Text mining and word embedding for classification of decision making variables in breast cancer surgery.

INTRODUCTION: Decision making in surgical oncology of the breast has increased its complexity over the last twenty years. This Delphi survey investigates the opinion of an expert panel about the decision making process in surgical procedures on the breast for oncological purposes. METHODS: Twenty-seven experts were invited to partake into a Delphi Survey. At the first round they have been asked to provide a list of features involved in the decision making process (patient's characteristics; disease characteristics; surgical techniques, outcomes) and comment on it. Using text-mining techniques we extracted a list of mono-bi-trigrams potentially representative of decision drivers. A technique of "natural language processing" called Word2vec was used to validate changes to texts using synonyms and plesionyms. Word2Vec was also used to test the semantic relevance of n-grams within a corpus of knowledge made up of books edited by panel members. The final list of variables extracted was submitted to the judgement of the panel for final validation at the second round of the Delphi using closed ended questions. RESULTS: 52 features out of 59 have been approved by the panel. The overall consensus was 87.1% CONCLUSIONS: Text mining and natural language processing allowed the extraction of a number of decision drivers and outcomes as part of the decision making process in surgical oncology on the breast. This result was obtained transforming narrative texts into structured data. The high level of consensus among experts provided validation to this process.

International multidisciplinary expert panel consensus on breast reconstruction and radiotherapy.

BACKGROUND: Conflicting evidence challenges clinical decision-making when breast reconstruction is considered in the context of radiotherapy. Current literature was evaluated and key statements on topical issues were generated and discussed by an expert panel at the International Oncoplastic Breast Surgery Meeting in Milan 2017. METHODS: Studies on radiotherapy and breast reconstruction (1985 to September 2017) were screened using MEDLINE, Embase and CENTRAL. The literature review yielded 30 controversial key questions. A set of key statements was derived and the highest levels of clinical evidence (LoE) for each of these were summarized. Nineteen panellists convened for dedicated discussions at the International Oncoplastic Breast Surgery Meeting to express agreement, disagreement or abstention for the generated key statements. RESULTS: The literature review identified 1522 peer-reviewed publications. A list of 22 key statements was produced, with the highest LoE recorded for each statement. These ranged from II to IV, with most statements (11 of 22, 50 per cent) supported by LoE III. There was full consensus for nine (41 per cent) of the 22 key statements, and more than 75 per cent agreement was reached for half (11 of 22). CONCLUSION: Poor evidence exists on which to base patient-informed consent. Low-quality studies are conflicting with wide-ranging treatment options, precluding expert consensus regarding optimal type and timing of breast reconstruction in the context of radiotherapy. There is a need for high-quality evidence from prospective registries and randomized trials in this field.

ANTECEDENTES: El hecho de que la evidencia disponible sea conflictiva supone un reto para la toma de decisiones a la hora de considerar la reconstrucción mamaria en el contexto de radioterapia (radiotherapy, RT). En el seno de un panel de expertos reunidos durante el International Oncoplastic Breast Surgery Meeting celebrado en Milán en 2017, se revisó la literatura disponible y se generaron y discutieron los aspectos más relevantes. MÉTODOS: Se hizo una búsqueda bibliográfica de los estudios de RT y reconstrucción mamaria (1985-septiembre de 2017) en las bases MEDLINE, EMBASE y CENTRAL. La revisión de la literatura permitió identificar 30 cuestiones clave controvertidas. A partir de ellas, se construyeron una serie de afirmaciones, para las que se obtuvo el mayor nivel de evidencia (levels of clinical evidence, LoE) posible. El acuerdo, desacuerdo o abstención respecto a las cuestiones propuestas fueron el resultado de las discusiones de 19 expertos reunidos durante el International Oncoplastic Breast Surgery Meeting. RESULTADOS: Se identificaron 1.522 artículos publicados en revistas con peer review. Se elaboró una lista de 22 afirmaciones clave y se anotó el LoE más alto obtenido para cada una de ellas. El grado de variabilidad fue de II a IV, pero la mayoría de las afirmaciones (54,5%) obtuvieron un LoE III. Hubo un consenso total en el 41% (9/22) de las afirmaciones, mientras que se obtuvo más de un 75% de acuerdo en la mitad de las afirmaciones (11/22). CONCLUSIÓN: La evidencia en la que basar el consentimiento informado en estos pacientes es escasa. Se trata de estudios de baja calidad con gran variedad de opciones terapéuticas, que dificultan el consenso de los expertos acerca del tipo y momento óptimo para la reconstrucción mamaria en el contexto de RT. Para obtener datos de mayor calidad se precisan estudios prospectivos y ensayos clínicos en este campo.

De-escalation of complexity in oncoplastic breast surgery: Case series from a specialized breast center.

INTRODUCTION: Oncoplastic breast surgery has evolved the surgical treatment of breast cancer over the past two decades. This practice still lacks validation and poses several dilemmas in terms of safety, local and systemic control, timing of adjuvant treatments and cost-effectiveness. Our case series investigates the effects of a reduced surgical complexity on cosmetic results and quality of life. METHODS: We treated 76 consecutive patients affected by early stage breast cancer from January 2016 to April 2017. We employed a decision support system to assist the final shared decision making. The communication process before surgery included new specific information on recent evidence about local control of disease and outcomes after multimodality treatment. In order to estimate the oncoplastic complexity, we created a new score based on scars, bilateral procedures and type and timing of reconstructions. We compared the outcomes of this series to that of a previous one from the same institution. RESULTS: The medium complexity score (CS) in the current series was significantly lower compared to that of the previous series (medium CS cohort 1 = 3.1 vs medium CS cohort 2 = 1.51; p = 0.001). Complications according to Clavien-Dindo classification did not vary significantly between the two series (p = 0.7). The increased use of primary systemic treatment did not translate into a significantly lower mastectomy rate (cohort 1 = 20% vs cohort 2 = 16%; p = n.s.). There was no significant difference in breast deformities after breast conserving surgery (p = 0.2). The BCCT.Core demonstrated a 67.1% occurrence of "good" results. Quality of life in patients who underwent breast-conserving surgery measured using the Breast-Q demonstrated similar results in the pre-post-op assessment. CONCLUSIONS: This study hypothesizes that a proper information may impact on patient's decisions and may reduce surgical complexity. This reduction likely has no effects on the main surgical outcomes estimated using standard tools. More investigations should be performed on a larger multi-institutional scale to confirm these conclusions.

Reduction of capsular thickness around silicone breast implants by zafirlukast in rats.

Capsular contracture is a very disappointing complication, with an overall incidence between 0.5 and 30% of breast implant operations and, if severe, requiring a further surgical procedure (capsulotomy or capsulectomy). Many frustrating attempts have been made to prevent the fibrotic reaction, mainly with steroids or antibiotics. More recently leukotriene antagonists clinically used in the asthma and lung diseases have been suggested to be potentially useful in counteracting the inflammatory pathway leading to a dense collagen membrane around the prosthesis and thus preventing contracture of the capsule. In this study we evaluated the effectiveness of zafirlukast with the following protocol. Disks of textured implant material were placed dorsally into each of the subcutaneous tissues of 40 rats that were subdivided in 2 groups: 20 rats treated with zafirlukast and 20 controls. At autopsy 77 days after, each implant with its surrounding collagenic tissue was excised, and the macroscopic measure of the membrane thickness was compared with the pathology reports, to definitely assess the foreign body reaction. The mean total thickness of the capsule around the implants was 161.97 microm in the zafirlukast-treated group compared with 345.98 microm in the control group (p < 0.001). Outstandingly, the collagen fibers and fibroblast layer were reduced in the zafirlukast-treated group compared to the controls. Our study confirms the effectiveness of this compound in preventing fibrosis and putatively also in reducing the extent of collagen reaction when a capsule has been formed.

Experimental methodology for digital breast shape analysis and objective surgical outcome evaluation.

Outcome evaluation in cosmetic and reconstructive surgery of the breast is commonly performed visually or employing bi-dimensional photography. The reconstructive process in the era of anatomical implants requires excellent survey capabilities that mainly rely on surgeon experience. In this paper we present a set of parameters to unambiguously estimate the shape of natural and reconstructed breast. A digital laser scanner was employed on seven female volunteers. A graphic depiction of curvature of the thoracic surface has been the most interesting result. Further work is required to provide clinical and instrumental validation to our technique.