Search

Abstract Image‐based machine learning tools are an ascendant ‘big data’ research avenue. Citizen science platforms, like iNaturalist, and museum‐led initiatives provide researchers with an abundance of data and knowledge to extract. These include extraction of metadata, species identification, and phenomic data. Ecological and evolutionary biologists are increasingly using complex, multi‐step processes on data. These processes often include machine learning techniques, often built by others, that are difficult to reuse by other members in a collaboration. We present a conceptual workflow model for machine learning applications using image data to extract biological knowledge in the emerging field of imageomics. We derive an implementation of this conceptual workflow for a specific imageomics application that adheres to FAIR principles as a formal workflow definition that allows fully automated and reproducible execution, and consists of reusable workflow components. We outline technologies and best practices for creating an automated, reusable and modular workflow, and we show how they promote the reuse of machine learning models and their adaptation for new research questions. This conceptual workflow can be adapted: it can be semi‐automated, contain different components than those presented here, or have parallel components for comparative studies. We encourage researchers—both computer scientists and biologists—to build upon this conceptual workflow that combines machine learning tools on image data to answer novel scientific questions in their respective fields.

Julia Savel,1,2 Marianne Lafitte,1 Yann Pucheu,1,3 Vincent Pradeau,1 Antoine Tabarin,2,3 Thierry Couffinhal1,3,41Centre d'Exploration, de Prévention et de Traitement de l'Athérosclérose, Hôpital Cardiologique, 2Service d'endocrinologie, CHU Bordeaux, Université Bordeaux Segalen, Bordeaux, France; 3Université de Bordeaux Adaptation cardiovasculaire à l'ischémie, 4INSERM, Adaptation cardiovasculaire à l'ischémie, U1034, Pessac, FranceAbstract: A number of epidemiological and clinical studies have demonstrated that plasma high-density lipoprotein (HDL) level is a strong inverse predictor of cardiovascular events. HDL is believed to retard the formation of atherosclerotic lesions by removing excess cholesterol from cells and preventing endothelial dysfunction. Lecithin cholesterol acyltransferase (LCAT) plays a central role in the formation and maturation of HDL, and in the intravascular stage of reverse cholesterol transport: a major mechanism by which HDL modulates the development and progression of atherosclerosis. A defect in LCAT function would be expected to enhance atherosclerosis, by interfering with the reverse cholesterol transport step. As such, one would expect to find more atherosclerosis and cardiovascular events in LCAT-deficient patients. But this relationship is not always evident. In this review, we describe contradictory reports in the literature about cardiovascular risks in this patient population. We discuss the paradoxical finding of severe HDL deficiency and an absence of subclinical atherosclerosis in LCAT-deficient patients, which has been used to reject the hypothesis that HDL level is important in the protection against atherosclerosis. Furthermore, to illustrate this paradoxical finding, we present a case study of one patient, referred for evaluation of global cardiovascular risk in the presence of a low HDL cholesterol level, who was diagnosed with LCAT gene mutations.Keywords: atherosclerosis, LCAT function, cardiovascular risk, high-density lipoprotein

This report describes a rare case of a 20-year-old man with an ACTH- and prolactin-secreting invasive pituitary macroadenoma causing hyperprolactinemia and Cushing’s disease. He was later found to have an AIP mutation. Treatment with cabergoline (1.5 mg weekly) normalized prolactin concentrations and induced a major shrinkage of the adenoma. Not only was urinary free cortisol normalized for more than 14 years, but also the treatment induced normal hypothalamo-pituitary-adrenal (HPA) axis function as illustrated by the reappearance of a normal cortisol/ACTH circadian rhythm, cortisol suppression to dexamethasone, and disappearance of the excessive and aberrant responses to CRH and desmopressin, respectively. This case is the first description of complete restoration of the physiological characteristics of the HPA axis by a medication during the treatment of Cushing’s disease. Although exceptional, it illustrates that drugs targeting the pituitary adenoma can bring true complete remission of Cushing’s disease.

Purpose: Mosaicism is a feature of several inherited tumor syndromes. Only a few cases of mosaicism have been described in multiple endocrine neoplasia type 1 (MEN1). Next-generation sequencing (NGS) offers new possibilities for detecti ng mosaicism. Here, we report the first study to systematically look for MEN1 mosaicism, using blood DNA, in MEN1-suspected patients but without MEN1 pathogenic variants (PV) in a heterozygous state. Methods: Digital targeted NGS, including unique molecular identifiers (U MIs), was performed in routine practice, and the analytic performance of this method was verified. Results: Among a cohort of 119 patients harboring from 2 to 5 MEN1 lesions, we identified 3 patients with MEN1 mosaic PVs. The allele frequencies ranged from 2.3 to 9.5%. The detection rate of MEN1 mosaicism in patients bearing at least 3 MEN1 lesions was 17% (3/18). No cases were detected in patients with two lesions. Conclusion: We report here three new cases with MEN1 mosaicism. This study examined the performance of UMI in the diagnosis of MEN1 mosaicism in routine practice, and our results underline that the frequency of mosaicism is probably underestimated in patients with suspected MEN1.

Abstract Introduction The first line of treatment for nonfunctioning pituitary adenoma (NFPA) is surgery. Adjuvant radiotherapy or surveillance and new treatment (second surgical operation or salvage radiotherapy) in case of recurrence are options discussed at the multidisciplinary tumor board. The purpose of this study was to evaluate the therapeutic outcome for each option. Methods The records of 256 patients followed with NFPA between 2007 and 2018 were retrospectively reviewed. Mean age at initial surgery was 55 years [18–86]. Post-operative MRI found a residual tumor in 87% of patients. Mean follow-up was 12.1 years [0.8–42.7]. Results After initial surgery, 40 patients had adjuvant radiotherapy. At 5, 10 and 15 years progression-free survival (PFS) was significantly different after surgery alone (77%, 58% and 40%) compared to surgery and adjuvant radiotherapy (84%, 78% and 78%) (HR = 0.24 [0–0.53] p

The El Niño–Southern Oscillation (ENSO) occurs in three phases: neutral, warm (El Niño), and cool (La Niña). While classifying El Niño and La Niña is relatively straightforward, El Niño events can be broadly classified into two types: central Pacific (CP) and eastern Pacific (EP). Differentiating between CP and EP events is currently dependent on both the method and observational dataset used. In this study, we create a new classification scheme using supervised machine learning trained on 18 observational and re-analysis products. This builds on previous work by identifying classes of events using the temporal evolution of sea surface temperature in multiple regions across the tropical Pacific. By applying this new classifier to seven single model initial-condition large ensembles (SMILEs) we investigate both the internal variability and forced changes in each type of ENSO event, where events identified behave similarly to those observed. It is currently debated whether the observed increase in the frequency of CP events after the late 1970s is due to climate change. We found it to be within the range of internal variability in the SMILEs for trends after 1950, but not for the full observed period (1896 onwards). When considering future changes, we do not project a change in CP frequency or amplitude under a strong warming scenario (RCP8.5/SSP370) and we find model differences in EP El Niño and La Niña frequency and amplitude projections. Finally, we find that models show differences in projected precipitation and sea surface temperature (SST) pattern changes for each event type that do not seem to be linked to the Pacific mean state SST change, although the SST and precipitation changes in individual SMILEs are linked. Our work demonstrates the value of combining machine learning with climate models, and highlights the need to use SMILEs when evaluating ENSO in climate models because of the large spread of results found within a single model due to internal variability alone.

Background: Cushing’s syndrome (CS) is a rare condition of chronically elevated cortisol levels resulting in diverse comorbidities, many of which endure beyond successful treatment affecting the quality of life. Few data are available concerning patients’ experiences of diagnosis, care and persistent comorbidities. Objective: To assess CS patients’ perspectives on the diagnostic and care journey to identify unmet therapeutic needs. Methods: A 12-item questionnaire was circulated in 2019 by the World Association for Pituitary Organisations. A parallel, 13-item questionnaire assessing physician perceptions on CS patient experiences was performed. Results: Three hundred twenty CS patients from 30 countries completed the questionnaire; 54% were aged 35–54 and 88% were female; 41% were in disease remission. The most burdensome symptom was obesity/weight gain (75%). For 49% of patients, time to diagnosis was over 2 years. Following treatment, 88.4% of patients reported ongoing symptoms including, fatigue (66.3%), muscle weakness (48.8%) and obesity/weight gain (41.9%). Comparisons with delay in diagnosis were significant for weight gain (P = 0.008) and decreased libido (P = 0.03). Forty physicians completed the parallel questionnaire which showed that generally, physicians poorly estimated the prevalence of comorbidities, particularly initial and persistent cognitive impairment. Only a minority of persistent comorbidities (occurrence in 1.3–66.3%; specialist treatment in 1.3–29.4%) were managed by specialists other than endocrinologists. 63% of patients were satisfied with treatment. Conclusion: This study confirms the delay in diagnosing CS. The high prevalence of persistent comorbidities following remission and differences in perceptions of health between patients and physicians highlight a probable deficiency in effective multidisciplinary management for CS comorbidities.

Context Current guidelines for distinguishing Cushing's disease (CD) from ectopic ACTH secretion (EAS) are questionable, as they use pituitary magnetic resonance imaging (MRI) as first-line investigation for all patients. CRH testing is no longer available, and they suggest performing inferior petrosal sinus sampling (BIPPS), an invasive and rarely available investigation, in many patients. Objective To establish noninvasive personalized diagnostic strategies based on the probability of EAS estimated from simple baseline parameters. Design Retrospective study. Setting University hospitals. Patients Two hundred forty-seven CD and 36 EAS patients evaluated between 2001 and 2023 in 2 French hospitals. A single-center cohort of 105 Belgian patients served as external validation. Results Twenty-four-hour urinary free cortisol (UFC) had the highest area under the receiver operating characteristic curve for discrimination of CD from EAS (.96 [95% confidence interval (CI),.92-.99] in the primary study and.99 [95% CI,.98-1.00] in the validation cohort). The addition of clinical, imaging, and biochemical parameters did not improve EAS prediction over UFC alone, with only BIPPS showing a modest improvement (C-statistic index.99 [95% CI,.97-1.00]). Three groups were defined based on baseline UFC: < 3 (group 1), 3-10 (group 2), and > 10 × the upper limit of normal (group 3), and they were associated with 0%, 6.1%, and 66.7% prevalence of EAS, respectively. Diagnostic approaches performed in our cohort support the use of pituitary MRI alone in group 1, MRI first followed by neck-to-pelvis computed tomography scan (npCT) when negative in group 2, and npCT first followed by pituitary MRI when negative in group 3. When not combined with the CRH test, the desmopressin test has limited diagnostic value. Conclusion UFC accurately predicts EAS and can serve to define personalized and noninvasive diagnostic algorithms. [ABSTRACT FROM AUTHOR]

ContextImpaired cognition and altered quality of life (QoL) may persist despite long-term remission of Cushing’s disease (CD). Persistent comorbidities and treatment modalities may account for cognitive impairments. Therefore, the role of hypercortisolism per se on cognitive sequelae remains debatable.ObjectiveTo investigate whether memory and QoL are impaired after long-term remission of CD in patients with no confounding comorbidity.Design and SettingCross-sectional case-control study in two tertiary referral centersPatients25 patients (44.5 ± 2.4 years) in remission from CD for 102.7 ± 19.3 Mo and 25 well-matched controls, without comorbidity or treatment liable to impair cognition.Main Outcome Measure(s)Hippocampus- and prefrontal cortex-dependent memory, including memory flexibility and working memory, were investigated using multiple tests including sensitive locally-developed computerized tasks. Depression and anxiety were evaluated with the MADRS and HADS questionnaires. QoL was evaluated with the SF-36 and CushingQoL questionnaires. The intensity of CD was assessed using mean urinary free cortisol and a score for clinical symptoms.ResultsCD patients displayed similar performance to controls in all cognitive tests. In contrast, despite the absence of depression and a minimal residual clinical Cushing score, patients had worse QoL. Most of the SF36 subscales and the CushingQoL score were negatively associated only with the duration of exposure to hypercortisolism (p≤ 0.01 to 0.001).ConclusionsPersistent comorbidities can be a primary cause of long-lasting cognitive impairment and should be actively treated. Persistently altered QoL may reflect irreversible effects of hypercortisolism, highlighting the need to reduce its duration.Clinical Trial Registration numberhttps://clinicaltrials.gov, identifier NCT02603653

Importance A major issue in the management of craniopharyngioma-related obesity (CRO) is the ineffectiveness of the current therapeutic approaches. Objective To study the efficacy of glucagon-like peptide-1 analogs compared with placebo in adults with obesity CRO. Design A double-blind multicenter superiority randomized clinical in trial in two parallel arms. Setting Eleven French University Hospital Centers. Participants Adults with CRO (body mass index > 30 kg/m²) without the sign of recurrence of craniopharyngioma in the past year. Interventions Exenatide or placebo injected subcutaneously twice a day during 26 weeks. Main Outcomes and Measures The primary outcome was the mean change in body weight at week 26 in the intention-to-treat population. Secondary outcomes were eating behavior, calories intake, energy expenditure, cardiovascular, metabolic risk factor, quality of life, and the tolerance profile. Results At week 26, weight decreased from baseline by a mean of −3.8 (SD 4.3) kg for exenatide and −1.6 (3.8) kg for placebo. The adjusted mean treatment difference was −3.1 kg (95% confidence interval [CI] −7.0 to 0.7, P = 0.11). Results were compatible with a higher reduction of hunger score with exenatide compared with placebo (estimated treatment difference in change from baseline to week 26: −2.3, 95% CI −4.5 to −0.2), while all other outcomes did not significantly differ between groups. Adverse events were more common with exenatide versus placebo, and occurred in, respectively, 19 (95%) participants (108 events) and 14 (70%) participants (54 events). Conclusions and Relevance Combined with intensive lifestyle interventions, a 26-week treatment with exenatide was not demonstrated superior to placebo to treat craniopharyngioma-related obesity. [ABSTRACT FROM AUTHOR]