186 results about "Patient survival" patented technology

According to embodiments of the invention, there is provided a method of producing an artificial neural network capable of predicting the survivability of a patient, the method including: storing in an electronic database patient health data, the patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron of the plurality of artificial neurons is adjusted in response to respective first, second and third parameters of different sets of data from the patient health data, such that the artificial neural network is trained to produce a prediction on the survivability of a patient.

A method of producing an artificial neural network capable of predicting the survivability of a patient, including: storing in an electronic database patient health data comprising a plurality of sets of data, each set having at least one of a first parameter relating to heart rate variability data and a second parameter relating to vital sign data, each set further having a third parameter relating to patient survivability; providing a network of nodes interconnected to form an artificial neural network, the nodes comprising a plurality of artificial neurons, each artificial neuron having at least one input with an associated weight; and training the artificial neural network using the patient health data such that the associated weight of the at least one input of each artificial neuron is adjusted in response to respective first, second and third parameters of different sets of data from the patient health data.

The invention provides generally a method of monitoring, diagnosing, prognosing and treating glioma. Specifically, the invention provides for three (3) prognostic subclasses of glioma, which are differentially associated with activation of the akt and notch signaling pathways. Tumor displaying neural or proneural PN lineage markers (including notch pathway elements) show longer median patient survival, while the two remaining tumor markers Prolif and Mes are associated with shortened survival. Tumors classified in this manner may also be treated with the appropriate PN- Prolif- or Mes- therapeutic corresponding to the subclassification in combination with anti-mitotic agents, anti-angiogenic agents, Akt antagonists, and neural differentiation agents. Alternatively, the invention also provides for method of prognosing and diagnosing glioma with a two- gene model based on the expression levels of PTEN and DLL3.

The present invention provides methods and kits a) for predicting colorectal cancer patient survival, as well as the survival of patients harboring other invasive cancers where cellular proliferation and carcinogenesis is linked, in part, to high levels of ODC activity and increased cellular polyamine contents, and b) for selecting the corresponding treatment options for such patients based on the allelic nucleotide sequence or SNP at position +316 of the ODC1 promoter gene as well as cancer treatment methods, in each case, which include the determination of the ODC1 promoter +316 position genotype, as a means to guide treatment selection.

Radiotherapy is one of the most effective treatments for cancer and its success depends critically on accurate targeting and delivery of the correct radiation dose. Accurate dosimetry is therefore essential to maintain and improve patient survival rates. However, size and long wait times currently limit water and graphite based calorimeters to standards laboratories leaving field-based dosimetry to ionization chamber measurements which depend upon a reference field-specified calibration factor. It would therefore be beneficial to provide radiotherapy equipment operators a direct approach of clinical reference dosimetry wherein the dosimeter provides increased independence on dose, dose rate, radiation energy, and energy type, etc. It would be further beneficial for such novel clinical dosimeters to be compact, function as secondary standards used routinely for measurements and allow radiotherapy doses to be measured directly and in an absolute manner. According to embodiments of the invention novel compact graphite probe calorimeters are provided.

The invention pertains to biomarkers for identifying a cancer that is likely or not likely to evade the immune system of a subject, thus, is likely or not likely to show better prognosis (prognostic biomarker) and / or better responses to cancer therapies (predictive biomarker). The invention provides a method of identifying a subject as having a cancer that is likely to evade the immune system of the subject based on one or more of the following biomarkers in the cancer cells of the subject: a) reduced amount of NLRC5 mRNA or protein; b) reduced activity of NLRC5 protein; c) a mutation that reduces the activity of NLRC5 protein; d) increased methylation of nlrc5 or a portion thereof; and e) reduced copy number of nlrc5. These variables are useful to predict both patient survival (prognostic biomarker) and patient responses to immunotherapies (predictive biomarker). Furthermore, this invention provides a method of identifying a subject as having a cancer that is likely to evade the immune system of the subject with greater prediction power by utilizing multiple variables, in addition to above a)-e) variables, including neoantigen load, mutation number, or expression of genes involved in immune responses, including but not limited to CTLA4, PD1, PD-L1 and PD-L2. The invention also pertains to a method of treating a cancer likely to evade the immune system of the subject by administering an immunotherapy and a therapy designed to activate the MHC class I antigen presentation pathway by activating the expression and / or activity of NLRC5 protein.

The invention discloses an application of POU5F1B in diagnosis, treatment, prognosis and relapse prediction of tumor. In the invention, it is found that the copy number and the expression level of the gene POU5F1B in various tumors are closely related to transfer, relapse, patient prognosis and dryness of the tumor cells. A research result proves that by means of high expression of the POU5F1B, formation of TIC is promoted and further the in-vivo tumorigenic capability of esophagus cancer cells is enhanced, thereby reducing the survival rate, and oppositely, by means of inhibition of the expression of the POU5F1B, the formation of the TIC is promoted and further the in-vivo tumorigenic capability of the esophagus cancer cells is reduced, thereby increasing the survival rate, so that it is obviously that by means of inhibition of the endogenous POU5F1B, the in-vivo tumorigenic capability of the esophagus cancer cells can be significantly reduced, thereby increasing the survival rate of patients, which proves that the POU5F1B can be used as a marker for diagnosis, treatment, prognosis and relapse prediction. An inhibitor of the POU5F1B has a great clinical application value in preparation of a drug composition for tumor, so that the invention provides a new drug and a new method for effective treatment of tumor.

The invention provides an esophageal squamous carcinoma patient survival risk prediction method based on a convolutional neural network. The method comprises the steps of: collecting M clinical phenotype indexes and survival information of esophageal squamous carcinoma patients as original data; performing research by using a Kaplan-Meier method and a log-rank method to obtain a relationship between clinical phenotype indexes and lifetime information of the esophageal cancer patients; analyzing clinical phenotype indexes influencing survival prognosis of the patients by using Univariate Cox hazard analysis; extracting clinical phenotype indexes with higher correlation with the survival risk of the patients through a Relief feature selection algorithm and Pearson correlation analysis; and finally, constructing a survival risk prediction model of the esophageal squamous carcinoma patients by using a convolutional neural network and using clinical phenotype indexes with higher correlation, and further judging the prognosis survival risk of the patients. According to the method, the postoperative survival condition of the esophageal squamous carcinoma patients is accurately predicted, the prognosis risk prediction capability is improved, and the prognosis risk prediction cost is reduced.

The present invention discloses and claims compositions, methods of treatment, and kits which cause an increase in the time of survival in cancer patients, wherein the cancer: (i) overexpresses thioredoxin or glutaredoxin and / or (ii) exhibits evidence of thioredoxin- or glutaredoxin-mediated resistance to one or more chemotherapeutic interventions. The present invention also discloses and claims methods and kits for the administration of said compositions to properly treat cancer patients. Additionally, the present invention discloses and claims methods and kits for quantitatively determining the level of expression of thioredoxin or glutaredoxin in the cancer cells of a cancer patient, methods of using those determined levels in the initial diagnosis and / or planning of subsequent treatment methodologies for said cancer patient, as well as ascertaining the potential growth “aggressiveness” of the particular cancer and treatment responsiveness of the particular type of cancer. Further, the present invention discloses and claims novel pharmaceutical compositions, methods, and kits used for the treatment of patients with medical conditions and disease where there is the overexpression of thioredoxin and / or glutaredoxin, and wherein this overexpression is associated with deleterious physiological effects in the patients.