This study analyzed the prognostic significance of clinico-pathologic factors, including the number of metastatic lymph nodes (LNs) and lymph node ratio (LNR), in patients with papillary thyroid carcinoma (PTC), and attempted to construct a disease recurrence prediction model using machine learning techniques. We retrospectively analyzed clinico-pathologic data from 1040 patients diagnosed with PTC between 2003 and 2009. We analyzed clinico-pathologic factors related to recurrence through logistic regression analysis. Among the factors that we included, only sex and tumor size were significantly correlated with disease recurrence. Parameters such as age, sex, tumor size, tumor multiplicity, ETE, ENE, pT, pN, ipsilateral central LN metastasis, contralateral central LNs metastasis, number of metastatic LNs, and LNR were input for construction of a machine learning prediction model. The performance of five machine learning models related to recurrence prediction was compared based on accuracy. The Decision Tree model showed the best accuracy at 95%, and the lightGBM and stacking model together showed 93% accuracy. Among those factors mentioned above, LNR and contralateral LN metastasis were used as important features in all machine learning prediction models. We confirmed that all machine learning prediction models showed an accuracy of 90% or more for predicting disease recurrence in PTC. LNR and contralateral LN metastasis were used as important features for constructing a robust machine learning prediction model. In the future, we have a plan to perform large-scale multicenter clinical studies to improve the performance of our prediction models and verify their clinical effectiveness.

It has been suggested that Porphyromonas gingivalis (P. gingivalis), a keystone pathogen in chronic periodontitis, is associated with a variety of cancers, including oral cancer. Recently, studies have shown the effects of persistent exposure to P. gingivalis on the promotion of tumorigenic properties of oral epithelial cells, suggesting that chronic P. gingivalis infection is a potential risk factor for oral cancer. On the other hand, Fusobacterium nucleatum (F. nucleatum), one of the major periodontal pathogens, has emerged as an important factor in the colon cancer progression. Here, we investigated the diagnostic potential of serum immunoglobulin G antibody against periodontal pathogens, P. gingivalis and F. nucleatum, and serum IL-6 for oral squamous cell carcinoma (OSCC). An enzyme-linked immunosorbent assay (ELISA) was used to determine and compare the serum levels of interleukin 6 (IL-6), F. nucleatum IgG, and P. gingivalis IgG in 62 OSCC patients with 46 healthy controls. The serum levels of P. gingivalis IgG and IL-6 were higher in OSCC patients than in non-OSCC controls, and the difference was statistically significant. In addition, a high serum level of IL-6 was associated with a worse prognosis in OSCC patients. Thus, P. gingivalis IgG and IL-6 could be utilized as potential serum biomarkers for the diagnosis of OSCC, and the serum level of IL-6 contributes to improved prognostic performance.

Voice change is a common complaint after thyroid surgery and has a significant impact on quality of life. The Korean Society of Laryngology, Phoniatrics and Logopedics assembled a task force to establish guideline recommendations on education, care, and management related to thyroid surgery. The guideline recommendations encompass preoperative voice education, management of anticipated voice change during surgery, and comprehensive voice care after thyroid surgery, and include in-depth information and up-to-date knowledge based on validated literature. The committee constructed 14 key questions (KQs) in three categories—preoperative (KQ 1–2), intraoperative (KQ 3–8), and postoperative (KQ 9–14) management—and developed 18 evidence-based recommendations. The Delphi survey reached an agreement on each recommendation. A detailed evidence profile is presented for each recommendation. The level of evidence for each recommendation was classified as high-quality, moderate-quality, or low-quality. The strength of each recommendation was designated as strong or weak considering the level of evidence supporting the recommendation. The guidelines are primarily targeted toward physicians who treat thyroid surgery patients and speech-language pathologists participating in patient care. These guidelines will also help primary care physicians, nurses, healthcare policymakers, and patients improve their understanding of voice changes and voice care after thyroid surgery.

Conclusion Loco-regional recurrence-free survival was significantly decreased in the papillary thyroid cancer patients with > 6 metastatic lymph nodes and a lymph node ratio > 0.22. Also, the risk of lung metastasis was significantly increased in cases with bilateral neck node metastases. Objective This study focused on the metastatic lymph node status of the lateral neck compartment to understand its prognostic significance for loco-regional recurrence and distant metastasis. Methods Between January 2004 and December 2009, 1040 patients were diagnosed with papillary thyroid cancer and underwent treatment. Results In a multivariate analysis, sex, the number of metastatic lymph nodes, and the lymph node ratio was significantly associated with loco-regional recurrence. The sensitivity/specificity of > 6 metastatic lymph nodes for predicting recurrence was 64.0%/69.7%. The 5-year loco-regional recurrence-free survival of patients with 0–6 metastatic lymph nodes and > 6 metastatic lymph nodes were 93.4% and 79.2%, respectively. The 5-year loco-regional recurrence-free survival of patients with a lymph node ratio ≤ 0.22 and a lymph node ratio > 0.22 were 97.1% and 78.8%, respectively. In the multivariate analysis, only bilateral neck node metastases were significantly associated with lung metastasis.