Smartphone applications for triaging adults with skin lesions that are suspicious for melanoma.

BACKGROUND: Melanoma accounts for a small proportion of all skin cancer cases but is responsible for most skin cancer-related deaths. Early detection and treatment can improve survival. Smartphone applications are readily accessible and potentially offer an instant risk assessment of the likelihood of malignancy so that the right people seek further medical attention from a clinician for more detailed assessment of the lesion. There is, however, a risk that melanomas will be missed and treatment delayed if the application reassures the user that their lesion is low risk. OBJECTIVES: To assess the diagnostic accuracy of smartphone applications to rule out cutaneous invasive melanoma and atypical intraepidermal melanocytic variants in adults with concerns about suspicious skin lesions. SEARCH METHODS: We undertook a comprehensive search of the following databases from inception to August 2016: Cochrane Central Register of Controlled Trials; MEDLINE; Embase; CINAHL; CPCI; Zetoc; Science Citation Index; US National Institutes of Health Ongoing Trials Register; NIHR Clinical Research Network Portfolio Database; and the World Health Organization International Clinical Trials Registry Platform. We studied reference lists and published systematic review articles. SELECTION CRITERIA: Studies of any design evaluating smartphone applications intended for use by individuals in a community setting who have lesions that might be suspicious for melanoma or atypical intraepidermal melanocytic variants versus a reference standard of histological confirmation or clinical follow-up and expert opinion. DATA COLLECTION AND ANALYSIS: Two review authors independently extracted all data using a standardised data extraction and quality assessment form (based on QUADAS-2). Due to scarcity of data and poor quality of studies, we did not perform a meta-analysis for this review. For illustrative purposes, we plotted estimates of sensitivity and specificity on coupled forest plots for each application under consideration. MAIN RESULTS: This review reports on two cohorts of lesions published in two studies. Both studies were at high risk of bias from selective participant recruitment and high rates of non-evaluable images. Concerns about applicability of findings were high due to inclusion only of lesions already selected for excision in a dermatology clinic setting, and image acquisition by clinicians rather than by smartphone app users.We report data for five mobile phone applications and 332 suspicious skin lesions with 86 melanomas across the two studies. Across the four artificial intelligence-based applications that classified lesion images (photographs) as melanomas (one application) or as high risk or 'problematic' lesions (three applications) using a pre-programmed algorithm, sensitivities ranged from 7% (95% CI 2% to 16%) to 73% (95% CI 52% to 88%) and specificities from 37% (95% CI 29% to 46%) to 94% (95% CI 87% to 97%). The single application using store-and-forward review of lesion images by a dermatologist had a sensitivity of 98% (95% CI 90% to 100%) and specificity of 30% (95% CI 22% to 40%).The number of test failures (lesion images analysed by the applications but classed as 'unevaluable' and excluded by the study authors) ranged from 3 to 31 (or 2% to 18% of lesions analysed). The store-and-forward application had one of the highest rates of test failure (15%). At least one melanoma was classed as unevaluable in three of the four application evaluations. AUTHORS' CONCLUSIONS: Smartphone applications using artificial intelligence-based analysis have not yet demonstrated sufficient promise in terms of accuracy, and they are associated with a high likelihood of missing melanomas. Applications based on store-and-forward images could have a potential role in the timely presentation of people with potentially malignant lesions by facilitating active self-management health practices and early engagement of those with suspicious skin lesions; however, they may incur a significant increase in resource and workload. Given the paucity of evidence and low methodological quality of existing studies, it is not possible to draw any implications for practice. Nevertheless, this is a rapidly advancing field, and new and better applications with robust reporting of studies could change these conclusions substantially.

Teledermatology for diagnosing skin cancer in adults.

BACKGROUND: Early accurate detection of all skin cancer types is essential to guide appropriate management and to improve morbidity and survival. Melanoma and squamous cell carcinoma (SCC) are high-risk skin cancers which have the potential to metastasise and ultimately lead to death, whereas basal cell carcinoma (BCC) is usually localised with potential to infiltrate and damage surrounding tissue. Anxiety around missing early curable cases needs to be balanced against inappropriate referral and unnecessary excision of benign lesions. Teledermatology provides a way for generalist clinicians to access the opinion of a specialist dermatologist for skin lesions that they consider to be suspicious without referring the patients through the normal referral pathway. Teledermatology consultations can be 'store-and-forward' with electronic digital images of a lesion sent to a dermatologist for review at a later time, or can be live and interactive consultations using videoconferencing to connect the patient, referrer and dermatologist in real time. OBJECTIVES: To determine the diagnostic accuracy of teledermatology for the detection of any skin cancer (melanoma, BCC or cutaneous squamous cell carcinoma (cSCC)) in adults, and to compare its accuracy with that of in-person diagnosis. SEARCH METHODS: We undertook a comprehensive search of the following databases from inception up to August 2016: Cochrane Central Register of Controlled Trials, MEDLINE, Embase, CINAHL, CPCI, Zetoc, Science Citation Index, US National Institutes of Health Ongoing Trials Register, NIHR Clinical Research Network Portfolio Database and the World Health Organization International Clinical Trials Registry Platform. We studied reference lists and published systematic review articles. SELECTION CRITERIA: Studies evaluating skin cancer diagnosis for teledermatology alone, or in comparison with face-to-face diagnosis by a specialist clinician, compared with a reference standard of histological confirmation or clinical follow-up and expert opinion. We also included studies evaluating the referral accuracy of teledermatology compared with a reference standard of face-to-face diagnosis by a specialist clinician. DATA COLLECTION AND ANALYSIS: Two review authors independently extracted all data using a standardised data extraction and quality assessment form (based on QUADAS-2). We contacted authors of included studies where there were information related to the target condition of any skin cancer missing. Data permitting, we estimated summary sensitivities and specificities using the bivariate hierarchical model. Due to the scarcity of data, we undertook no covariate investigations for this review. For illustrative purposes, we plotted estimates of sensitivity and specificity on coupled forest plots for diagnostic threshold and target condition under consideration. MAIN RESULTS: The review included 22 studies reporting diagnostic accuracy data for 4057 lesions and 879 malignant cases (16 studies) and referral accuracy data for reported data for 1449 lesions and 270 'positive' cases as determined by the reference standard face-to-face decision (six studies). Methodological quality was variable with poor reporting hindering assessment. The overall risk of bias was high or unclear for participant selection, reference standard, and participant flow and timing in at least half of all studies; the majority were at low risk of bias for the index test. The applicability of study findings were of high or unclear concern for most studies in all domains assessed due to the recruitment of participants from secondary care settings or specialist clinics rather than from primary or community-based settings in which teledermatology is more likely to be used and due to the acquisition of lesion images by dermatologists or in specialist imaging units rather than by primary care clinicians.Seven studies provided data for the primary target condition of any skin cancer (1588 lesions and 638 malignancies). For the correct diagnosis of lesions as malignant using photographic images, summary sensitivity was 94.9% (95% confidence interval (CI) 90.1% to 97.4%) and summary specificity was 84.3% (95% CI 48.5% to 96.8%) (from four studies). Individual study estimates using dermoscopic images or a combination of photographic and dermoscopic images generally suggested similarly high sensitivities with highly variable specificities. Limited comparative data suggested similar diagnostic accuracy between teledermatology assessment and in-person diagnosis by a dermatologist; however, data were too scarce to draw firm conclusions. For the detection of invasive melanoma or atypical intraepidermal melanocytic variants both sensitivities and specificities were more variable. Sensitivities ranged from 59% (95% CI 42% to 74%) to 100% (95% CI 48% to 100%) and specificities from 30% (95% CI 22% to 40%) to 100% (95% CI 93% to 100%), with reported diagnostic thresholds including the correct diagnosis of melanoma, classification of lesions as 'atypical' or 'typical, and the decision to refer or to excise a lesion.Referral accuracy data comparing teledermatology against a face-to-face reference standard suggested good agreement for lesions considered to require some positive action by face-to-face assessment (sensitivities of over 90%). For lesions considered of less concern when assessed face-to-face (e.g. for lesions not recommended for excision or referral), agreement was more variable with teledermatology specificities ranging from 57% (95% CI 39% to 73%) to 100% (95% CI 86% to 100%), suggesting that remote assessment is more likely recommend excision, referral or follow-up compared to in-person decisions. AUTHORS' CONCLUSIONS: Studies were generally small and heterogeneous and methodological quality was difficult to judge due to poor reporting. Bearing in mind concerns regarding the applicability of study participants and of lesion image acquisition in specialist settings, our results suggest that teledermatology can correctly identify the majority of malignant lesions. Using a more widely defined threshold to identify 'possibly' malignant cases or lesions that should be considered for excision is likely to appropriately triage those lesions requiring face-to-face assessment by a specialist. Despite the increasing use of teledermatology on an international level, the evidence base to support its ability to accurately diagnose lesions and to triage lesions from primary to secondary care is lacking and further prospective and pragmatic evaluation is needed.

Use of user-centered design to create a smartphone application for patient-reported outcomes in atopic dermatitis.

The ubiquity and convenience of smartphones carries great potential for collecting patient-reported data to address many gaps in research, especially those that rely on ongoing, real-time data collection. Health care apps have often suffered from low utility due to lack of consideration of the needs of multiple stakeholders. We employed an iterative user-centered design approach to create the myEczema smartphone application (app) to study the burden of disease of atopic dermatitis. We outline below the steps we took for developing myEczema for multiple stakeholders, including patients, clinicians, and researchers.

Incidence of and Risk Factors for Skin Cancer in Organ Transplant Recipients in the United States.

Importance: Skin cancer is the most common malignancy occurring after organ transplantation. Although previous research has reported an increased risk of skin cancer in solid organ transplant recipients (OTRs), no study has estimated the posttransplant population-based incidence in the United States. Objective: To determine the incidence and evaluate the risk factors for posttransplant skin cancer, including squamous cell carcinoma (SCC), melanoma (MM), and Merkel cell carcinoma (MCC) in a cohort of US OTRs receiving a primary organ transplant in 2003 or 2008. Design, Setting, and Participants: This multicenter retrospective cohort study examined 10 649 adult recipients of a primary transplant performed at 26 centers across the United States in the Transplant Skin Cancer Network during 1 of 2 calendar years (either 2003 or 2008) identified through the Organ Procurement and Transplantation Network (OPTN) database. Recipients of all organs except intestine were included, and the follow-up periods were 5 and 10 years. Main Outcomes and Measures: Incident skin cancer was determined through detailed medical record review. Data on predictors were obtained from the OPTN database. The incidence rates for posttransplant skin cancer overall and for SCC, MM, and MCC were calculated per 100 000 person-years. Potential risk factors for posttransplant skin cancer were tested using multivariate Cox regression analysis to yield adjusted hazard ratios (HR). Results: Overall, 10 649 organ transplant recipients (mean [SD] age, 51 [12] years; 3873 women [36%] and 6776 men [64%]) contributed 59 923 years of follow-up. The incidence rates for posttransplant skin cancer was 1437 per 100 000 person-years. Specific subtype rates for SCC, MM, and MCC were 812, 75, and 2 per 100 000 person-years, respectively. Statistically significant risk factors for posttransplant skin cancer included pretransplant skin cancer (HR, 4.69; 95% CI, 3.26-6.73), male sex (HR, 1.56; 95% CI, 1.34-1.81), white race (HR, 9.04; 95% CI, 6.20-13.18), age at transplant 50 years or older (HR, 2.77; 95% CI, 2.20-3.48), and being transplanted in 2008 vs 2003 (HR, 1.53; 95% CI, 1.22-1.94). Conclusions and Relevance: Posttransplant skin cancer is common, with elevated risk imparted by increased age, white race, male sex, and thoracic organ transplantation. A temporal cohort effect was present. Understanding the risk factors and trends in posttransplant skin cancer is fundamental to targeted screening and prevention in this population.

Prevalence and impact of health-related internet and smartphone use among dermatology patients.

Health information is increasingly accessible via the Internet and smartphone applications (apps), and patients may perceive these resources as tools for self-education and/or self-diagnosis. The objective of this study was to assess the characteristics of dermatology patients who use the Internet and/or smartphone apps to access health information and to evaluate the impact that these resources have on patients' health care-seeking behavior and interactions with physicians. Online resources offer both opportunities and challenges for dermatologists. Because patients often consult online resources for information about dermatologic conditions and may rely on these resources instead of seeking the care of a dermatologist, it is important for dermatologists to be involved in the development of high-quality online content that educates the public while also emphasizing the need to seek in-person medical care.

Non-random geographic distribution of patients with cutaneous T-cell lymphoma in the Greater Pittsburgh Area.

BACKGROUND: Environmental hazards may play a role in the etiology of cutaneous T-cell lymphoma (CTCL). Some studies have found an increased incidence of CTCL among workers in chemical science, transportation, and manufacturing industries, but other studies have not. This discrepancy may be attributable to population migration, complicating accurate assessment of lifetime exposures. The Pittsburgh population has very low migration rates and most CTCL patients seen at the University of Pittsburgh Medical Center (UPMC) Cutaneous Lymphoma Center are life-long local residents. The Greater Pittsburgh Area used to be an industrial hub. There are residential communities positioned within close proximity to inactive industrial sites that continue to contain pollutants. OBJECTIVE: To determine whether CTCL patients' residences cluster within specific Pittsburgh regions, in particular, those with high levels of environmental pollutants. METHODS: Our study included patients diagnosed with CTCL at the UPMC Cutaneous Lymphoma Center between 2000 and 2012. We mapped the longitudinal and latitudinal coordinates of patients' residences at diagnosis, superfund sites, toxic release inventory sites, particular matter levels, and dermatologists' offices using ArcMap 10.1. We then performed a SaTScan analysis using zip codes to assess for geographic clustering of patients' residences in the Pittsburgh metropolitan statistical area. We assessed for a correlation between case distribution and both environmental hazards sites and dermatologist density in the area. RESULTS: We identified 274 patients with CTCL in the Greater Pittsburgh area. We identified a statistically significant geographic cluster (p<.001) in zip code 15213, which is the most densely populated neighborhood in Pittsburgh and the site of the region's only CTCL clinic. We observed no relationship between the locations of superfund sites, toxic release inventory sites, or particular matter levels and CTCL case distribution. CONCLUSION: Our findings do not support an association between exposure to environmental toxins and CTCL. CTCL cases clustered in areas with the highest population density, which also happen to include a regional CTCL center. To evaluate a possibility of urban pollutants playing a role in etiology of CTCL, dermatologist density and access to care need to be addressed as potential confounders in the future studies.

Phytophotodermatitis.

Phytophotodermatitis is a phototoxic cutaneous eruption due to skin exposure to furocourmarins combined with ultraviolet light. Bizzare linear patterns, ranging from erythema to bullae with residual hyperpigmentaion, is the clinical clue to this diagnosis. Avoidance of furocoumarins in direct sunlight can prevent recurrences.

Melanoma depth in patients with an established dermatologist.

BACKGROUND: The impact of having an established dermatologist on melanoma depth at diagnosis is incompletely understood. OBJECTIVE: We sought to determine whether having had a previous dermatologic examination (an established dermatologist), the recency of the last examination, and the wait time for the dermatology appointment are associated with melanoma invasiveness and depth. METHODS: This was a retrospective cross-sectional study of 388 patients with primary melanoma at an academic dermatology department. RESULTS: Patients with an established dermatologist were more likely than patients without an established dermatologist to be given a diagnosis of melanoma in situ (103/162 [63.6%] vs 69/155 [44.5%], P = .001) and to have thinner invasive melanoma (0.48 [0.30-0.71] mm vs 0.61 [0.40-1.10] mm, respectively, P = .003). These trends were observed for patients with self-detected, but not dermatologist-detected, melanoma. Patient-detected melanomas made up 184/361 (51.0%) of all melanomas, 83/199 (41.7%) of in situ melanomas, and 101/162 (62.4%) invasive melanomas. Self-detected melanomas were in situ in 36 of 61 (59.0%) patients with an established dermatologist versus 40 of 108 (37.0%) patients without an established dermatologist, P = .006. Neither time from last dermatologic examination nor wait time for an appointment was associated with melanoma invasiveness or depth. LIMITATIONS: Data are retrospective and from 1 large academic health care system. CONCLUSION: Education obtained at the dermatology appointment may improve early self-detection of melanoma, and having an established dermatologist may facilitate earlier evaluation of concerning lesions.

Individual and ecological factors associated with early detection of nodular melanoma in the United States.

The aim of the study was to identify individual and ecological factors associated with early diagnosis of nodular melanoma (NM). Using cross-sectional, prospective data from 18 Surveillance, Epidemiology, and End Results registries, we performed multiple logistic regression to generate odds of thick (>4 mm) versus thin (≤2 mm) NM using patient-level demographics and tumor characteristics as well as county-level socioeconomic status, healthcare access, and preventive service use as predictors. We identified 10 475 patients with NM. Divorced, separated, and widowed individuals had increased odds of thick versus thin NM compared with married individuals [odds ratio (OR): 1.47, P<0.001], as did never married individuals (OR: 1.63, P<0.001). Individuals who lived in areas with high (≥4/100 000) dermatologist density had decreased odds of thick versus thin NM (OR: 0.75, P=0.02). Women aged 18-65 years who lived in areas with high Papanicolaou test use and women aged 40 years and older who lived in areas with high mammography use had decreased odds of thick versus thin NM (OR: 0.60, P<0.001 and OR: 0.68, P<0.001, respectively). High school completion, median income, insurance status, family medicine physician density, and internist density in one's area of residence were not associated with odds of thick versus thin NM. In contrast to other types of melanoma, NM thickness at diagnosis is not associated with the socioeconomic environment in one's area of residence. Instead, it is related to factors associated with incidental or formal detection. This information should be used to better target melanoma education and early detection programs.

Epidemiology of ophthalmologic disease associated with erythema multiforme, Stevens-Johnson syndrome, and toxic epidermal necrolysis in hospitalized children in the United States.

The objective of the current study was to characterize the epidemiology and resource use of U.S. children hospitalized with ophthalmologic disease secondary to erythema multiforme (EM), Stevens-Johnson syndrome (SJS), and toxic epidermal necrolysis (TEN). We studied children ages 5 to 19 years hospitalized in 2005 in 11 states, encompassing 38% of the U.S. pediatric population. Using International Classification of Diseases, Ninth Revision, Clinical Modification codes, we identified admissions of children with EM, SJS, or TEN and the presence of concurrent ophthalmologic disease, analyzed patient and hospitalization characteristics, and generated age- and sex-adjusted national estimates. We identified 460 children admitted with EM, SJS, or TEN, corresponding to 1,229 U.S. hospitalizations in 2005. Of the children with EM, SJS, or TEN, 60 (13.0%) had ophthalmologic disease, primarily (90.0%) disorders of the conjunctiva. Children with the highest proportions of ophthalmologic disease included those with mycoplasma pneumonia (26.7%), herpes simplex virus (15.6%), upper respiratory infection (13.9%), and lower respiratory infection (13.7%). Individuals with EM, SJS, or TEN and ophthalmologic disease were more likely than those without ophthalmologic disease to receive intensive care unit care (28.3% vs 17.0%, p = 0.03) and to be admitted to a children's hospital (63.3% vs 48.8%, p = 0.03). Ophthalmologic disease was also associated with a significantly longer median length of stay (6.0 days, interquartile range [IQR] 3-9 days vs 3.0 days, IQR 2-6 days, p < 0.001) and median hospital cost ($7,868, IQR $3,539-$17,440 vs $2,969, IQR $1,603-$8,656, p < 0.001). In children with EM, SJS, or TEN, ophthalmologic disease was most common in those with concurrent Mycoplasma pneumoniae and herpes simplex virus infections. Ophthalmologic disease was associated with considerably higher inpatient resource use in this population. Children with EM, SJS, or TEN should be screened and treated early for ophthalmologic disease to prevent morbidity and minimize long-term sequellae.

Compliance with pregnancy prevention measures during isotretinoin therapy.

BACKGROUND: Approximately 150 women annually become pregnant while taking isotretinoin despite participation in the iPLEDGE program. Noncompliance with the requirement to be abstinent or use 2 contraceptive methods may be a contributing factor. OBJECTIVE: We sought to determine the degree of adherence to contraception or abstinence among women taking isotretinoin. METHODS: We conducted an anonymous survey of women of childbearing potential taking isotretinoin for at least 2 months. RESULTS: Among 75 participants, 21 (28%) chose abstinence as their primary means of pregnancy prevention, of whom 4 (19%) were sexually active during treatment. The most commonly chosen contraceptive methods among the 39 women who were sexually active were condoms (35, 90%) and oral contraceptive pills (18, 46%). Twelve women (31%) admitted to having intercourse at least once using 1 or fewer forms of contraception; 10 failed to use condoms, and 1 reported completely unprotected intercourse. Among sexually active oral contraceptive pill users, 7 (39%) reported missing 1 or more pills in the previous month. LIMITATIONS: Data were self-reported, thus participants may have inaccurately reported contraception use. CONCLUSIONS: Encouraging the use of highly effective, patient-independent contraception and limiting abstinence to women who have never been sexually active may further reduce the rate of isotretinoin-exposed pregnancies.

Mobile applications in dermatology.

IMPORTANCE: With advancements in mobile technology, cellular phone-based mobile applications (apps) may be used in the practice and delivery of dermatologic care. OBJECTIVE: To identify and categorize the variety of current mobile apps available in dermatology for patients and providers. DESIGN, SETTING, AND PARTICIPANTS: Dermatology-related search terms were queried in the online app stores of the most commonly used mobile platforms developed by Apple, Android, Blackberry, Nokia, and Windows. Applications were assigned to categories based on description. Popularity, price, and reviews were recorded and target audiences were determined through websites offering online mobile apps. MAIN OUTCOMES AND MEASURES: Number, type, and price of mobile apps in dermatology. RESULTS: A total of 229 dermatology-related apps were identified in the following categories: general dermatology reference (61 [26.6%]), self-surveillance/diagnosis (41 [17.9%]), disease guide (39 [17.0%]), educational aid (20 [8.7%]), sunscreen/UV recommendation (19 [8.3%]), calculator (12 [5.2%]), teledermatology (8 [3.5%]), conference (6 [2.6%]), journal (6 [2.6%]), photograph storage/sharing (5 [2.2%]), dermoscopy (2 [0.9%]), pathology (2 [0.9%]), and other (8 [3.5%]). The most reviewed apps included Ultraviolet ~ UV Index (355 reviews), VisualDx (306), SPF (128), iSore (61), and SpotMole (50). There were 209 unique apps, with 17 apps existing on more than 1 operating system. More than half of the apps were offered free of charge (117 [51.1%]). Paid apps (112 [48.9%]) ranged from $0.99 to $139.99 (median, $2.99). Target audiences included patient (117 [51.1%]), health care provider (94 [41.0%]), and both (18 [7.9%]). CONCLUSIONS AND RELEVANCE: The widespread variety and popularity of mobile apps demonstrate a great potential to expand the practice and delivery of dermatologic care.

Characteristics and survival of patients with invasive amelanotic melanoma in the USA.

Amelanotic melanoma (AM) has not been well characterized on a population-based level. Using cross-sectional, prospective data from 18 Surveillance, Epidemiology, and End Results registries, we carried out χ(2)-tests to compare characteristics of patients with AM with characteristics of patients with melanotic melanoma (MM), the Kaplan-Meier method to calculate 5-year survival among patients with AM and MM by stage, and competing risks regression to generate subdistribution hazard ratios for patients with AM using age, sex, and stage as predictors. We identified 628 cases of AM and 157,524 cases of MM. Patients with AM were more often male and older than patients with MM (P = 0.011 and P < 0.001, respectively). AM was more common on the face/ears compared with MM and less common on the trunk (P = 0.004 and P < 0.001, respectively). Ulceration was over three times more common among patients with AM than among patients with MM (38.0 vs. 12.5%, P < 0.001), and it remained more common among patients with AM even when stratified by Breslow depths of up to 2 mm (P < 0.001). Patients with AM were over three times more likely than patients with MM to have distant disease at diagnosis (10.0 vs. 2.9%, P < 0.001). Five-year melanoma-specific survival was significantly lower in patients with AM than in patients with MM (72.3 vs. 91.1%, P < 0.001). In competing risks regression, only stage was a significant predictor of melanoma-specific death. Our results demonstrate that the demographics of patients with AM and MM differ. AM is more advanced at diagnosis and is often more lethal than MM. Understanding the epidemiology of AM may help identify patients at highest risk and improve strategies for early detection.

Hospitalizations of children with neurologic disorders in the United States.

OBJECTIVES: Although neurologic disorders are among the most serious acute pediatric illnesses, epidemiologic data are scarce. We sought to determine the scope and outcomes of children with these disorders in the United States. DESIGN: Retrospective cohort study. SETTING: All nonfederal hospitals in 11 states encompassing 38% of the U.S. pediatric population. PATIENTS: Children 29 days to 19 years old hospitalized in 2005. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Using International Classification of Diseases, 9th Revision, Clinical Modification, codes, we identified admissions with neurologic diagnoses, analyzed patient and hospitalization characteristics, and generated age- and sex-adjusted national estimates. Of 960,020 admissions in the 11 states, 10.7% (103,140) included a neurologic diagnosis, which yields a national estimate of 273,900 admissions of children with neurologic diagnoses. The most common were seizures (53.9%) and traumatic brain injury (17.3%). Children with neurologic diagnoses had nearly three times greater ICU use than other hospitalized children (30.6% vs 10.6%, p < 0.001). Neurologic diagnoses were associated with nearly half of deaths (46.2%, n = 1,790). Among ICU patients, children with neurologic diagnoses had more than three times the mortality of other patients (4.8% vs1.5%, p < 0.001). Children with neurologic diagnoses had a significantly longer median hospital length of stay than other children (3 d [1, 5] vs 2 d [2, 4], p < 0.001) and greater median hospital costs ($4,630 [$2,380, $9,730] vs $2,840 [$1,520, $5,550], p < 0.001). CONCLUSIONS: Children with neurologic diagnoses account for a disproportionate amount of ICU stays and deaths compared with children hospitalized for other reasons.

Diagnostic inaccuracy of smartphone applications for melanoma detection.

OBJECTIVE: To measure the performance of smartphone applications that evaluate photographs of skin lesions and provide the user with feedback about the likelihood of malignancy. DESIGN: Case-control diagnostic accuracy study. SETTING: Academic dermatology department. PARTICIPANTS AND MATERIALS: Digital clinical images of pigmented cutaneous lesions (60 melanoma and 128 benign control lesions) with a histologic diagnosis rendered by a board-certified dermatopathologist, obtained before biopsy from patients undergoing lesion removal as a part of routine care. MAIN OUTCOME MEASURES: Sensitivity, specificity, and positive and negative predictive values of 4 smartphone applications designed to aid nonclinician users in determining whether their skin lesion is benign or malignant. RESULTS: Sensitivity of the 4 tested applications ranged from 6.8% to 98.1%; specificity, 30.4% to 93.7%; positive predictive value, 33.3% to 42.1%; and negative predictive value, 65.4% to 97.0%. The highest sensitivity for melanoma diagnosis was observed for an application that sends the image directly to a board-certified dermatologist for analysis; the lowest, for applications that use automated algorithms to analyze images. CONCLUSIONS: The performance of smartphone applications in assessing melanoma risk is highly variable, and 3 of 4 smartphone applications incorrectly classified 30% or more of melanomas as unconcerning. Reliance on these applications, which are not subject to regulatory oversight, in lieu of medical consultation can delay the diagnosis of melanoma and harm users.