Biomedical subjects

Sudeshna Adak

Publications and source records attributed to Sudeshna Adak.

6 recordsLinked to original sources

PubMed2006

Neural networks for longitudinal studies in Alzheimer's disease.

OBJECTIVE: Alzheimer's disease affects a growing population of elderly people today. The predictions about the course of the disease is a key component of health care decision making for patients with Alzheimer's. The physician's prognosis and predicted trajectory of cognitive decline often form the basis of treatment and health care decisions taken by patients and their families. These predictions are difficult to make because of the high variability and non-linearity exhibited by individual patterns of cognitive decline. This paper presents a new method of predicting the course of a disease using longitudinal data collected through multiple clinic visits. Longitudinal databases are similar to temporal databases, with some important differences--data is collected at irregular time intervals that are patient specific and also a varying number of observations are made for each patient, depending upon the number of times the patient visited the clinic. We propose a new type of neural network called the mixed effects neural network (MENN) model that can incorporate this type of longitudinal information. MATERIAL AND METHODS: We have used longitudinal data on 704 subjects enrolled at the Layton aging and research center (LAARC) at Oregon Health and Science University. A back-propagation algorithm, modified for longitudinal data is used to obtain the weight parameters of the MENN. The modified back-propagation algorithm is further embedded in an iterative procedure that estimates the noise variance and the parameters that capture the longitudinal (temporal) correlation structure. RESULTS: We have compared the performance of the MENN with linear mixed effects models and standard neural networks (NN). MENN show better performance (misclassification rate = 0.13 and relative MSE = 0.35) as compared to standard NN (misclassification rate = 0.34 and relative MSE = 2.74) and linear mixed effects models (misclassification rate = 0.14 and relative MSE = 0.4). CONCLUSION: The results show that this method can be a useful tool for predicting non-linear disease trajectories and uncovering significant prognostic factors in longitudinal databases.

Aged↗

PubMed2006

High-field magnetic resonance imaging of brain iron in Alzheimer disease.

OBJECTIVES: Increased iron deposition in the brain may occur in several neurodegenerative diseases, including Alzheimer disease (AD). Iron deposits shorten T2 relaxation times on T2-weighted magnetic resonance (MR) images. Iron-dependent contrast increases with magnetic field strength. We hypothesized that T2 mapping using 3 T MR imaging (MRI) can disclose differences between normal controls and AD subjects. METHODS: High-resolution brain imaging protocols were developed and applied to 24 AD patients and 20 age-matched controls using 3 T MRI. Eight anatomical regions of interest were manually segmented, and T2 histograms were computed. A visual analysis technique, the heat map, was modified and applied to the large image data sets generated by these protocols. RESULTS: A large number (163) of features from these histograms were examined, and 38 of these were significantly different (P < 0.05) between the groups. In the hippocampus, evidence was found for AD-related increases in iron deposition (shortened T2) and in the concentration of free tissue water (lengthened T2). Imaging of a section of postmortem brain before and after chemically extracting the iron established the presence of MRI-detectable iron in the hippocampus, cortex, and white matter in addition to brain regions traditionally viewed as containing high iron concentrations.

Aged↗

PubMed2004

Prospective phase II trial of PFL-induction chemotherapy followed by definitive local treatment for advanced squamous cell carcinoma of the head and neck: 10-year follow-up.

Reported is an analysis of overall survival at 10 years of 102 patients with advanced squamous cell carcinoma of the head and neck (SCCHN) who were enrolled in a prospective phase II trial of high-dose cisplatin, 5-fluorouracil (5-FU), and high-dose leucovorin (PFL) induction chemotherapy followed by surgery and/or definitive radiation therapy (RT) between 1987 and 1991. Initially, 14 patients underwent primary site (PS) and neck surgery irrespective of the clinical response to PFL. The high rate of clinical and pathologic complete response (CR) to PFL prompted a switch from PS surgery to definitive RT. Of 102 patients, 18 (17.6%) who completed PFL and local-regional treatment for SCCHN between 1988 to 1991 were alive in December 2000. Among these, 1 of 14 patients (7%) who had undergone PS resection and 17 of 85 (20%) who were treated after PFL with definitive RT but without PS surgery were alive at 10 years. Median survival time was higher in the nonsurgical group (98.9 vs. 51.9 months). Subset analysis suggested that patients with oropharyngeal PS had the longest median survival (108.6 months). The oropharyngeal patients represented the 61% (11/18) of the long-term survivors with organ preservation. An organ preservation approach for patients with advanced SCCHN who demonstrated PS CR to chemotherapy demonstrated a trend to improved overall survival.

Adolescent↗

PubMed2004

Docetaxel for malignant mesothelioma: phase II study of the Eastern Cooperative Oncology Group.

This Eastern Cooperative Oncology Group phase II trial was conducted to study the effectiveness of docetaxel in patients with malignant mesothelioma. Patients were treated with docetaxel 100 mg/m2 intravenously administered as a 1-hour infusion repeated every 3 weeks. The study accrued a total of 20 patients, 1 of whom was considered ineligible. Of the 19 eligible patients, 1 patient (5%) achieved a partial response, 3 patients (16%) had stable disease, 11 patients (58%) had progressive disease, and 4 patients (21%) were unevaluable. The study was terminated after the first accrual stage because of an insufficient number of complete or partial responses. To date, only 1 patient (with stable disease) has not relapsed. The estimated median survival time is 4 months and the estimated median time to treatment failure is 2.2 months. There were 3 early deaths associated with the treatment regimen: severe gastrointestinal toxicity, hemorrhage, and an acute pulmonary event. Docetaxel as a single agent does not demonstrate evidence of activity in malignant mesothelioma.

Aged↗

PubMed2002

Combined-modality treatment for resectable metastatic colorectal carcinoma to the liver: surgical resection of hepatic metastases in combination with continuous infusion of chemotherapy--an intergroup study.

PURPOSE: Despite technical improvements that have minimized the morbidity and mortality of hepatic surgery, the long-term outcome of resection of hepatic metastases of colorectal cancer remains poor, with the majority of patients experiencing treatment failure in the liver. Because arterial chemotherapy regimens targeted to the liver have demonstrated high response rates, an intergroup trial of adjuvant therapy for patients undergoing hepatic resection of liver metastases from colorectal cancer was initiated. PATIENTS AND METHODS: Patients with one to three potentially resectable metastases were randomized preoperatively to receive no further therapy (control arm, 56 patients) or postoperative hepatic arterial floxuridine combined with intravenous continuous-infusion fluorouracil (chemotherapy arm, 53 patients). After exclusion of patients identified as ineligible for the planned treatment at the time of surgery, there were 45 control patients and 30 on the chemotherapy arm. The study was powered to evaluate improvement in time to recurrence and hepatic disease-free survival, not overall survival. RESULTS: The 4-year recurrence-free rate was 25% for the control arm and 46% for the chemotherapy group (P =.04). The 4-year liver recurrence-free rate was 43% in the control group and 67% in the chemotherapy group (P =.03). The median survival of the 75 assessable patients was 49 months for the control arm and 63.7 months for the chemotherapy arm (P =.60). The median survival of all 109 patients was 47 months for the control arm compared with 34 months for the chemotherapy arm (P =.19) CONCLUSION: These data demonstrate that adjuvant intra-arterial and intravenous chemotherapy was beneficial in prolonging time to recurrence and pre-venting hepatic recurrence after hepatic resection of colorectal cancer.

Antimetabolites, Antineoplastic↗

PubMed2002

Survival analysis with time-varying regression effects using a tree-based approach.

Nonproportional hazards often arise in survival analysis, as is evident in the data from the International Non-Hodgkin's Lymphoma Prognostic Factors Project. A tree-based method to handle such survival data is developed for the assessment and estimation of time-dependent regression effects under a Cox-type model. The tree method approximates the time-varying regression effects as piecewise constants and is designed to estimate change points in the regression parameters. A fast algorithm that relies on maximized score statistics is used in recursive segmentation of the time axis. Following the segmentation, a pruning algorithm with optimal properties similar to those of classification and regression trees (CART) is used to determine a sparse segmentation. Bootstrap resampling is used in correcting for overoptimism due to split point optimization. The piecewise constant model is often more suitable for clinical interpretation of the regression parameters than the more flexible spline models. The utility of the algorithm is shown on the lymphoma data, where we further develop the published International Risk Index into a time-varying risk index for non-Hodgkin's lymphoma.

Algorithms↗