In recent years personalized medicine reached an increasing importance, especially in the design of oncological therapies. In particular, the development of patients’ profiling strategies suggests the possibility of promising rewards. In this work, we present an explainable artificial intelligence (XAI) framework based on an adaptive dimensional reduction which (i) outlines the most important clinical features for oncological patients’ profiling and (ii), based on these features, determines the profile, i.e., the cluster a patient belongs to. For these purposes, we collected a cohort of 267 breast cancer patients. The adopted dimensional reduction method determines the relevant subspace where distances among patients are used by a hierarchical clustering procedure to identify the corresponding optimal categories. Our results demonstrate how the molecular subtype is the most important feature for clustering. Then, we assessed the robustness of current therapies and guidelines; our findings show a striking correspondence between available patients’ profiles determined in an unsupervised way and either molecular subtypes or therapies chosen according to guidelines, which guarantees the interpretability characterizing explainable approaches to machine learning techniques. Accordingly, our work suggests the possibility to design data-driven therapies to emphasize the differences observed among the patients.

Cancer treatment planning benefits from an accurate early prediction of the treatment efficacy. The goal of this study is to give an early prediction of three-year Breast Cancer Recurrence (BCR) for patients who underwent neoadjuvant chemotherapy. We addressed the task from a new perspective based on transfer learning applied to pre-treatment and early-treatment DCE-MRI scans. Firstly, low-level features were automatically extracted from MR images using a pre-trained Convolutional Neural Network (CNN) architecture without human intervention. Subsequently, the prediction model was built with an optimal subset of CNN features and evaluated on two sets of patients from I-SPY1 TRIAL and BREAST-MRI-NACT-Pilot public databases: a fine-tuning dataset (70 not recurrent and 26 recurrent cases), which was primarily used to find the optimal subset of CNN features, and an independent test (45 not recurrent and 17 recurrent cases), whose patients had not been involved in the feature selection process. The best results were achieved when the optimal CNN features were augmented by four clinical variables (age, ER, PgR, HER2+), reaching an accuracy of 91.7% and 85.2%, a sensitivity of 80.8% and 84.6%, a specificity of 95.7% and 85.4%, and an AUC value of 0.93 and 0.83 on the fine-tuning dataset and the independent test, respectively. Finally, the CNN features extracted from pre-treatment and early-treatment exams were revealed to be strong predictors of BCR.

Background: Several GI peptides linked to intestinal barrier function could be involved in the modification of intestinal permeability and the onset of diarrhea during adjuvant chemotherapy. The aim of the study was to evaluate the circulating levels of zonulin, glucagon-like peptide-2 (GLP-2), epidermal growth factor (EGF) and ghrelin and their relationship with intestinal permeability and chemotherapy induced diarrhea (CTD). Methods: Sixty breast cancer patients undergoing an FEC60 regimen were enrolled, 37 patients completed the study. CTD(+) patients were discriminated by appropriate questionnaire and criteria. During chemotherapy, intestinal permeability was assessed by lactulose/mannitol urinary test on day 0 and day 14. Zonulin, GLP-2, EGF and ghrelin circulating levels were evaluated by ELISA tests at five time-points (days 0, 3, 10, 14, and 21). Results: During FEC60 administration, the lactulose/mannitol ratio was significantly higher on day 14 than at baseline. Zonulin levels were not affected by chemotherapy, whereas GLP-2 and EGF levels decreased significantly. GLP-2 levels on day 14 were significantly lower than those on day 0 and day 3, while EGF values were significantly lower on day 10 than at the baseline. In contrast, the total concentrations of ghrelin increased significantly at day 3 compared to days 0 and 21, respectively. Ten patients (27%) suffered from diarrhea. On day 14 of chemotherapy, a significant increase of the La/Ma ratio occurred in CTD(+) patients compared to CTD(−) patients. With regards to circulating gut peptides, the AUCg of GLP-2 and ghrelin were significantly lower and higher in CTD(+) patients than CTD(−) ones, respectively. Finally in CTD(+) patients a significant and inverse correlation between GLP-2 and La/Ma ratio was found on day 14. Conclusions: Breast cancer patients undergoing FEC60 showed alterations in the intestinal permeability, which was associated with modifications in the levels of GLP-2, ghrelin and EGF. In CTD(+) patients, a different GI peptide profile and increased intestinal permeability was found in comparison to CTD(−) patients. This evidence deserves further studies for investigating the potentially different intestinal luminal and microbiota conditions. Trial registration: Clinical trial NCT01382667

To date, some artificial intelligence (AI) methods have exploited Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) to identify finer tumor properties as potential earlier indicators of pathological Complete Response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). However, they work either for sagittal or axial MRI protocols. More flexible AI tools, to be used easily in clinical practice across various institutions in accordance with its own imaging acquisition protocol, are required. Here, we addressed this topic by developing an AI method based on deep learning in giving an early prediction of pCR at various DCE-MRI protocols (axial and sagittal). Sagittal DCE-MRIs refer to 151 patients (42 pCR; 109 non-pCR) from the public I-SPY1 TRIAL database (DB); axial DCE-MRIs are related to 74 patients (22 pCR; 52 non-pCR) from a private DB provided by Istituto Tumori “Giovanni Paolo II” in Bari (Italy). By merging the features extracted from baseline MRIs with some pre-treatment clinical variables, accuracies of 84.4% and 77.3% and AUC values of 80.3% and 78.0% were achieved on the independent tests related to the public DB and the private DB, respectively. Overall, the presented method has shown to be robust regardless of the specific MRI protocol.

In the absence of lymph node abnormalities detectable on clinical examination or imaging, the guidelines provide for the dissection of the first axillary draining lymph nodes during surgery. It is not always possible to arrive at surgery without diagnostic doubts, and machine learning algorithms can support clinical decisions. The web calculator CancerMath (CM) allows you to estimate the probability of having positive lymph nodes valued on the basis of tumor size, age, histologic type, grading, expression of estrogen receptor, and progesterone receptor. We collected 993 patients referred to our institute with clinically negative results characterized by sentinel lymph node status, prognostic factors defined by CM, and also human epidermal growth factor receptor 2 (HER2) and Ki-67. Area Under the Curve (AUC) values obtained by the online CM application were comparable with those obtained after training its algorithm on our database. Nevertheless, by training the CM model on our dataset and using the same feature, we reached a sensitivity median value of 72%, whereas the online one was equal to 46%, despite a specificity reduction. We found that the addition of the prognostic factors Her2 and Ki67 could help improve performances on the classification of particular types of patients with the aim of reducing as much as possible the false positives that lead to axillary dissection. As showed by our experimental results, it is not particularly suitable for use as a support instrument for the prediction of metastatic lymph nodes on clinically negative patients.

Addition of trastuzumab to adjuvant chemotherapy has dramatically reduced the risk of recurrence and has become the standard of care for human epidermal growth factor receptor 2 (HER2)-positive early breast cancer patients. Since most data on trastuzumab benefits come from clinical trials, conducted in selected patient populations, we performed a retrospective analysis of HER2-positive early breast cancer patients treated in the “pre-trastuzumab” and “trastuzumab” eras, with the aim to determine patients' outcomes in real-world practice. 925 consecutive HER2-positive breast cancer patients treated with adjuvant chemotherapy in ten Italian oncologic centers were identified. Patients who had received adjuvant chemotherapy alone (cohort A, 352 patients), and patients who had received adjuvant chemotherapy followed or combined with trastuzumab (cohort B, 573 patients) were analyzed. Relapse rate at 3 years, relapse-free survival, and overall survival were significantly more unfavorable in the cohort A than in the cohort B (p < 0.0001). In multivariate analysis, factors related to relapse were younger age, advanced stage at diagnosis, absence of hormonal and of trastuzumab therapy. The benefit derived from the addition of trastuzumab was independent of nodal status and hormonal receptors expression. A subgroup analysis including 163 “triple positive” tumors with high levels of estrogen and progesterone receptor (TP50) suggested that addition of trastuzumab to adjuvant chemotherapy and hormonal therapy did not translate into better outcomes. In our analysis, trastuzumab benefit was confirmed in all but a small subset of TP50 tumors subgroups. In this subset further investigations are needed.