Comparing performance between clinics of an embryo evaluation algorithm based on time-lapse images and machine learning.

PURPOSE: This article aims to assess how differences in maternal age distributions between IVF clinics affect the performance of an artificial intelligence model for embryo viability prediction and proposes a method to account for such differences. METHODS: Using retrospectively collected data from 4805 fresh and frozen single blastocyst transfers of embryos incubated for 5 to 6 days, the discriminative performance was assessed based on fetal heartbeat outcomes. The data was collected from 4 clinics, and the discrimination was measured in terms of the area under ROC curves (AUC) for each clinic. To account for the different age distributions between clinics, a method for age-standardizing the AUCs was developed in which the clinic-specific AUCs were standardized using weights for each embryo according to the relative frequency of the maternal age in the relevant clinic compared to the age distribution in a common reference population. RESULTS: There was substantial variation in the clinic-specific AUCs with estimates ranging from 0.58 to 0.69 before standardization. The age-standardization of the AUCs reduced the between-clinic variance by 16%. Most notably, three of the clinics had quite similar AUCs after standardization, while the last clinic had a markedly lower AUC both with and without standardization. CONCLUSION: The method of using age-standardization of the AUCs that is proposed in this article mitigates some of the variability between clinics. This enables a comparison of clinic-specific AUCs where the difference in age distributions is accounted for.

Prevalence of parental mental health conditions among children aged 0-16 years in Denmark: A nationwide register-based cross-sectional study.

Aim: Parental mental health conditions adversely affect the children. Information on the prevalence of parental mental health conditions is needed to help policymakers allocate resources appropriately. Therefore, the aim of this study was to estimate the prevalence of children with parental mental health conditions in Denmark and further estimate the age-specific prevalence and geographical variation. Methods: In this nationwide register-based cross-sectional study, we included all children born between 2000 and 2016 if they resided in Denmark on 31 December 2016. Information on both maternal and paternal mental health conditions was retrieved from primary and secondary healthcare registers. Parental mental health conditions were categorised in three severity groups: minor, moderate, and severe. We estimated the proportion of children with parental mental health conditions on 31 December 2016. Results: Of the 1,106,459 children aged 0-16 years, 39.1% had at least one parent with a mental health condition. The prevalence increased with age of the children until the age of six years. Geographical variation in the prevalence ranged from 29.0% to 48.3% in the 98 municipalities. Minor parental mental health conditions (23.5%) were more common than moderate (13.5%) and severe parental mental health conditions (2.2%). Hospital-diagnosed parental mental health conditions were prevalent in 12.8% of the children. Conclusions: Two in five children aged 0-16 years in Denmark have parents with a mental health condition and geographical variation exists. The high prevalence of children with parental mental health conditions is an important public health challenge, which calls for attention.

Cell-free DNA promoter hypermethylation as a diagnostic marker for pancreatic ductal adenocarcinoma - An external validation study.

BACKGROUND: We recently identified a diagnostic prediction model based on promoter hypermethylation of eight selected genes in plasma cell-free (cf) DNA, which showed promising results as a diagnostic biomarker for pancreatic ductal adenocarcinoma (PDAC). The aim of the present study was to validate this biomarker profile in an external patient cohort and examine any additional effect of serum CA 19-9. METHODS: Patients with PDAC (n = 346, stage I-IV) and chronic pancreatitis (n = 25) were included. Methylation-specific PCR of a 28-gene panel was performed on serum cfDNA samples. The previously developed diagnostic prediction model (age>65 years, BMP3, RASSF1A, BNC1, MESTv2, TFPI2, APC, SFRP1 and SFRP2) was validated alone and in combination with serum CA 19-9 in this external patient cohort. RESULTS: Patients with PDAC had a higher number of hypermethylated genes (mean 8.11, 95% CI 7.70-8.52) than patients with chronic pancreatitis (mean 5.60, 95% CI 4.42-6.78, p = 0.011). Validation of the diagnostic prediction model yielded an AUC of 0.77 (95% CI 0.69-0.84). The combination of serum CA 19-9 and our test had an AUC of 0.93 (95% CI 0.89-0.96) in the primary study and 0.85 (95% CI 0.79-0.91) in the validation study. CONCLUSION: In this validation study, PDAC was associated with a higher number of hypermethylated genes in serum cfDNA than chronic pancreatitis. Our diagnostic test was superior to the predictive value of serum CA 19-9 alone in both the primary and the validation study. The combination of our test with CA 19-9 may serve as a clinically useful diagnostic biomarker for PDAC.

Reporting and handling of equivocal imaging findings in diagnostic studies of bone metastasis in prostate cancer.

BACKGROUND: Equivocal scanning results occur. It remains unclear how these results are presented and their management influence diagnostic characteristics. PURPOSE: To investigate the reporting and handling of equivocal imaging findings in diagnostic studies of bone metastases, and to assess the impact on diagnostic performance of the methods used to analyze equivocal findings. The conceptual issue was reified based on two actual observations. MATERIAL AND METHODS: A recent meta-analysis of bone metastases in prostate cancer was conducted and data were obtained from a large clinical trial with a true reference of bone metastasis, where diagnostic characteristics were calculated with equivocal scans handled by: removal; considered malignant; considered benign; and intention-to-diagnose. RESULTS: The meta-analysis included 18 trials where the median proportion of reported equivocal results was 27%. Eleven (61%) studies reported an equivocal option for the index test, 42% reported equivocal results and described how these were analyzed. The clinical trial included 583 prostate cancer patients with 20% equivocal results. The different methods of managing equivocal findings resulted in highly variable outcomes: sensitivity = 85%-100%; specificity = 78%-99%; and positive and negative predictive values = 44%-94% and 97%-100%, respectively. The diagnostic performances obtained using the four methods were differentially susceptible to the proportion of equivocal imaging findings and the prevalence of bone metastases. CONCLUSION: Reporting of equivocal results was inadequate in bone imaging trials. The handling of equivocal findings strongly influenced diagnostic accuracy.