Search

Abstract Background Depression is a common condition among cancer patients, across several points in the disease trajectory. Although presenting higher prevalence rates than the general population, it is often not reported or remains unnoticed. Moreover, somatic symptoms of depression are common in the oncological context and should not be dismissed as a general symptom of cancer. It becomes even more challenging to track psychological distress in the period after the treatment, where connection with the healthcare system typically becomes sporadic. The main goal of the FAITH project is to remotely identify and predict depressive symptoms in cancer survivors, based on a federated machine learning (ML) approach, towards optimization of privacy. Methods FAITH will remotely analyse depression markers, predicting their negative trends. These markers will be treated in distinct categories, namely nutrition, sleep, activity and voice, assessed in part through wearable technologies. The study will include 300 patients who have had a previous diagnosis of breast or lung cancer and will be recruited 1 to 5 years after the end of primary cancer. The study will be organized as a 12-month longitudinal prospective observational cohort study, with monthly assessments to evaluate depression symptoms and quality of life among cancer survivors. The primary endpoint is the severity of depressive symptoms as measured by the Hamilton Depression Rating Scale (Ham-D) at months 3, 6, 9 and 12. Secondary outcomes include self-reported anxiety and depression symptoms (HADS scale), and perceived quality of life (EORTC questionnaires), at baseline and monthly. Based on the predictive models gathered during the study, FAITH will also aim at further developing a conceptual federated learning framework, enabling to build machine learning models for the prediction and monitoring of depression without direct access to user’s personal data. Discussion Improvements in the objectivity of psychiatric assessment are necessary. Wearable technologies can provide potential indicators of depression and anxiety and be used for biofeedback. If the FAITH application is effective, it will provide healthcare systems with a novel and innovative method to screen depressive symptoms in oncological settings. Trial registration Trial ID: ISRCTN10423782 . Date registered: 21/03/2022.

Abstract Triple-negative breast cancer (TNBC) is highly responsive to neoadjuvant polychemotherapy regimens including anthracyclines, taxanes, and, more recently, carboplatin. However, there is inadequate information on the individual contribution of each of these agents to the global activity of the combinations, and the use of combinations of up to four of these drugs is associated with relevant toxicity. Identifying single-drug activity in the clinical neoadjuvant setting is challenging. We developed patient-derived xenografts (PDXs) from several chemotherapy-naïve TNBC samples to assess the antitumor activity of single drugs and combinations of drugs. PDXs were established from chemotherapy-naïve TNBC samples. Nine TNBC PDX models (all of which corresponded to a basal-like phenotype according to the PAM50 classifier) were treated with carboplatin, docetaxel, and doxorubicin and the combination of docetaxel and carboplatin. Only one of nine PDX models showed sensitivity to doxorubicin, while eight of nine PDX models showed sensitivity to docetaxel and carboplatin as single agents. The 3 PDX models derived from patients with gBRCA-1 or gPALB2 mutations were very sensitive to carboplatin single agent. All 6 PDX models from patients without hereditary germ-line mutations showed increased sensitivity to the combination of docetaxel and carboplatin. In the present study, docetaxel and carboplatin single agents were active drugs against basal-like TNBC, while doxorubicin monotherapy showed low activity. The combination of docetaxel and carboplatin was more effective than the drugs used as single agents, except in the PDX from patients with gBRCA1/PALB2 mutations.

Background: Cancer patients represent a vulnerable population for COVID-19 illness. We aimed to analyze outcomes of lung cancer patients affected by COVID-19 in a tertiary hospital of a high-incidence region during the pandemic.Methods: We annotated 23 lung cancer patients consecutively diagnosed with COVID-19 at our institution (HGUGM; Madrid, Spain) between March 4th, 2020 and May 12th, 2020. Only patients with a confirmatory SARS-CoV-2 RT-PCR were included in the study.Results: All patients had at least 1 COVID-19 related symptom; cough (48%), shortness of breath (48%), fever (39%), and low-grade fever (30%) were the most common. Time from symptoms onset to first positive SARS-CoV-2 PCR was 5.5 days (range 1–17), with 13% of cases needed from a 2nd PCR to confirm diagnosis. There was a high variability on thoracic imaging findings, with multilobar pneumonia as the most commonly found pattern (74%). Main lab test abnormalities were low lymphocytes count (87%), high neutrophil to lymphocyte ratio -NLR- (78%), and elevated inflammatory markers: fibrinogen (91%), c-reactive protein -CRP- (87%), and D-dimer (70%). In our series, hospitalization rate was 74%, 39% of patients developed acute respiratory distress syndrome (ARDS), and the case-fatality rate was 35% (8/23). 87% of patients received anti-viral treatment (87% hydroxychloroquine, 74% lopinavir/ritonavir, 13% azithromycin), 43% corticosteroids, 26% interferon-β, 4% tocilizumab, and 82% of hospitalized patients received anticoagulation. High-oxygen requirements were needed in 39% of patients, but only 1 pt was admitted for invasive MV and was discharged 42 days after admission. Multiple variables related to tumor status, clinical baseline conditions, and inflammation markers were associated with mortality but did not remain statistically significant in a multivariate model. In patients with lung cancer receiving systemic therapy (n = 242) incidence and mortality from COVID-19 were 4.5, and 2.1%, respectively, with no differences found by type of treatment.Conclusions: Lung cancer patients represent a vulnerable population for COVID-19, according to the high rate of hospitalization, onset of ARDS, and high mortality rate. Although larger series are needed, no differences in mortality were found by type of cancer treatment. Measures to minimize the risk of SARS-CoV-2 infection remain key to protect lung cancer patients.

Over the last decade, regularized regression methods have offered alternatives for performing multi-marker analysis and feature selection in a whole genome context. The process of defining a list of genes that will characterize an expression profile remains unclear. It currently relies upon advanced statistics and can use an agnostic point of view or include some a priori knowledge, but overfitting remains a problem. This paper introduces a methodology to deal with the variable selection and model estimation problems in the high-dimensional set-up, which can be particularly useful in the whole genome context. Results are validated using simulated data and a real dataset from a triple-negative breast cancer study.