Potential Prognostic Value of Preoperative Leukocyte Count, Lactate Dehydrogenase and C-Reactive Protein in Thymic Epithelial Tumors.

Thymic epithelial tumors are the most common mediastinal tumors. Surgery is the mainstay of treatment and complete resection provides the best survival rate. However, advanced tumors often require multimodality treatment and thus we analyzed the prognostic potential of routine circulating biomarkers that might help to risk-stratify patients beyond tumor stage and histology. Preoperative values for white blood cell count (WBC), C-reactive protein (CRP) and lactate dehydrogenase (LDH) were analyzed in 220 thymic epithelial tumor patients operated between 1999 and 2018. Increased CRP levels (>1 mg/dl) were significantly more often measured in thymic carcinoma and neuroendocrine tumors when compared to thymoma. LDH serum activity was higher in thymic neuroendocrine tumors when compared to thymoma or thymic carcinoma. The median disease specific survival was significantly longer in thymoma cases than in thymic carcinoma and neuroendocrine tumors. Increased preoperative LDH level (>240 U/L) associated with shorter survival in thymus carcinoma (HR 4.76, p = 0.0299). In summary, higher CRP associated with carcinoma and neuroendocrine tumors, while LDH increased primarily in neuroendocrine tumors suggesting that biomarker analysis should be performed in a histology specific manner. Importantly, preoperative serum LDH might be a prognosticator in thymic carcinoma and may help to risk stratify surgically treated patients in multimodal treatment regimens.

An Interpretable Predictive Model of Vaccine Utilization for Tanzania.

Providing accurate utilization forecasts is key to maintaining optimal vaccine stocks in any health facility. Current approaches to vaccine utilization forecasting are based on often outdated population census data, and rely on weak, low-dimensional demand forecasting models. Further, these models provide very little insights into factors that influence vaccine utilization. Here, we built a state-of-the-art, machine learning model using novel, temporally and regionally relevant vaccine utilization data. This highly multidimensional machine learning approach accurately predicted bi-weekly vaccine utilization at the individual health facility level. Specifically, we achieved a forecasting fraction error of less than two for about 45% of regional health facilities in both the Tanzania regions analyzed. Our "random forest regressor" had an average forecasting fraction error that was almost 18 times less compared to the existing system. Importantly, using our model, we gleaned several key insights into factors underlying utilization forecasts. This work serves as an important starting point to reimagining predictive health systems in the developing world by leveraging the power of Artificial Intelligence and big data.

Lymph Node Involvement and the Surgical Treatment of Thymic Epithelial and Neuroendocrine Carcinoma.

BACKGROUND: Thymic epithelial and neuroendocrine carcinomas are rare malignancies, and only a few prognosticators are defined. Surgery is the mainstay of treatment, and complete resection contributes to superior outcome. Systematic lymph node dissection is not routinely performed in thymic malignancies. The aim of this study was to assess the impact of histologically confirmed lymph node metastases on the outcome after thymectomy. METHODS: We identified 53 patients with thymic epithelial or neuroendocrine carcinomas who underwent surgical resection at our center between 1999 and 2016. The clinical follow-up was retrospectively collected, and the impact of clinicopathologic factors on overall survival was analyzed. RESULTS: Ninety-one percent of the patients were treated taking a multimodal approach. Median overall survival was 11.3 years. Lymph node metastases were identified in 16 patients (30.2%; 11 pN1 and 5 pN2). Lymph node metastasis was associated with inferior overall survival (hazard ratio [HR] 3.03, 95% confidence interval [CI]: 1.03 to 8.87, p = 0.044). Masaoka-Koga stage (4 versus 1 to 3) was another significant prognosticator (HR 7.01, 95% CI: 2.52 to 19.50, p = 0.0002). Organ metastases were present in 18 patients at the time of thymectomy and were associated with inferior outcome (HR 5.8, 95% CI: 2.04 to 16.79, p = 0.001). CONCLUSIONS: This retrospective, single-center analysis demonstrates a high rate of lymph node metastasis in resectable thymic neuroendocrine tumors or carcinomas. Positive lymph nodes are associated with an inferior outcome. Prospective studies are warranted to explore whether this outcome can be improved by systematic lymphadenectomy and adjuvant therapies. Nevertheless, lymphadenectomy provides optimal staging and should be a routine part of surgery for patients with thymic malignancies.