Machine Learning techniques in breast cancer prognosis prediction: A primary evaluation.

More than 750 000 women in Italy are surviving a diagnosis of breast cancer. A large body of literature tells us which characteristics impact the most on their prognosis. However, the prediction of each disease course and then the establishment of a therapeutic plan and follow-up tailored to the patient is still very complicated. In order to address this issue, a multidisciplinary approach has become widely accepted, while the Multigene Signature Panels and the Nottingham Prognostic Index are still discussed options. The current technological resources permit to gather many data for each patient. Machine Learning (ML) allows us to draw on these data, to discover their mutual relations and to esteem the prognosis for the new instances. This study provides a primary evaluation of the application of ML to predict breast cancer prognosis. We analyzed 1021 patients who underwent surgery for breast cancer in our Institute and we included 610 of them. Three outcomes were chosen: cancer recurrence (both loco-regional and systemic) and death from the disease within 32 months. We developed two types of ML models for every outcome (Artificial Neural Network and Support Vector Machine). Each ML algorithm was tested in accuracy (=95.29%-96.86%), sensitivity (=0.35-0.64), specificity (=0.97-0.99), and AUC (=0.804-0.916). These models might become an additional resource to evaluate the prognosis of breast cancer patients in our daily clinical practice. Before that, we should increase their sensitivity, according to literature, by considering a wider population sample with a longer period of follow-up. However, specificity, accuracy, minimal additional costs, and reproducibility are already encouraging.

Wound healing and postsurgical complications in breast cancer surgery: a comparison between PEAK PlasmaBlade and conventional electrosurgery - a preliminary report of a case series.

PURPOSE: PEAK PlasmaBlade is a recent and distinctive type of electrosurgical device. Previous studies have already documented some meaningful advantages of this device over conventional electrosurgery. This study compared the use of PEAK PlasmaBlade to standard electrosurgery in mastectomy and breast conservative surgery. The purpose was to test the impact of PEAK PlasmaBlade on the wound-healing process and on postsurgical complications in breast cancer surgery. METHODS: Sixty patients undergoing breast cancer surgery were enrolled. The PEAK PlasmaBlade was used for 20 of those. A standard electrosurgical device was used for the other 40 patients. The 2 groups were homogenous in age, body mass index, comorbidities and type of surgery. We recorded wound complications, serum drainage amount and duration of stay, blood loss, time of surgery, length of hospital stay, and total number of medications required. RESULTS: The 2 groups were not significantly different in terms of patient characteristics. A statistically significant reduction in incidence of seroma was observed in the PEAK group: only 10% versus 37.5% of the patients in the conventional electrosurgery group developed this complication (Fisher exact test, P = 0.034). CONCLUSION: Seroma is the most important wound complication in breast surgery. The research of new instruments that might reduce its incidence is desirable. In order to validate or deny the results of this study, it is necessary to enroll more subjects and to consider the impact of this device on axillary lymph node dissection.

Thyroidectomy in elderly patients aged ≥70 years.

Worldwide, the indications for thyroid surgery have been continuously extended among elderly patients in the last 20 years. The balance between treatment indication and surgical risk is certainly an interesting topic for every thyroid surgeon. This paper is a review of recent literature from January 2005 up to April 2017. We analyzed three principal subjects: indications for surgical treatment, medical complications and surgical complications. We can summarize the conclusions of our analysis, stating that age could not be considered as an absolute factor, but in relation to the comorbidities and the general clinical condition of the patient. Special risk indices dedicated to geriatric patients could be very useful in order to facilitate the decision-making process; however, relying on the current knowledge, we could state that there is value in providing surgery to geriatric patients in highly specialized and high-volume centers, where access to technology and its systematic use, coupled with surgeons' experience, could certainly avail the geriatric patient management.