Investigating harms of testing for ovarian cancer - psychological outcomes and cancer conversion rates in women with symptoms of ovarian cancer: A cohort study embedded in the multicentre ROCkeTS prospective diagnostic study.

OBJECTIVE: To investigate psychological correlates in women referred with suspected ovarian cancer via the fast-track pathway, explore how anxiety and distress levels change at 12 months post-testing, and report cancer conversion rates by age and referral pathway. DESIGN: Single-arm prospective cohort study. SETTING: Multicentre. Secondary care including outpatient clinics and emergency admissions. POPULATION: A cohort of 2596 newly presenting symptomatic women with a raised CA125 level, abnormal imaging or both. METHODS: Women completed anxiety and distress questionnaires at recruitment and at 12 months for those who had not undergone surgery or a biopsy within 3 months of recruitment. MAIN OUTCOME MEASURES: Anxiety and distress levels measured using a six-item short form of the State-Trait Anxiety Inventory (STAI-6) and the Impact of Event Scale - Revised (IES-r) questionnaire. Ovarian cancer (OC) conversion rates by age, menopausal status and referral pathway. RESULTS: Overall, 1355/2596 (52.1%) and 1781/2596 (68.6%) experienced moderate-to-severe distress and anxiety, respectively, at recruitment. Younger age and emergency presentations had higher distress levels. The clinical category for anxiety and distress remained unchanged/worsened in 76% of respondents at 12 months, despite a non-cancer diagnosis. The OC rates by age were 1.6% (95% CI 0.5%-5.9%) for age <40 years and 10.9% (95% CI 8.7%-13.6%) for age ≥40 years. In women referred through fast-track pathways, 3.3% (95% CI 1.9%-5.7%) of pre- and 18.5% (95% CI 16.1%-21.0%) of postmenopausal women were diagnosed with OC. CONCLUSIONS: Women undergoing diagnostic testing display severe anxiety and distress. Younger women are especially vulnerable and should be targeted for support. Women under the age of 40 years have low conversion rates and we advocate reducing testing in this group to reduce the harms of testing.

ADNEX risk prediction model for diagnosis of ovarian cancer: systematic review and meta-analysis of external validation studies.

Objectives: To conduct a systematic review of studies externally validating the ADNEX (Assessment of Different Neoplasias in the adnexa) model for diagnosis of ovarian cancer and to present a meta-analysis of its performance. Design: Systematic review and meta-analysis of external validation studies. Data sources: Medline, Embase, Web of Science, Scopus, and Europe PMC, from 15 October 2014 to 15 May 2023. Eligibility criteria for selecting studies: All external validation studies of the performance of ADNEX, with any study design and any study population of patients with an adnexal mass. Two independent reviewers extracted the data. Disagreements were resolved by discussion. Reporting quality of the studies was scored with the TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) reporting guideline, and methodological conduct and risk of bias with PROBAST (Prediction model Risk Of Bias Assessment Tool). Random effects meta-analysis of the area under the receiver operating characteristic curve (AUC), sensitivity and specificity at the 10% risk of malignancy threshold, and net benefit and relative utility at the 10% risk of malignancy threshold were performed. Results: 47 studies (17 007 tumours) were included, with a median study sample size of 261 (range 24-4905). On average, 61% of TRIPOD items were reported. Handling of missing data, justification of sample size, and model calibration were rarely described. 91% of validations were at high risk of bias, mainly because of the unexplained exclusion of incomplete cases, small sample size, or no assessment of calibration. The summary AUC to distinguish benign from malignant tumours in patients who underwent surgery was 0.93 (95% confidence interval 0.92 to 0.94, 95% prediction interval 0.85 to 0.98) for ADNEX with the serum biomarker, cancer antigen 125 (CA125), as a predictor (9202 tumours, 43 centres, 18 countries, and 21 studies) and 0.93 (95% confidence interval 0.91 to 0.94, 95% prediction interval 0.85 to 0.98) for ADNEX without CA125 (6309 tumours, 31 centres, 13 countries, and 12 studies). The estimated probability that the model has use clinically in a new centre was 95% (with CA125) and 91% (without CA125). When restricting analysis to studies with a low risk of bias, summary AUC values were 0.93 (with CA125) and 0.91 (without CA125), and estimated probabilities that the model has use clinically were 89% (with CA125) and 87% (without CA125). Conclusions: The results of the meta-analysis indicated that ADNEX performed well in distinguishing between benign and malignant tumours in populations from different countries and settings, regardless of whether the serum biomarker, CA125, was used as a predictor. A key limitation was that calibration was rarely assessed. Systematic review registration: PROSPERO CRD42022373182.

Machine learning and radiomics for segmentation and classification of adnexal masses on ultrasound.

Ultrasound-based models exist to support the classification of adnexal masses but are subjective and rely upon ultrasound expertise. We aimed to develop an end-to-end machine learning (ML) model capable of automating the classification of adnexal masses. In this retrospective study, transvaginal ultrasound scan images with linked diagnoses (ultrasound subjective assessment or histology) were extracted and segmented from Imperial College Healthcare, UK (ICH development dataset; n = 577 masses; 1444 images) and Morgagni-Pierantoni Hospital, Italy (MPH external dataset; n = 184 masses; 476 images). A segmentation and classification model was developed using convolutional neural networks and traditional radiomics features. Dice surface coefficient (DICE) was used to measure segmentation performance and area under the ROC curve (AUC), F1-score and recall for classification performance. The ICH and MPH datasets had a median age of 45 (IQR 35-60) and 48 (IQR 38-57) years old and consisted of 23.1% and 31.5% malignant cases, respectively. The best segmentation model achieved a DICE score of 0.85 ± 0.01, 0.88 ± 0.01 and 0.85 ± 0.01 in the ICH training, ICH validation and MPH test sets. The best classification model achieved a recall of 1.00 and F1-score of 0.88 (AUC:0.93), 0.94 (AUC:0.89) and 0.83 (AUC:0.90) in the ICH training, ICH validation and MPH test sets, respectively. We have developed an end-to-end radiomics-based model capable of adnexal mass segmentation and classification, with a comparable predictive performance (AUC 0.90) to the published performance of expert subjective assessment (gold standard), and current risk models. Further prospective evaluation of the classification performance of this ML model against existing methods is required.

Comparison of the ADNEX and ROMA risk prediction models for the diagnosis of ovarian cancer: a multicentre external validation in patients who underwent surgery.

BACKGROUND: Several diagnostic prediction models to help clinicians discriminate between benign and malignant adnexal masses are available. This study is a head-to-head comparison of the performance of the Assessment of Different NEoplasias in the adneXa (ADNEX) model with that of the Risk of Ovarian Malignancy Algorithm (ROMA). METHODS: This is a retrospective study based on prospectively included consecutive women with an adnexal tumour scheduled for surgery at five oncology centres and one non-oncology centre in four countries between 2015 and 2019. The reference standard was histology. Model performance for ADNEX and ROMA was evaluated regarding discrimination, calibration, and clinical utility. RESULTS: The primary analysis included 894 patients, of whom 434 (49%) had a malignant tumour. The area under the receiver operating characteristic curve (AUC) was 0.92 (95% CI 0.88-0.95) for ADNEX with CA125, 0.90 (0.84-0.94) for ADNEX without CA125, and 0.85 (0.80-0.89) for ROMA. ROMA, and to a lesser extent ADNEX, underestimated the risk of malignancy. Clinical utility was highest for ADNEX. ROMA had no clinical utility at decision thresholds <27%. CONCLUSIONS: ADNEX had better ability to discriminate between benign and malignant adnexal tumours and higher clinical utility than ROMA. CLINICAL TRIAL REGISTRATION: clinicaltrials.gov NCT01698632 and NCT02847832.

A comparison of hyperparameter tuning procedures for clinical prediction models: A simulation study.

Tuning hyperparameters, such as the regularization parameter in Ridge or Lasso regression, is often aimed at improving the predictive performance of risk prediction models. In this study, various hyperparameter tuning procedures for clinical prediction models were systematically compared and evaluated in low-dimensional data. The focus was on out-of-sample predictive performance (discrimination, calibration, and overall prediction error) of risk prediction models developed using Ridge, Lasso, Elastic Net, or Random Forest. The influence of sample size, number of predictors and events fraction on performance of the hyperparameter tuning procedures was studied using extensive simulations. The results indicate important differences between tuning procedures in calibration performance, while generally showing similar discriminative performance. The one-standard-error rule for tuning applied to cross-validation (1SE CV) often resulted in severe miscalibration. Standard non-repeated and repeated cross-validation (both 5-fold and 10-fold) performed similarly well and outperformed the other tuning procedures. Bootstrap showed a slight tendency to more severe miscalibration than standard cross-validation-based tuning procedures. Differences between tuning procedures were larger for smaller sample sizes, lower events fractions and fewer predictors. These results imply that the choice of tuning procedure can have a profound influence on the predictive performance of prediction models. The results support the application of standard 5-fold or 10-fold cross-validation that minimizes out-of-sample prediction error. Despite an increased computational burden, we found no clear benefit of repeated over non-repeated cross-validation for hyperparameter tuning. We warn against the potentially detrimental effects on model calibration of the popular 1SE CV rule for tuning prediction models in low-dimensional settings.

Using simple clinical and ultrasound variables to develop a model to predict first trimester pregnancy viability.

INTRODUCTION: Early prediction of pregnancies destined to miscarry will allow couples to prepare for this common but often unexpected eventuality, and clinicians to allocate finite resources. We aimed to develop a prediction model combining clinical, demographic, and sonographic data as a clinical tool to aid counselling about first trimester pregnancy outcome. MATERIAL AND METHODS: This is a prospective, observational cohort study conducted at Queen Charlotte's and Chelsea Hospital, UK from March 2014 to May 2019. Women with confirmed intrauterine pregnancies between 5 weeks and their dating scan (11-14 weeks) were recruited. Participants attended serial ultrasound scans in the first trimester and at each visit recorded symptoms of vaginal bleeding, pelvic pain, nausea and vomiting using validated scoring tools. Pregnancies were followed up until the dating scan (11-14 weeks). Univariate and multivariate analyses were performed to predict first trimester viability. A model was developed with multivariable logistic regression, variables limited by feature selection, and bootstrapping with multiple imputation was used for internal validation. RESULTS: 1403 women were recruited and after exclusions, data were available for 1105. 160 women (14.5 %) experienced first trimester miscarriage and 945 women (85.5 %) had viable pregnancies at 11-14 weeks' gestation. The average gestational age at the initial visit (calculated from the menstrual dates) was 7 + 1 weeks (+/-12.2 days). A multivariable logistic regression model was developed to predict first trimester viability and included the variables: mean gestational sac diameter, presence of fetal heart pulsations, difference in gestational age from last menstrual period and from mean sac diameter on ultrasonography, current folic acid usage and maternal age. The model demonstrated good performance (optimism-corrected area under curve (AUC) 0.84, 95 % CI 0.81-0.87; optimism-corrected calibration slope 0.969). CONCLUSION: We have developed and internally validated a model to predict first trimester viability with good accuracy prior to the 11-14 week dating scan, which now needs to be externally validated prior to clinical use.

Multiclass risk models for ovarian malignancy: an illustration of prediction uncertainty due to the choice of algorithm.

BACKGROUND: Assessing malignancy risk is important to choose appropriate management of ovarian tumors. We compared six algorithms to estimate the probabilities that an ovarian tumor is benign, borderline malignant, stage I primary invasive, stage II-IV primary invasive, or secondary metastatic. METHODS: This retrospective cohort study used 5909 patients recruited from 1999 to 2012 for model development, and 3199 patients recruited from 2012 to 2015 for model validation. Patients were recruited at oncology referral or general centers and underwent an ultrasound examination and surgery ≤ 120 days later. We developed models using standard multinomial logistic regression (MLR), Ridge MLR, random forest (RF), XGBoost, neural networks (NN), and support vector machines (SVM). We used nine clinical and ultrasound predictors but developed models with or without CA125. RESULTS: Most tumors were benign (3980 in development and 1688 in validation data), secondary metastatic tumors were least common (246 and 172). The c-statistic (AUROC) to discriminate benign from any type of malignant tumor ranged from 0.89 to 0.92 for models with CA125, from 0.89 to 0.91 for models without. The multiclass c-statistic ranged from 0.41 (SVM) to 0.55 (XGBoost) for models with CA125, and from 0.42 (SVM) to 0.51 (standard MLR) for models without. Multiclass calibration was best for RF and XGBoost. Estimated probabilities for a benign tumor in the same patient often differed by more than 0.2 (20% points) depending on the model. Net Benefit for diagnosing malignancy was similar for algorithms at the commonly used 10% risk threshold, but was slightly higher for RF at higher thresholds. Comparing models, between 3% (XGBoost vs. NN, with CA125) and 30% (NN vs. SVM, without CA125) of patients fell on opposite sides of the 10% threshold. CONCLUSION: Although several models had similarly good performance, individual probability estimates varied substantially.

O-RADS US v2022: An Update from the American College of Radiology's Ovarian-Adnexal Reporting and Data System US Committee.

First published in 2019, the Ovarian-Adnexal Reporting and Data System (O-RADS) US provides a standardized lexicon for ovarian and adnexal lesions, enables stratification of these lesions with use of a numeric score based on morphologic features to indicate the risk of malignancy, and offers management guidance. This risk stratification system has subsequently been validated in retrospective studies and has yielded good interreader concordance, even with users of different levels of expertise. As use of the system increased, it was recognized that an update was needed to address certain clinical challenges, clarify recommendations, and incorporate emerging data from validation studies. Additional morphologic features that favor benignity, such as the bilocular feature for cysts without solid components and shadowing for solid lesions with smooth contours, were added to O-RADS US for optimal risk-appropriate scoring. As O-RADS US 4 has been shown to be an appropriate cutoff for malignancy, it is now recommended that lower-risk O-RADS US 3 lesions be followed with US if not excised. For solid lesions and cystic lesions with solid components, further characterization with MRI is now emphasized as a supplemental evaluation method, as MRI may provide higher specificity. This statement summarizes the updates to the governing concepts, lexicon terminology and assessment categories, and management recommendations found in the 2022 version of O-RADS US.

Definition and Criteria for Diagnosing Cesarean Scar Disorder.

Importance: Approximately 60% of women develop a uterine niche after a cesarean delivery (CD). A niche is associated with various gynecological symptoms including abnormal uterine bleeding, pain, and infertility, but there is little consensus in the literature on the distinction between the sonographic finding of a niche and the constellation of associated symptoms. Objective: To achieve consensus on defining the clinical condition that constitutes a symptomatic uterine niche and agree upon diagnostic criteria and uniform nomenclature for this condition. Design, Setting, and Participants: A consensus based modified electronic Delphi (eDelphi) study, with a predefined Rate of Agreement (RoA) of 70% or higher. Experts were selected according to their expertise with niche-related consultations, publications, and participation in expert groups and received online questionnaires between November 2021 and May 2022. Main Outcomes and Measures: Definition, nomenclature, symptoms, conditions to exclude, and diagnostic criteria of an illness caused by a symptomatic uterine niche. Results: In total, 31 of the 60 invited experts (51.7%) participated, of whom the majority worked in university-affiliated hospitals (28 of 31 [90.3%]), specialized in benign gynecology (20 of 31 [64.5%]), and worked in Europe (24 of 31 [77.4%]). Three rounds were required to achieve consensus on all items. All participants underlined the relevance of a new term for a condition caused by a symptomatic niche and its differentiation from a sonographic finding only. Experts agreed to name this condition cesarean scar disorder, defined as a uterine niche in combination with at least 1 primary or 2 secondary symptoms (RoA, 77.8%). Defined primary symptoms were postmenstrual spotting, pain during uterine bleeding, technical issues with catheter insertion during embryo transfer, and secondary unexplained infertility combined with intrauterine fluid. Secondary symptoms were dyspareunia, abnormal vaginal discharge, chronic pelvic pain, avoiding sexual intercourse, odor associated with abnormal blood loss, secondary unexplained infertility, secondary infertility despite assisted reproductive technology, negative self-image, and discomfort during participation in leisure activities. Consensus was also achieved on certain criteria that should be met and conditions that should be excluded before making the diagnosis. Conclusions and Relevance: In this modified Delphi study, a panel of 31 international niche experts reached consensus for the constellation of symptoms secondary to a uterine niche and named it cesarean scar disorder.

External Validation of the Ovarian-Adnexal Reporting and Data System (O-RADS) Lexicon and the International Ovarian Tumor Analysis 2-Step Strategy to Stratify Ovarian Tumors Into O-RADS Risk Groups.

Importance: Correct diagnosis of ovarian cancer results in better prognosis. Adnexal lesions can be stratified into the Ovarian-Adnexal Reporting and Data System (O-RADS) risk of malignancy categories with either the O-RADS lexicon, proposed by the American College of Radiology, or the International Ovarian Tumor Analysis (IOTA) 2-step strategy. Objective: To investigate the diagnostic performance of the O-RADS lexicon and the IOTA 2-step strategy. Design, Setting, and Participants: Retrospective external diagnostic validation study based on interim data of IOTA5, a prospective international multicenter cohort study, in 36 oncology referral centers or other types of centers. A total of 8519 consecutive adult patients presenting with an adnexal mass between January 1, 2012, and March 1, 2015, and treated either with surgery or conservatively were included in this diagnostic study. Twenty-five patients were excluded for withdrawal of consent, 2777 were excluded from 19 centers that did not meet predefined data quality criteria, and 812 were excluded because they were already in follow-up at recruitment. The analysis included 4905 patients with a newly detected adnexal mass in 17 centers that met predefined data quality criteria. Data were analyzed from January 31 to March 1, 2022. Exposures: Stratification into O-RADS categories (malignancy risk <1%, 1% to <10%, 10% to <50%, and ≥50%). For the IOTA 2-step strategy, the stratification is based on the individual risk of malignancy calculated with the IOTA 2-step strategy. Main Outcomes and Measures: Observed prevalence of malignancy in each O-RADS risk category, as well as sensitivity and specificity. The reference standard was the status of the tumor at inclusion, determined by histology or clinical and ultrasonographic follow-up for 1 year. Multiple imputation was used for uncertain outcomes owing to inconclusive follow-up information. Results: Median age of the 4905 patients was 48 years (IQR, 36-62 years). Data on race and ethnicity were not collected. A total of 3441 tumors (70%) were benign, 978 (20%) were malignant, and 486 (10%) had uncertain classification. Using the O-RADS lexicon resulted in 1.1% (24 of 2196) observed prevalence of malignancy in O-RADS 2, 4% (34 of 857) in O-RADS 3, 27% (246 of 904) in O-RADS 4, and 78% (732 of 939) in O-RADS 5; the corresponding results for the IOTA 2-step strategy were 0.9% (18 of 1984), 4% (58 of 1304), 30% (206 of 690), and 82% (756 of 927). At the 10% risk threshold (O-RADS 4-5), the O-RADS lexicon had 92% sensitivity (95% CI, 87%-96%) and 80% specificity (95% CI, 74%-85%), and the IOTA 2-step strategy had 91% sensitivity (95% CI, 84%-95%) and 85% specificity (95% CI, 80%-88%). Conclusions and Relevance: The findings of this external diagnostic validation study suggest that both the O-RADS lexicon and the IOTA 2-step strategy can be used to stratify patients into risk groups. However, the observed malignancy rate in O-RADS 2 was not clearly below 1%.

A Microfluidics Approach for Ovarian Cancer Immune Monitoring in an Outpatient Setting.

Among cancer diagnoses in women, ovarian cancer has the fifth-highest mortality rate. Current treatments are unsatisfactory, and new therapies are highly needed. Immunotherapies show great promise but have not reached their full potential in ovarian cancer patients. Implementation of an immune readout could offer better guidance and development of immunotherapies. However, immune profiling is often performed using a flow cytometer, which is bulky, complex, and expensive. This equipment is centralized and operated by highly trained personnel, making it cumbersome and time-consuming. We aim to develop a disposable microfluidic chip capable of performing an immune readout with the sensitivity needed to guide diagnostic decision making as close as possible to the patient. As a proof of concept of the fluidics module of this concept, acquisition of a limited immune panel based on CD45, CD8, programmed cell death protein 1 (PD1), and a live/dead marker was compared to a conventional flow cytometer (BD FACSymphony). Based on a dataset of peripheral blood mononuclear cells of 15 patients with ovarian cancer across different stages of treatment, we obtained a 99% correlation coefficient for the detection of CD8+PD1+ T cells relative to the total amount of CD45+ white blood cells. Upon further system development comprising further miniaturization of optics, this microfluidics chip could enable immune monitoring in an outpatient setting, facilitating rapid acquisition of data without the need for highly trained staff.

Sonographic, Demographic, and Clinical Characteristics of Pre- and Postmenopausal Women with Endometrial Cancer; Results from a Post Hoc Analysis of the IETA4 (International Endometrial Tumor Analysis) Multicenter Cohort.

In this study, we conducted a comparative analysis of demographic, histopathological, and sonographic characteristics between pre- and postmenopausal women diagnosed with endometrial cancer, while also examining sonographic and anthropometric features in 'low' and 'intermediate/high-risk' cases, stratified by menopausal status. Our analysis, based on data from the International Endometrial Tumor Analysis (IETA) 4 cohort comprising 1538 women (161 premenopausal, 1377 postmenopausal) with biopsy-confirmed endometrial cancer, revealed that premenopausal women, compared to their postmenopausal counterparts, exhibited lower parity (median 1, IQR 0-2 vs. 1, IQR 1-2, p = 0.001), a higher family history of colon cancer (16% vs. 7%, p = 0.001), and smaller waist circumferences (median 92 cm, IQR 82-108 cm vs. 98 cm, IQR 87-112 cm, p = 0.002). Premenopausal women more often had a regular endometrial-myometrial border (39% vs. 23%, p < 0.001), a visible endometrial midline (23% vs. 11%, p < 0.001), and undefined tumor (73% vs. 84%, p = 0.001). Notably, despite experiencing a longer duration of abnormal uterine bleeding (median 5 months, IQR 3-12 vs. 3 months, 2-6, p < 0.001), premenopausal women more often had 'low' risk disease (78% vs. 46%, p < 0.001). Among sonographic and anthropometric features, only an irregular endometrial-myometrial border was associated with 'intermediate/high' risk in premenopausal women. Conversely, in postmenopausal women, multiple features correlated with 'intermediate/high' risk disease. Our findings emphasize the importance of considering menopausal status when evaluating sonographic features in women with endometrial cancer.

Evaluation of Adnexal Masses: The IOTA Concept.

Ovarian lesions have a wide range of sonomorphological features with numerous different underlying benign and malignant histologies. Based on the studies conducted by the International Ovarian Tumor Analysis (IOTA) group, ovarian masses can currently be reliably characterized by ultrasound. In the following article, we explain how to use the IOTA terms and definitions and we provide insight into how to safely triage patients with an ovarian mass.

Pan-Cancer Detection and Typing by Mining Patterns in Large Genome-Wide Cell-Free DNA Sequencing Datasets.

BACKGROUND: Cell-free DNA (cfDNA) analysis holds great promise for non-invasive cancer screening, diagnosis, and monitoring. We hypothesized that mining the patterns of cfDNA shallow whole-genome sequencing datasets from patients with cancer could improve cancer detection. METHODS: By applying unsupervised clustering and supervised machine learning on large cfDNA shallow whole-genome sequencing datasets from healthy individuals (n = 367) and patients with different hematological (n = 238) and solid malignancies (n = 320), we identified cfDNA signatures that enabled cancer detection and typing. RESULTS: Unsupervised clustering revealed cancer type-specific sub-grouping. Classification using a supervised machine learning model yielded accuracies of 96% and 65% in discriminating hematological and solid malignancies from healthy controls, respectively. The accuracy of disease type prediction was 85% and 70% for the hematological and solid cancers, respectively. The potential utility of managing a specific cancer was demonstrated by classifying benign from invasive and borderline adnexal masses with an area under the curve of 0.87 and 0.74, respectively. CONCLUSIONS: This approach provides a generic analytical strategy for non-invasive pan-cancer detection and cancer type prediction.

The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression.

OBJECTIVE: Methods to correct class imbalance (imbalance between the frequency of outcome events and nonevents) are receiving increasing interest for developing prediction models. We examined the effect of imbalance correction on the performance of logistic regression models. MATERIAL AND METHODS: Prediction models were developed using standard and penalized (ridge) logistic regression under 4 methods to address class imbalance: no correction, random undersampling, random oversampling, and SMOTE. Model performance was evaluated in terms of discrimination, calibration, and classification. Using Monte Carlo simulations, we studied the impact of training set size, number of predictors, and the outcome event fraction. A case study on prediction modeling for ovarian cancer diagnosis is presented. RESULTS: The use of random undersampling, random oversampling, or SMOTE yielded poorly calibrated models: the probability to belong to the minority class was strongly overestimated. These methods did not result in higher areas under the ROC curve when compared with models developed without correction for class imbalance. Although imbalance correction improved the balance between sensitivity and specificity, similar results were obtained by shifting the probability threshold instead. DISCUSSION: Imbalance correction led to models with strong miscalibration without better ability to distinguish between patients with and without the outcome event. The inaccurate probability estimates reduce the clinical utility of the model, because decisions about treatment are ill-informed. CONCLUSION: Outcome imbalance is not a problem in itself, imbalance correction may even worsen model performance.

Similar long-term recurrence rates with cystectomy and CO2 laser vaporization for endometrioma: a retrospective study.

RESEARCH QUESTION: Is there a difference in recurrence rate of endometrioma(s) after cystectomy versus CO2 laser vaporization of the cyst wall? DESIGN: This single-centre retrospective study included 270 patients undergoing laparoscopic surgery for endometriomas between January 2010 and December 2014, stratified according to the surgical technique used. All 270 included patients underwent complete laparoscopic surgery for endometrioma(s): 155 underwent cystectomy, 63 complete CO2 laser vaporization of the cyst wall and 52 a mixed technique. The primary outcome studied was the difference in recurrence rate between the cystectomy group and the CO2 laser vaporization group. RESULTS: The mean duration of follow-up was 58 (±34) months. Imaging-based recurrence (any cyst size) was reported in 9.9% of patients (n = 12/121) treated with cystectomy and in 13.3% of patients (n = 6/45) who underwent a vaporization (P = 0.577). The need for reintervention for endometrioma(s) was also similar in both groups, with a rate of 3.2% (n = 5/155) after cystectomy and 4.8% (n = 3/63) after vaporization (P = 0.476). Of 160 women who wanted to conceive immediately after surgery, 73.8% became pregnant (72.6% [77/106] in the cystectomy group and 75.9% [41/54] in the vaporization group [P = 0.310]). Conception occurred mostly by assisted reproductive technology (57.1% [44/77] in the cystectomy group and 70.7% [29/41] in the vaporization group [P = 0.074]). CONCLUSIONS: Similar rates of recurrence for endometrioma(s) were observed after cystectomy versus CO2 laser vaporization. As other studies have suggested that CO2 laser vaporization may be less harmful to the normal ovarian tissue, it can be considered as a safe alternative for cystectomy in women wishing to preserve their reproductive potential.

Nucleosome footprinting in plasma cell-free DNA for the pre-surgical diagnosis of ovarian cancer.

Fragmentation patterns of plasma cell-free DNA (cfDNA) are known to reflect nucleosome positions of cell types contributing to cfDNA. Based on cfDNA fragmentation patterns, the deviation in nucleosome footprints was quantified between diagnosed ovarian cancer patients and healthy individuals. Multinomial modeling was subsequently applied to capture these deviations in a per sample nucleosome footprint score. Validation was performed in 271 cfDNAs pre-surgically collected from women with an adnexal mass. We confirmed that nucleosome scores were elevated in invasive carcinoma patients, but not in patients with benign or borderline disease. Combining nucleosome scores with chromosomal instability scores assessed in the same cfDNA improved prediction of malignancy. Nucleosome scores were, however, more reliable to predict non-high-grade serous ovarian tumors, which are characterized by low chromosomal instability. These data highlight that compared to chromosomal instability, nucleosome footprinting provides a complementary and more generic read-out for pre-surgical diagnosis of invasive disease in women with adnexal masses.

Prognostic factors for post-traumatic stress, anxiety and depression in women after early pregnancy loss: a multi-centre prospective cohort study.

OBJECTIVES: To investigate prognostic factors for anxiety, depression and post-traumatic stress (PTS) symptoms 1 month after early pregnancy loss (EPL). DESIGN: A prospective cohort study. Consecutive women were recruited, and demographic and clinical data were collected. Surveys containing the Hospital Anxiety and Depression Scale (HADS) and Post-traumatic Stress Diagnostic Scale (PDS) were emailed 1 month after a loss. Univariable logistic regression was performed to link factors with caseness of anxiety, depression or PTS according to screening measures. SETTING: Early pregnancy units of three central London hospitals. PARTICIPANTS: 737/1116 eligible women with an EPL were recruited. 492 responded to HADS and 487 to PDS. PRIMARY AND SECONDARY OUTCOME MEASURES: Primary outcome is the area under the curve (AUC) to predict any psychological morbidity (defined as moderate/severe anxiety or depression, or meeting screening criteria for PTS) for each variable. Further outcomes are explained variation (R2) and p value for any morbidity, and AUC, explained variation, and p value for each morbidity separately. RESULTS: Women who had a past diagnosis of a psychiatric condition were more likely to meet criteria for anxiety, depression or PTS (75% for current diagnosis vs 55% for past vs 30% for no diagnosis; AUC 0.61; R2 8.4%; p<0.0001), as were those with previous pregnancy loss (48% vs 30%; AUC 0.59; R2 4.3%; p<0.0001). Most of the assessed factors did not demonstrate potential utility in predicting psychological distress, including gestational age, overnight admission, time taken for diagnosis, pre-existing children and the diagnosis itself (miscarriage vs ectopic vs other) (AUCs≤0.54; R2≤0.9%). CONCLUSIONS: Women with a history of mental health problems, or those with previous losses, may be at higher risk of psychological illness 1 month after pregnancy loss. However, prognostic ability was poor overall. All women should be considered at risk.

The Risk of Endometrial Malignancy and Other Endometrial Pathology in Women with Abnormal Uterine Bleeding: An Ultrasound-Based Model Development Study by the IETA Group.

OBJECTIVES: The aim of this study was to develop a model that can discriminate between different etiologies of abnormal uterine bleeding. DESIGN: The International Endometrial Tumor Analysis 1 study is a multicenter observational diagnostic study in 18 bleeding clinics in 9 countries. Consecutive women with abnormal vaginal bleeding presenting for ultrasound examination (n = 2,417) were recruited. The histology was obtained from endometrial sampling, D&C, hysteroscopic resection, hysterectomy, or ultrasound follow-up for >1 year. METHODS: A model was developed using multinomial regression based on age, body mass index, and ultrasound predictors to distinguish between: (1) endometrial atrophy, (2) endometrial polyp or intracavitary myoma, (3) endometrial malignancy or atypical hyperplasia, (4) proliferative/secretory changes, endometritis, or hyperplasia without atypia and validated using leave-center-out cross-validation and bootstrapping. The main outcomes are the model's ability to discriminate between the four outcomes and the calibration of risk estimates. RESULTS: The median age in 2,417 women was 50 (interquartile range 43-57). 414 (17%) women had endometrial atrophy; 996 (41%) had a polyp or myoma; 155 (6%) had an endometrial malignancy or atypical hyperplasia; and 852 (35%) had proliferative/secretory changes, endometritis, or hyperplasia without atypia. The model distinguished well between malignant and benign histology (c-statistic 0.88 95% CI: 0.85-0.91) and between all benign histologies. The probabilities for each of the four outcomes were over- or underestimated depending on the centers. LIMITATIONS: Not all patients had a diagnosis based on histology. The model over- or underestimated the risk for certain outcomes in some centers, indicating local recalibration is advisable. CONCLUSIONS: The proposed model reliably distinguishes between four histological outcomes. This is the first model to discriminate between several outcomes and is the only model applicable when menopausal status is uncertain. The model could be useful for patient management and counseling, and aid in the interpretation of ultrasound findings. Future research is needed to externally validate and locally recalibrate the model.