Machine learning for classification of postoperative patient status using standardized medical data.

BACKGROUND AND OBJECTIVE: Real-world evidence is defined as clinical evidence regarding the use and potential benefits or risks of a medical product derived from real-world data analyses. Standardization and structuring of data are necessary to analyze medical real-world data collected from different medical institutions. An electronic message and repository have been developed to link electronic medical records in this research project, which has simplified the data integration. Therefore, this paper proposes an analysis method and learning health systems to determine the priority of clinical intervention by clustering and visualizing time-series and prioritizing patient outcomes and status during hospitalization. METHODS: Common data items for reimbursement (Diagnosis Procedure Combination [DPC]) and clinical pathway data were examined in this project at each participating institution that runs the verification test. Long-term hospitalization data were analyzed using the data stored in the cloud platform of the institutions' repositories using multiple machine learning methods for classification, visualization, and interpretation. RESULTS: The ePath platform contributed to integrate the standardized data from multiple institutions. The distribution of DPC items or variances could be confirmed by clustering, temporal tendency through the directed graph, and extracting variables that contributed to the prediction and evaluation of SHapley Additive Explanation effects. Constipation was determined to be the risk factor most strongly related to long-term hospitalization. Drainage management was identified as a factor that can improve long-term hospitalization. These analyses effectively extracted patient status to provide feedback to the learning health system. CONCLUSIONS: We successfully generated evidence of medical processes by gathering patient status, medical purposes, and patient outcomes with high data quality from multiple institutions, which were difficult with conventional electronic medical records. Regarding the significant analysis results, the learning health system will be used on this project to provide feedback to each institution, operate it for a certain period, and analyze and re-evaluate it.

Factors Preventing Prolonged Closed-Suction Drain Placement after Immediate Breast Reconstruction with Tissue Expanders.

BACKGROUND: Prolonged drain placement occasionally causes complications such as infection in patients who have undergone implant-based breast reconstruction; therefore, the drainage period must be shortened to avoid complications. PURPOSE: To identify the factors that prevent prolonged drain placement in patients who have undergone immediate breast reconstruction with tissue expanders. METHODS: This was a retrospective medical chart review of all patients who underwent immediate breast reconstruction with tissue expanders at a single center from April 2013 to March 2016. Closed-suction drains were placed in and on the implant pocket. An extra drain was positioned in the axilla in patients undergoing axillary lymph node dissection. The drains were removed at a drainage volume of ≤50 ml per 24 hours. Prolonged drain placement was defined as a period greater than the 75th percentile among all patients. Nine potential risk factors associated with prolonged drain placement were analyzed with multivariate logistic regression analysis. RESULTS: In total, 89 tissue expanders in 89 patients were placed in this study. Prolonged drain placement, determined as ≥9 days (range, 5-14 days), was significantly associated with body mass index ≥25 kg/m2, tissue expander size ≥500 ml, and intraoperative bleeding ≥100 ml, in the multivariate analysis. Axillary lymph node dissection with extra-axillary drainage did not prolong the drainage period. CONCLUSIONS: Our findings suggested that placing an extra-axillary closed-suction drain following axillary dissection, and reducing intraoperative bleeding and surgical trauma, could prevent prolonged drain placement in immediate breast reconstruction with tissue expanders.

Risk Factors for Lymphedema in Breast Cancer Survivors Following Axillary Lymph Node Dissection.

OBJECTIVE: The aim of the current study was to assess the risk factors for developing lymphedema following breast cancer treatment. METHODS: The subjects of this study were 238 consecutive patients who underwent axillary lymph node dissection for breast cancer at Shikoku Cancer Center. The study variables were the occurrence of lymphedema, the body mass index, the follow-up period, the drain removal time, the level of lymph node dissection, the presence or absence of co-resident household members, radiation therapy, neoadjuvant chemotherapy, and adjuvant chemotherapy. RESULTS: We observed lymphedema in 23.9% of patients after axillary lymph node dissection for breast cancer. Neoadjuvant chemotherapy and adjuvant chemotherapy using docetaxel and cyclophosphamide increased the risk of developing lymphedema (P <0.05). CONCLUSIONS: Those patients treated with neoadjuvant chemotherapy and adjuvant chemotherapy using docetaxel and cyclophosphamide should be observed closely after axillary lymph node dissection, and appropriate intervention should be considered from an early stage.

Efficacy and safety of omeprazole in Japanese patients with nonerosive reflux disease.

BACKGROUND: There is increasing awareness of nonerosive reflux disease (NERD) as a disease requiring treatment in Japan. This randomized, double-blind, placebo-controlled, parallel-group study was conducted to investigate the efficacy and safety of omeprazole 10 mg and 20 mg once daily in Japanese patients with NERD. METHODS: Patients with heartburn for at least 2 days a week during the month before entry into the study and no endoscopic signs of a mucosal break (grade M or N according to Hoshihara's modification of the Los Angeles classification) were randomly assigned to one of three groups (omeprazole 10 mg or 20 mg, or placebo) once daily for 4 weeks. RESULTS: Overall, 355 patients were enrolled, of whom 284 were randomly assigned to one of the three groups (omeprazole 10 mg, n = 96; omeprazole 20 mg, n = 93; placebo, n = 95). The rate of complete resolution of heartburn in week 4 was significantly higher in patients treated with omeprazole 10 mg [32.3%, 95% confidence interval (CI), 22.9%-41.6%] or 20 mg (25.8%, 95% CI, 16.9%-34.7%) than in the placebo group (12.0%, 95% CI, 5.3%-18.6%). No significant difference between the two omeprazole groups was observed. The rate of complete resolution of heartburn by omeprazole was similar between patients with grade M and those with grade N esophagus. Omeprazole also increased the rate of sufficient relief from heartburn. Omeprazole was well tolerated. CONCLUSIONS: Omeprazole 10 mg or 20 mg once daily is effective and well tolerated in patients with NERD regardless of their endoscopic classification.

Epidermal inclusion cyst of the breast.

Epidermal inclusion cysts are uncommon in the breast, but the consequences can be severe when these cysts occur in the breast parenchyma. Here, we report two such cases. The patient in case 1 was an 85-year-old woman with a 3-cm palpable mass in the right breast. Mammography revealed a round and smoothly outlined mass, which indicated a benign tumor, and sonography showed an irregularly shaped and heterogeneous hypoechoic mass. Breast cancer was suspected on the basis of the sonographic findings and the age of the patient, but excisional biopsy revealed an epidermal inclusion cyst. The patient in case 2 was a 45-year-old woman with a 9-cm lesion in the left breast. Mammography revealed a round, dense, smoothly outlined mass, and sonography showed a well-defined, central hyperechoic mass. A phyllodes tumor or a giant fibroadenoma was suspected on the basis of clinical and imaging findings, but the resected specimen revealed an epidermal inclusion cyst.

[Local communication system between hospitals, clinics and nursing homes and their team approaches are essential in a consistent medical care for cancer patients].

Designated cancer care hospitals are responsible for constructing a local communication system between hospitals, clinics and nursing homes. Their team approaches are essential in a consistent medical care for cancer patients. Clinical pathway sheets shared by them will promote their collaboration and keep the consistency of medical care. Counseling and supporting section, palliative care unit and palliative care team in the designated cancer care hospital play an important role improving the quality of medical care for cancer patients.

Nodular pseudoangiomatous stromal hyperplasia of mammary stroma in a case showing rapid tumor growth.

Pseudoangiomatous stromal hyperplasia (PASH) is an uncommon benign breast disease that presents as a localized breast mass. Breast tissue affected by PASH is characterized by a dense, collagenous proliferation of mammary stroma, forming interanastomosing capillary-like spaces. The importance of this benign lesion lies in distinguishing it from low grade angiosarcoma. We report a case of a 38-year-old woman who presented with a rapidly growing breast tumor. She visited our hospital with a complaint of a painless right breast mass. Physical examination revealed a 3.6 x 2.2 cm, oval, elastic-firm, well-defined and easily movable mass. Mammograms revealed no discrete mass or calcifications. Sonographic examination revealed a 3.5 x 2.5 x 2.2 cm, oval, well-defined and homogenous hypoechoic mass without a cyst. A fine-needle aspiration sample of the breast mass showed some clusters of epithelial cells with small papillary structures and many scattered stromal cells with naked nuclei. Based on these findings, a provisional diagnosis of fibroadenoma was made and the patient was followed up. One year after the first visit, the mass enlarged rapidly and a follow-up mammogram revealed an 8.2 x 5.5 cm circumscribed mass without calcifications. Given the history of rapid growth of the mass, tumor excision was performed. The excised tumor was well demarcated and had a smooth external surface. Histologic examination revealed normal breast ducts and lobules, and specific proliferative epithelial changes were not seen. The lobular and duct structure of the breast parenchyma were separated by an increased amount of stroma. The fibrous stroma contained numerous anastomosing slit-like spaces. Isolated spindle cells appeared intermittently at the margins of the spaces resembled endothelial cells. Immunohistochemical staining showed that endothelial cells lining true blood vessels were positive for Factor VIII-related antigen, but the spindle cells were negative for Factor VIII. Pseudoangiomatous stromal hyperplasia was diagnosed.