Using machine learning algorithm to analyse the hypothyroidism complications caused by radiotherapy in patients with head and neck cancer.

Machine learning algorithms were used to analyze the odds and predictors of complications of thyroid damage after radiation therapy in patients with head and neck cancer. This study used decision tree (DT), random forest (RF), and support vector machine (SVM) algorithms to evaluate predictors for the data of 137 head and neck cancer patients. Candidate factors included gender, age, thyroid volume, minimum dose, average dose, maximum dose, number of treatments, and relative volume of the organ receiving X dose (X: 10, 20, 30, 40, 50, 60 Gy). The algorithm was optimized according to these factors and tenfold cross-validation to analyze the state of thyroid damage and select the predictors of thyroid dysfunction. The importance of the predictors identified by the three machine learning algorithms was ranked: the top five predictors were age, thyroid volume, average dose, V50 and V60. Of these, age and volume were negatively correlated with thyroid damage, indicating that the greater the age and thyroid volume, the lower the risk of thyroid damage; the average dose, V50 and V60 were positively correlated with thyroid damage, indicating that the larger the average dose, V50 and V60, the higher the risk of thyroid damage. The RF algorithm was most accurate in predicting the probability of thyroid damage among the three algorithms optimized using the above factors. The Area under the receiver operating characteristic curve (AUC) was 0.827 and the accuracy (ACC) was 0.824. This study found that five predictors (age, thyroid volume, mean dose, V50 and V60) are important factors affecting the chance that patients with head and neck cancer who received radiation therapy will develop hypothyroidism. Using these factors as the prediction basis of the algorithm and using RF to predict the occurrence of hypothyroidism had the highest ACC, which was 82.4%. This algorithm is quite helpful in predicting the probability of radiotherapy complications. It also provides references for assisting medical decision-making in the future.

Technical Note: Radiotherapy dose characterization of gel dosimetry using shear wave elasticity imaging.

PURPOSE: Radiotherapy is an effective treatment for many types of cancer in clinical settings. Gel dosimetry has the potential to record three-dimensional (3D) dose distribution compared to a conventional ion chamber. As the elasticity of the gel is altered after irradiation due to gel polymerization, we aim to measure the dose recorded in gel dosimetry with ultrasonic shear wave elasticity imaging (SWEI), a nondestructive and quantitative elasticity imaging tool. METHODS: In this study, a cylindrical N-isopropylacrylamide (NIPAM) polymer gel with a diameter of 10 cm and a height of 10 cm and with cellulose as an ultrasonic scatterer was irradiated by a linear accelerator with the irradiation parameters of 6 MV x-ray, dose rate of 100 cGy/min and field size of 10  ×  20 mm2 . The six gel phantoms were irradiated with the dose of 0, 1, 3, 5, 8, or 10 Gy. The gel phantoms were measured with SWEI at 24, 36, and 48 h after x-ray irradiation. The two-dimensional (2D) shear wave velocity and Young's modulus maps corresponding to x-ray dose distribution were reconstructed following a time-of-flight reconstruction from a set of time-series displacement maps. The spatial resolution of the reconstructed SWEI image is ~1 mm. RESULTS: Our results show that the elastic modulus increases linearly as irradiation dose increases (R2  = 0.94 at 24 h, R2  = 0.98 at 36 h, R2  = 0.98 at 48 h), suggesting that the gel elasticity is highly associated with x-ray irradiation dose at 36 h post irradiation, and the dose resolution was 0.66 kPa/Gy. From the 3D elastic modulus maps, the dose distribution along the depth and lateral direction can be reflected in the NIPAM gel dosimetry using SWEI as well. CONCLUSIONS: In this study, the irradiated NIPAM gel phantom was quantitatively measured with SWEI for the first time to read the dose distribution recorded in the gel dosimetry. The results suggest that the gel elasticity is highly associated with x-ray irradiation dose. In the future, 2D/or 3D dose distribution from intensity modulated radiotherapy (IMRT) or other potential particle radiotherapy will be measured and reconstructed with SWEI and compared with the dose map from a treatment planning system (TPS) in the clinic.

Comparison of serologic responses to vaccination with one dose or two doses of 7-valent pneumococcal conjugate vaccine in HIV-infected adult patients.

BACKGROUND: Vaccination with 7-valent pneumococcal conjugate vaccine (PCV) has been shown to decrease the incidence of recurrent invasive pneumococcal disease among HIV-infected adults in Africa. Longitudinal follow-up studies of serologic responses to different doses of 7-valent PCV are rarely performed in HIV-infected adult patients receiving combination antiretroviral therapy (cART). METHODS: From October 2008 to June 2010, 115 CD4-matched pairs of HIV-infected patients aged ≥ 20 years who had no prior pneumococcal vaccination received one or two doses of 7-valent PCV. Anticapsular antibodies against 4 serotypes (6B, 14, 19F, and 23F) were examined at the 12th, 24th, 36th, and 48th week following vaccination. Significant antibody responses were defined as ≥ 2-fold increase in the IgG level plus a post-vaccination antibody level ≥ 1000 ng/ml. RESULTS: The most common reported adverse effects were injection site soreness (19.3%) and pain (4.8%). Significant antibody response rate was highest for serotype 14, followed by 23F, 19F, and 6B in all of the four time points examined. At week 48, patients who received two doses of 7-valent PCV had a significantly higher response rate to serotype 6B (P=0.03) and 23F (P=0.01) than those who received one dose; moreover, the former group also had a higher response rate to at least one (P=0.03) and two serotypes (P=0.02) in intention-to-treat analysis than the latter group. CONCLUSIONS: HIV-infected adult patients on cART who received two doses of 7-valent PCV achieved better serological responses to at least one serotype than those who received one dose during the 48 weeks of follow-up.

Inhibition of HIV-1 Tat-mediated transcription by a coumarin derivative, BPRHIV001, through the Akt pathway.

The human immunodeficiency virus type 1 (HIV-1)-encoded RNA-binding protein Tat is known to play an essential role in viral gene expression. In the search for novel compounds to inhibit Tat transactivity, one coumarin derivative, BPRHIV001, was identified, with a 50% effective concentration (EC(50)) against HIV-1 at 1.3 nM. BPRHIV001 is likely to exert its effects at the stage after initiation of RNAPII elongation since Tat protein expression and the assembly of the Tat/P-TEFb complex remained unchanged. Next, a reduction of the p300 protein level, known to modulate Tat function through acetylation, was observed upon BPRHIV001 treatment, while the p300 mRNA level was unaffected. A concordant reduction of phosphorylated Akt, which was shown to be closely related to p300 stability, was observed in the presence of BPRHIV001 and was accompanied by a decrease of phosphorylated PDPK1, a well-known Akt activator. Furthermore, the docking analysis revealed that the reduced PDPK1 phosphorylation likely resulted from the allosteric effect of interaction between BPRHIV001 and PDPK1. With strong synergistic effects with current reverse transcriptase inhibitors, BPRHIV001 has the potential to become a promising lead compound for the development of a novel therapeutic agent against HIV-1 infection.

Anti-HSV activity of digitoxin and its possible mechanisms.

Herpes simplex virus type 1 (HSV-1) can establish latent infection in the nervous system and usually leads to life-threatening diseases in immunocompromised individuals upon reactivation. Treatment with conventional nucleoside analogue such as acyclovir is effective in most cases, but drug-resistance may arise due to prolonged treatment in immunocompromised individuals. In this study, we identified an in-use medication, digitoxin, which actively inhibited HSV-1 replication with a 50% effective concentration (EC(50)) of 0.05 microM. The 50% cytotoxicity concentration (CC(50)) of digitoxin is 10.66 microM and the derived selective index is 213. Several structural analogues of digitoxin such as digoxin, ouabain octahydrate and G-strophanthin also showed anti-HSV activity. The inhibitory effects of digitoxin are likely to be introduced at the early stage of HSV-1 replication and the virus release stage. The observation that digitoxin can inhibit acyclovir-resistant viruses further implicates that digitoxin represents a novel drug class with distinct antiviral mechanisms from traditional drugs.