Abstract: A computer-implemented method for privacy-preserving data mining to determine cancer survival rates includes providing a random matrix B agreed to by a plurality of entities, wherein each entity i possesses a data matrix Ai of cancer survival data that is not publicly available, providing a class matrix Di for each of the data matrices Ai, providing a kernel K(Ai, B) by each of said plurality of entities to allow public computation of a full kernel, and computing a binary classifier that incorporates said public full kernel, wherein said classifier is adapted to classify a new data vector according to a sign of said classifier.

Abstract: Knowledge-based interpretable predictive modeling is provided. Expert knowledge is used to seed training of a model by a machine. The expert knowledge may be incorporated as diagram information, which relates known causal relationships between predictive variables. A predictive model is trained. In one embodiment, the model operates even with a missing value for one or more variables by using the relationship between variables. For application, the model outputs a prediction, such as the likelihood of survival for two years of a lung cancer patient. A graphical representation of the model is also output. The graphical representation shows the variables and relationships between variables used to determine the prediction. The graphical representation is interpretable by a physician or other to assist in understanding.

Abstract: Modeling of prognosis of survivability, side-effect, or both is provided. For example, RILI is predicted using bullae information. The amount, volume or ratio of Bullae, even alone, may indicate the likelihood of complication, such as the likelihood of significant (e.g., stage 3) pneumonitis. As another example, RILI is predicted using uptake values of an imaging agent. Standardized uptake from a functional image (e.g., FDG uptake from a positron emission image), alone or in combination with other features, may indicate the likelihood of side-effect. In another example, survivability, such as two-year survivability, is predicted using blood biomarkers. The characteristics of a patient's blood may be measured and, alone or in combination with other features, may indicate the likelihood of survival. The modeling may be for survivability, side-effect, or both and may use one or more of the blood biomarker, uptake value, and bullae features.

Abstract: A predictor of medical treatment outcome is developed and applied. A prognosis model is developed from literature. The model is determined by reverse engineering the literature reported quantities. A relationship of a given variable to a treatment outcome is derived from the literature. A processor may then use individual patient values for one or more variables to predict outcome. The accuracy may be increased by including a data driven model in combination with the literature driven model.

Abstract: Knowledge-based interpretable predictive modeling is provided. Expert knowledge is used to seed training of a model by a machine. The expert knowledge may be incorporated as diagram information, which relates known causal relationships between predictive variables. A predictive model is trained. In one embodiment, the model operates even with a missing value for one or more variables by using the relationship between variables. For application, the model outputs a prediction, such as the likelihood of survival for two years of a lung cancer patient. A graphical representation of the model is also output. The graphical representation shows the variables and relationships between variables used to determine the prediction. The graphical representation is interpretable by a physician or other to assist in understanding.

Abstract: Modeling of prognosis of survivability, side-effect, or both is provided. For example, RILI is predicted using bullae information. The amount, volume or ratio of Bullae, even alone, may indicate the likelihood of complication, such as the likelihood of significant (e.g., stage 3) pneumonitis. As another example, RILI is predicted using uptake values of an imaging agent. Standardized uptake from a functional image (e.g., FDG uptake from a positron emission image), alone or in combination with other features, may indicate the likelihood of side-effect. In another example, survivability, such as two-year survivability, is predicted using blood biomarkers. The characteristics of a patient's blood may be measured and, alone or in combination with other features, may indicate the likelihood of survival. The modeling may be for survivability, side-effect, or both and may use one or more of the blood biomarker, uptake value, and bullae features.

Abstract: A system for modeling complete response prediction is provided. The system includes an input that is operable to receive treatment information representing treatment data that may be used to predict a complete response of a tumor. The complete response may include a disappearance of all or substantially all of a disease. A processor may be operable to use a model to predict complete response of the tumor as a function of the treatment data. The model represents a probability of complete response to treatment given the treatment data. A display is operable to output an image as a function of the complete response prediction.

Abstract: A computer-implemented method for privacy-preserving data mining to determine cancer survival rates includes providing a random matrix B agreed to by a plurality of entities, wherein each entity i possesses a data matrix Ai of cancer survival data that is not publicly available, providing a class matrix Di for each of the data matrices Ai, providing a kernel K(Ai, B) by each of said plurality of entities to allow public computation of a full kernel, and computing a binary classifier that incorporates said public full kernel, wherein said classifier is adapted to classify a new data vector according to a sign of said classifier.

Abstract: A predictor of medical treatment outcome is developed and applied. A prognosis model is developed from literature. The model is determined by reverse engineering the literature reported quantities. A relationship of a given variable to a treatment outcome is derived from the literature. A processor may then use individual patient values for one or more variables to predict outcome. The accuracy may be increased by including a data driven model in combination with the literature driven model.