Artificial intelligence in mobile health for skin cancer diagnostics at home (AIM HIGH): a pilot feasibility study.

Background: Artificial intelligence (AI)-based mobile phone apps (mHealth) have the potential to streamline care for suspicious skin lesions in primary care. This study aims to investigate the conditions and feasibility of a study that incorporates an AI-based app in primary care and evaluates its potential impact. Methods: We conducted a pilot feasibility study from November 22nd, 2021 to June 9th, 2022 with a mixed-methods design on implementation of an AI-based mHealth app for skin cancer detection in three primary care practices in the Netherlands (Rotterdam, Leiden and Katwijk). The primary outcome was the inclusion and successful participation rate of patients and general practitioners (GPs). Secondary outcomes were the reasons, facilitators and barriers for successful participation and the potential impact in both pathways for future sample size calculations. Patients were offered use of an AI-based mHealth app before consulting their GP. GPs assessed the patients blinded and then unblinded to the app. Qualitative data included observations and audio-diaries from patients and GPs and focus-groups and interviews with GPs and GP assistants. Findings: Fifty patients were included with a median age of 52 years (IQR 33.5-60.3), 64% were female, and 90% had a light skin type. The average patient inclusion rate was 4-6 per GP practice per month and 84% (n = 42) successfully participated. Similarly, in 90% (n = 45 patients) the GPs also successfully completed the study. GPs never changed their working diagnosis, but did change their treatment plan (n = 5) based on the app's assessments. Notably, 54% of patients with a benign skin lesion and low risk rating, indicated that they would be reassured and cancel their GP visit with these results (p < 0.001). Interpretation: Our findings suggest that studying implementation of an AI-based mHealth app for detection of skin cancer in the hands of patients or as a diagnostic tool used by GPs in primary care appears feasible. Preliminary results indicate potential to further investigate both intended use settings. Funding: SkinVision B.V.

An artificial intelligence based app for skin cancer detection evaluated in a population based setting.

Artificial intelligence (AI) based algorithms for classification of suspicious skin lesions have been implemented in mobile phone apps (mHealth), but their effect on healthcare systems is undocumented. In 2019, a large Dutch health insurance company offered 2.2 million adults free access to an mHealth app for skin cancer detection. To study the impact on dermatological healthcare consumption, we conducted a retrospective population-based pragmatic study. We matched 18,960 mHealth-users who completed at least one successful assessment with the app to 56,880 controls who did not use the app and calculated odds ratios (OR) to compare dermatological claims between both groups in the first year after granting free access. A short-term cost-effectiveness analysis was performed to determine the cost per additional detected (pre)malignancy. Here we report that mHealth-users had more claims for (pre)malignant skin lesions than controls (6.0% vs 4.6%, OR 1.3 (95% CI 1.2-1.4)) and also a more than threefold higher risk of claims for benign skin tumors and nevi (5.9% vs 1.7%, OR 3.7 (95% CI 3.4-4.1)). The costs of detecting one additional (pre)malignant skin lesion with the app compared to the current standard of care were €2567. Based on these results, AI in mHealth appears to have a positive impact on detecting more cutaneous (pre)malignancies, but this should be balanced against the for now stronger increase in care consumption for benign skin tumors and nevi.

Efficacy of endovascular treatment of pelvic varicose veins: A single-center retrospective observational study.

OBJECTIVE: To evaluate the efficacy of endovascular embolization of pelvic varicose veins in the treatment of pelvic venous disorders (PeVD). METHODS: A single-center retrospective study was performed, including 156 women referred to the Erasmus University Medical Center between January 2011 and October 2020 for an evaluation of PeVD. Data on presenting symptoms, clinical workup, treatment, and clinical outcomes were collected. The primary end point was resolution of symptoms after treatment. Secondary outcomes were correlation between symptoms at presentation and relief of symptoms after treatment, minor or major procedural complications, recurrences, and additional treatments needed. RESULTS: Ninety patients underwent a pelvic phlebography, of which 75 received embolization of pelvic varicose veins. Median follow-up after phlebography was 13.2 months (interquartile range, 6.0-40.1 months). Of the treated patients, 53 (70.7%) had partial or complete relief of symptoms. Forty-six women (61.3%) who received embolization of pelvic varicose veins required additional treatments for leg and/or vulvar varicose veins. CONCLUSIONS: This study found that endovascular embolization of pelvic varicose veins can be an effective treatment for PeVDs. However, additional treatments are often required for leg and/or vulvar varicose veins.

Maternal lipid levels in early pregnancy as a predictor of childhood lipid levels: a prospective cohort study.

BACKGROUND: Maternal lipid levels in early pregnancy are associated with maternal health and foetal growth. It is however unclear if maternal lipids in early pregnancy can be used to predict childhood lipid levels. The aim of this study is to assess the association between maternal and offspring childhood lipid levels, and to investigate the influence of maternal BMI and diet on these associations. METHODS: This study included 2692 women participating in the Generation R study, an ongoing population-based prospective cohort study from early life onwards. Women with an expected delivery date between 2002 and 2006 living in Rotterdam, the Netherlands were included. Total cholesterol, triglycerides and high-density lipoprotein cholesterol (HDL-c) were measured in early pregnancy (median 13.2 weeks [90% range 10.6; 17.1]). Low-density lipoprotein cholesterol (LDL-c), remnant cholesterol and non-HDL-c were calculated. Corresponding lipid measurements were determined in 2692 children at the age of 6 (median 6.0 years [90% range 5.7; 7.5]) and 1673 children 10 years (median 9.7 years [90% range 9.5; 10.3]). Multivariate linear regression analysis was used to examine the association between maternal lipid levels in early pregnancy and the corresponding childhood lipid measurements at the ages of 6 and 10 years while adjusting for confounders. RESULTS: Maternal lipid levels in early pregnancy are positively associated with corresponding childhood lipid levels 6 and 10 years after pregnancy, independent of maternal body mass index and diet. CONCLUSIONS: Maternal lipid levels in early pregnancy may provide an insight to the lipid profile of children years later. Gestational lipid levels may therefore be used as an early predictor of children's long-term health. Monitoring of these gestational lipid levels may give a window-of-opportunity to start early interventions to decrease offspring's lipid levels and possibly diminish their cardiovascular risk later in life. Future studies are warranted to investigate the genetic contribution on maternal lipid levels in pregnancy and lipid levels of their offspring years later.

Gestational lipid profile as an early marker of metabolic syndrome in later life: a population-based prospective cohort study.

BACKGROUND: In pregnancy lipid levels increase with gestation resembling an atherogenic lipid profile. Currently it is unclear whether gestational lipid levels are associated with an adverse cardiovascular risk profile later in life. The aim of this study is to assess the association between gestational lipid levels and lipid levels and prevalence of the metabolic syndrome (MS) six years after pregnancy. METHODS: In plasma of 3510 women from the Generation R Study; a prospective population-based cohort, we measured lipid levels (total cholesterol, triglycerides and high-density lipoprotein cholesterol [HDL-c]), and low-density lipoprotein cholesterol (LDL-c), remnant cholesterol and non-HDL-c were calculated in early pregnancy (median 13.2 weeks, 90% range [10.5 to 17.1]) and six years after pregnancy (median 6.5 years, 90% range [6.2 to 7.8]). MS was assessed six years after pregnancy according to the NCEP/ATP3 criteria. We also examined the influence of pregnancy complications on these associations. RESULTS: Gestational lipid levels were positively associated with corresponding lipid levels six years after pregnancy, independent of pregnancy complications. Six years after pregnancy the prevalence of MS was 10.0%; the prevalence was higher for women with a previous placental syndrome (13.5%). Gestational triglycerides and remnant cholesterol in the highest quartile and HDL-c in the lowest quartile were associated with the highest risk for future MS, independent of smoking and body mass index. CONCLUSIONS: Gestational lipid levels provide an insight in the future cardiovascular risk profile of women in later life. Monitoring and lifestyle intervention could be indicated in women with an unfavorable gestational lipid profile to optimize timely cardiovascular risk prevention.

Maternal lipid profile in early pregnancy is associated with foetal growth and the risk of a child born large-for-gestational age: a population-based prospective cohort study : Maternal lipid profile in early pregnancy and foetal growth.

BACKGROUND: Lipids such as cholesterol and triglycerides play an important role in both maternal and foetal energy metabolism. Little is known about maternal lipid levels in pregnancy and their effect on foetal growth. The aim of this study was to assess maternal lipid levels, foetal growth and the risk of small-for-gestational age (SGA) and large-for-gestational age (LGA). METHODS: We included 5702 women from the Generation R Study, a prospective population-based cohort. Maternal lipid levels (total cholesterol, triglycerides and high-density lipoprotein cholesterol [HDL-c]) were measured in early pregnancy (median 13.4 weeks, 90% range [10.5 to 17.2]). Low-density lipoprotein cholesterol (LDL-c), remnant cholesterol and non-HDL-c were calculated. Foetal growth was measured repeatedly by ultrasound. Information on birth anthropometrics was retrieved from medical records. A birth weight below the 10th percentile was defined as SGA and above the 90th percentile as LGA. RESULTS: Maternal triglyceride and remnant cholesterol levels were associated with increased foetal head circumference and abdominal circumference growth rates. Triglycerides and remnant cholesterol were positively associated with the risk of LGA (odds ratio [OR] 1.11, 95% confidence interval [CI] [1.01 to 1.22] and OR 1.11, 95% CI [1.01 to 1.23], respectively). These associations were independent of maternal pre-pregnancy body mass index, but not maternal glucose levels. We observed no association between maternal lipids in early pregnancy and SGA. CONCLUSIONS: Our study suggests a novel association of early pregnancy triglyceride and remnant cholesterol levels with foetal growth, patterns of foetal growth and the risk of LGA. Future studies are warranted to explore clinical implication possibilities.

Is maternal lipid profile in early pregnancy associated with pregnancy complications and blood pressure in pregnancy and long term postpartum?

BACKGROUND: An atherogenic lipid profile is a risk factor for the initiation and progression of atherosclerosis. This ultimately leads to cardiovascular disease. Women with a history of hypertensive disorders of pregnancy are at increased risk of sustained hypertension and cardiovascular disease later in life. Currently it is unclear whether dyslipidemia during pregnancy contributes to these risks. OBJECTIVE: The objective of the study was to determine the associations between early pregnancy maternal lipid profile, hypertensive disorders of pregnancy, and blood pressure during and years after pregnancy. STUDY DESIGN: We included 5690 women from the Generation R Study, an ongoing population-based prospective birth cohort. Two hundred eighteen women (3.8%) developed gestational hypertension and 139 (2.4%) preeclampsia. A maternal lipid profile consisting of total cholesterol, triglycerides, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, remnant cholesterol, and non-high-density lipoprotein cholesterol was determined in early pregnancy (median, 13.4 weeks of gestation). Systolic and diastolic blood pressures were measured in early, mid-, and late pregnancy and 6 and 9 years after pregnancy. RESULTS: Triglycerides and remnant cholesterol in early pregnancy were positively associated with preeclampsia. Maternal lipid levels in early pregnancy were not associated with gestational hypertension. Total cholesterol, low-density lipoprotein cholesterol, non-high-density lipoprotein cholesterol, and especially triglycerides and remnant cholesterol were positively associated with blood pressure in pregnancy and 6 and 9 years after pregnancy. Triglycerides and remnant cholesterol are positively associated with sustained hypertension 6 and 9 years after pregnancy. CONCLUSION: An atherogenic lipid profile in early pregnancy reflecting impaired triglyceride-rich lipoprotein metabolism is independently associated with preeclampsia and blood pressure throughout pregnancy but also with sustained hypertension long term postpartum. Lipid levels in early pregnancy may help to identify women at risk for future hypertension and perhaps also women at risk for future cardiovascular disease.