.79-0.86), with sensitivity and specificity of 79.9% and 70.9%; and dermatologists (92 studies) 0.91 (0.88-0.93), 87.5%, and 81.4%, respectively. CONCLUSIONS: DERM has the potential to be used as a decision support tool in primary care, by providing dermatologist-grade recommendation on the likelihood of malignant melanoma.

RESUMEN

Importance: A high proportion of suspicious pigmented skin lesions referred for investigation are benign. Techniques to improve the accuracy of melanoma diagnoses throughout the patient pathway are needed to reduce the pressure on secondary care and pathology services. Objective: To determine the accuracy of an artificial intelligence algorithm in identifying melanoma in dermoscopic images of lesions taken with smartphone and digital single-lens reflex (DSLR) cameras. Design, Setting, and Participants: This prospective, multicenter, single-arm, masked diagnostic trial took place in dermatology and plastic surgery clinics in 7 UK hospitals. Dermoscopic images of suspicious and control skin lesions from 514 patients with at least 1 suspicious pigmented skin lesion scheduled for biopsy were captured on 3 different cameras. Data were collected from January 2017 to July 2018. Clinicians and the Deep Ensemble for Recognition of Malignancy, a deterministic artificial intelligence algorithm trained to identify melanoma in dermoscopic images of pigmented skin lesions using deep learning techniques, assessed the likelihood of melanoma. Initial data analysis was conducted in September 2018; further analysis was conducted from February 2019 to August 2019. Interventions: Clinician and algorithmic assessment of melanoma. Main Outcomes and Measures: Area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity of the algorithmic and specialist assessment, determined using histopathology diagnosis as the criterion standard. Results: The study population of 514 patients included 279 women (55.7%) and 484 white patients (96.8%), with a mean (SD) age of 52.1 (18.6) years. A total of 1550 images of skin lesions were included in the analysis (551 [35.6%] biopsied lesions; 999 [64.4%] control lesions); 286 images (18.6%) were used to train the algorithm, and a further 849 (54.8%) images were missing or unsuitable for analysis. Of the biopsied lesions that were assessed by the algorithm and specialists, 125 (22.7%) were diagnosed as melanoma. Of these, 77 (16.7%) were used for the primary analysis. The algorithm achieved an AUROC of 90.1% (95% CI, 86.3%-94.0%) for biopsied lesions and 95.8% (95% CI, 94.1%-97.6%) for all lesions using iPhone 6s images; an AUROC of 85.8% (95% CI, 81.0%-90.7%) for biopsied lesions and 93.8% (95% CI, 91.4%-96.2%) for all lesions using Galaxy S6 images; and an AUROC of 86.9% (95% CI, 80.8%-93.0%) for biopsied lesions and 91.8% (95% CI, 87.5%-96.1%) for all lesions using DSLR camera images. At 100% sensitivity, the algorithm achieved a specificity of 64.8% with iPhone 6s images. Specialists achieved an AUROC of 77.8% (95% CI, 72.5%-81.9%) and a specificity of 69.9%. Conclusions and Relevance: In this study, the algorithm demonstrated an ability to identify melanoma from dermoscopic images of selected lesions with an accuracy similar to that of specialists.

Asunto(s)

RESUMEN

BACKGROUND: Allergic Rhinitis is an inflammatory disease which is characterised by burdensome nasal and/or ocular symptoms. This study aimed to assess the impact of symptoms (number of symptom-free days (SFD) and Quality of Life (QoL)) in patients with Seasonal Allergic Rhinitis (SAR) being treated with fluticasone furoate (FF), mometasone furoate (MF) or fluticasone propionate (FP). METHODS: In a cross-sectional, non-interventional, cohort analysis, primary care physicians and allergy specialists in France, Germany, and Spain were recruited via telephone interviews. Each physician prospectively recruited 4 SAR patients - 2 receiving FF, 1 receiving MF and 1 receiving FP - during June 2009. Patients answered questions on symptoms and completed questionnaires on QoL (mini-rhinoconjunctivitis Quality of Life Questionnaire, RQLQ) and burden of illness (Pittsburgh Sleep Quality Index). RESULTS: A total of 540 patients were recruited during June 2009. 88 patients were subsequently found to be ineligible and excluded from the analyses. In the 4 weeks prior to assessment, patients reported a mean of 14.58 (±8.42) SFD. Patients receiving FF had more SFD (mean 15.45 ±8.29) than patients receiving MF (adjusted mean difference -1.22, 95% Confidence Interval (CI) [-3.16 to 0.72], p=0.434) or FP (adjusted mean difference -1.95, 95% CI [-3.87 to -0.03], p=0.092), although statistical significance was not achieved. The mean RQLQ score was 1.54 (±1.06). Patients receiving FF had a better quality of life in the previous week (mini-RQLQ score: mean 1.42, ±1.04) than patients receiving MF (adjusted mean difference 0.28, 95% CI [0.03 to 0.52], p=0.052) or FP (adjusted mean difference 0.18, 95% CI [-0.05 to 0.41], p=0.244). Again, none of these results achieved statistical significance. CONCLUSIONS: At the height of the allergy season, patients with SAR suffer symptoms approximately 50% of the time, and report an impact on their QoL. No significant differences were observed between FF, FP and MF related to SFD or QoL. TRIAL REGISTRATION: ClinicalTrials.gov identifier: NCT01199757.

RESUMEN

The quality of a consultation provided by a physician can have a profound impact on the quality of care and patient engagement in treatment decisions. When the COPD Assessment Test (CAT) was developed, one of its aims was to aid the communication between physician and patient about the impact of COPD. We developed a novel study design to assess this in a primary care consultation. Primary care physicians across five countries in Europe conducted videoed consultations with six standardised COPD patients (played by trained actors) which had patient-specific issues that the physician needed to identify through questioning. Half the physicians saw the patients with the completed CAT, and half without. Independent assessors scored the physicians on their ability to identify and address the patient-specific issues, review standard COPD aspects, their understanding of the case and their overall performance. This novel study design presented many challenges which needed to be addressed to achieve an acceptable level of robustness to assess the utility of the CAT. This paper discusses these challenges and the measures adopted to eliminate or minimise their impact on the study results.

Asunto(s)

RESUMEN

BACKGROUND: One of the aims of the COPD Assessment Test (CAT) is to aid communication between the physician and patient about the burden of chronic obstructive pulmonary disease (COPD) on the patient's life. AIMS: To investigate the impact of the CAT on the quality of primary care consultations in COPD patients. METHODS: Primary care physicians across Europe conducted six consultations with standardised COPD patients (played by trained actors). Physicians were randomised to see the patient with the completed CAT (CAT+ arm) or without (no CAT arm) during the consultation. These were videoed and independent assessors scored the physicians on their ability to identify and address patient-specific issues such as depression (sub-score A); review standard COPD issues such as breathlessness (sub-score B); their understanding of the case (understanding score); and their overall performance. The primary endpoint was the global score (sub-scores A+B; scale range 0-40). RESULTS: A total of 165 physicians enrolled in the study and carried out six consultations each; 882 consultations were deemed suitable for analysis. No difference was seen between the arms in the global score (no CAT arm 20.3; CAT+ arm 20.7; 95% CI -1.0 to 1.8; p=0.606) or on sub-score A (p=0.255). A statistically significant difference, though of limited clinical relevance, was observed in mean sub-score B (no CAT arm 8.8; CAT+ arm 9.6; 95% CI 0.0 to 1.6; p=0.045). There was no difference in understanding score (p=0.824) or overall performance (p=0.655). CONCLUSIONS: The CAT is a disease-specific instrument that aids physician assessment of COPD. It does not appear to improve detection of non-COPD symptoms and co-morbidities.

Asunto(s)

RESUMEN

A gas-phase electron diffraction study of the azoxy compound which was synthesized by the reaction of CF3NO with N2F4 in a Pyrex glass vessel results in a trans CF3N(O)NF structure (F trans to CF3), although quantum chemical calculations (MP2 and B3LYP) predict a greater stability of the cis CF3NN(O)F isomer by about 12 kcal/mol. The CF3 group eclipses the N=N double bond. The following skeletal geometric parameters (r(a) values with 3sigma uncertainties) were obtained: N=N 1.287(15) A; N=O 1.231(6) A; N-F 1.380(6) A; N-C 1.498(6) A; N=N=O 131.2(13) degrees; N=N-F 103.5(13) degrees; N=N-C 114.0(12) degrees. The bond lengths in CF3N(O)NF are compared to those in azo, nitryl, and nitrosyl compounds with fluorine and/or CF3 substituents.