Biomedical subjects

Massimo Buscema

Publications and source records attributed to Massimo Buscema.

12 recordsLinked to original sources

PubMed2005

Possible contribution of artificial neural networks and linear discriminant analysis in recognition of patients with suspected atrophic body gastritis.

AIM: To investigate whether ANNs and LDA could recognize patients with ABG in a database, containing only clinical and biochemical variables, of a pool of patients with and without ABG, by selecting the most predictive variables and by reducing input data to the minimum. METHODS: Data was collected from 350 consecutive outpatients (263 with ABG, 87 with non-atrophic gastritis and/or celiac disease [controls]). Structured questionnaires with 22 items (anagraphic, anamnestic, clinical, and biochemical data) were filled out for each patient. All patients underwent gastroscopy with biopsies. ANNs and LDA were applied to recognize patients with ABG. Experiment 1: random selection on 37 variables, experiment 2: optimization process on 30 variables, experiment 3: input data reduction on 8 variables, experiment 4: use of only clinical input data on 5 variables, and experiment 5: use of only serological variables. RESULTS: In experiment 1, overall accuracies of ANNs and LDA were 96.6% and 94.6%, respectively, for predicting patients with ABG. In experiment 2, ANNs and LDA reached an overall accuracy of 98.8% and 96.8%, respectively. In experiment 3, overall accuracy of ANNs was 98.4%. In experiment 4, overall accuracies of ANNs and LDA were, respectively, 91.3% and 88.6%. In experiment 5, overall accuracies of ANNs and LDA were, respectively, 97.7% and 94.5%. CONCLUSION: This preliminary study suggests that advanced statistical methods, not only ANNs, but also LDA, may contribute to better address bioptic sampling during gastroscopy in a subset of patients in whom ABG may be suspected on the basis of aspecific gastrointestinal symptoms or non-digestive disorders.

Adult↗

PubMed2005

Artificial neural networks allow the use of simultaneous measurements of Alzheimer disease markers for early detection of the disease.

BACKGROUND: Previous studies have shown that in platelets of mild Alzheimer Disease (AD) patients there are alterations of specific APP forms, paralleled by alteration in expression level of both ADAM 10 and BACE when compared to control subjects. Due to the poor linear relation among each key-element of beta-amyloid cascade and the target diagnosis, the use of systems able to afford non linear tasks, like artificial neural networks (ANNs), should allow a better discriminating capacity in comparison with classical statistics. OBJECTIVE: To evaluate the accuracy of ANNs in AD diagnosis. METHODS: 37 mild-AD patients and 25 control subjects were enrolled, and APP, ADM10 and BACE measures were performed. Fifteen different models of feed-forward and complex-recurrent ANNs (provided by Semeion Research Centre), based on different learning laws (back propagation, sine-net, bi-modal) were compared with the linear discriminant analysis (LDA). RESULTS: The best ANN model correctly identified mild AD patients in the 94% of cases and the control subjects in the 92%. The corresponding diagnostic performance obtained with LDA was 90% and 73%. CONCLUSION: This preliminary study suggests that the processing of biochemical tests related to beta-amyloid cascade with ANNs allows a very good discrimination of AD in early stages, higher than that obtainable with classical statistics methods.

Journal Article↗

PubMed2005

The traveling salesman problem as a new screening test in early Alzheimer's disease: an exploratory study. Visual problem-solving in AD.

BACKGROUND AND AIMS: In the clinical setting, brief general mental status tests tend to detect early-stage Alzheimer's disease (AD) less well than more specific cognitive tests. Some preliminary information was collected on the diagnostic accuracy of the Traveling Salesman Problem (TSP) compared with the Mini-Mental State Examination (MMSE) in recognizing early AD from normal aging. METHODS: Fifteen AD outpatients (mean +/- SD MMSE: 24.45 +/- 2.61) and 30 age- and education-matched controls were submitted in a single blind protocol to a paper-and-pencil visually-presented version of the TSP, containing a random array of 30 points (TSP30). The task consisted of drawing the shortest continuous path, passing through each point once and only once, and returning to the starting point. Path lengths for subjects' solutions were computed and compared with the optimal solution given by a specific evolutionary algorithm called GenD. RESULTS: TP30 discriminated significantly better between AD subjects and controls (ROC curve AUC = 0.976; 95% CI 0.94-1.01) compared with the MMSE corrected for age and education (ROC curve AUC = 0.877; 95% CI 0.74-1.005). A path length of 478.2354, taken as "cut-off point", classified correctly subjects with a sensitivity of 93.3% and a specificity of 99.3%, whereas a score corrected for age and education of 25.85 on the MMSE had a sensitivity of 73.3% and a specificity of 96.7%. CONCLUSIONS: The TSP seems to be particularly sensitive to early AD and independent of patient's age and educational level. The high diagnostic ability, simplicity, and independence of age and education make the TSP promising as a screening test for early AD.

Aged↗

PubMed2005

Two different Alzheimer diseases in men and women: clues from advanced neural networks and artificial intelligence.

BACKGROUND: Studies of the gender-related differences in the clinical presentation of Alzheimer's disease (AD) have focused on specific aspects of the disease (eg, circulating metabolites, cognitive capacity, or epidemiologic trends). OBJECTIVE: This study accounts for several descriptors of the disease simultaneously, providing a multidimensional analysis of a cohort of patients with AD. METHODS: Our analysis was conducted using self-organizing maps (SOMs). The high number (60) of independent variables (clinical, demographic, biochemical, and neuropsychological) observed in the study patients defines a complex and high-dimensional input space that can be processed by SOMs. Without supervision, SOMs examine nonlinear relations among the variables and cluster observations so that topologic relationships between variables correspond to the similarity of their distribution. Through such nonlinear autoclustering, subsets of observations (ie, clusters of subjects) can be identified in which essential information is concentrated. Each subject is identified by particular values of the variables (the record), and a specific set of variable values (the codebook) defines a distinct class. RESULTS: The study sample included 211 patients with mild to moderate AD (143 women, 68 men; mean [SD] age, 71.9 [7.2] years). All patients were assigned to 3 macroclasses-called A, B, and C-on the basis of matrix codebook neighborhoods. In terms of vectorial distance between codebooks, class A and B were quite similar, whereas the separation between class C and classes A and B was evident. The SOM distribution of values of variables across the output matrix did not show any specific pattern for most of the considered characteristics. However, we found only male patients in class C. This class distinction was not substantially changed when sex was removed from the database. Male and female patients were comparable with respect to dementia severity, demographic characteristics, psychiatric and behavioral symptoms, indicators of physical disability, and general health status. CONCLUSIONS: SOMs indicate nonlinear multifactorial interactions among the descriptors of the features of AD that seem to be linked to sex and would have been missed by traditional statistical analysis. This finding may offer a novel epidemiologic rationale for research into different pathogenic mechanisms in men and women with AD.

Aged↗

PubMed2005

Artificial neural networks are able to recognize gastro-oesophageal reflux disease patients solely on the basis of clinical data.

BACKGROUND: Artificial neural networks (ANN) are modelling mechanisms that are highly flexible and adaptive to solve the non-linearity inherent in the relationship between symptoms and underlying pathology. OBJECTIVES: To assess the efficacy of ANN in achieving a diagnosis of gastro-oesophageal reflux disease (GORD) using oesophagoscopy or pH-metry as a diagnostic gold standard and discriminant analysis as a statistical comparator technique in a group of patients with typical GORD symptoms and with or without GORD objective findings (e.g. a positive oesophagoscopy or a pathological oesophageal pH-metry). METHODS: The sample of 159 cases (88 men, 71 women) presenting with typical symptoms of GORD, were subdivided on the basis of endoscopy and pH-metry results into two groups: GORD patients with or without oesophagitis, group 1 (N=103), and pH and endoscopy-negative patients in whom both examinations were negative, group 2 (N=56). A total of 101 different independent variables were collected: demographic information, medical history, generic health state and lifestyle, intensity and frequency of typical and atypical symptoms based on the Italian version of the Gastroesophageal Reflux Questionnaire (Mayo Clinic). The diagnosis was used as a dependent variable. Different ANN models were assessed. RESULTS: Specific evolutionary algorithms selected 45 independent variables, concerning clinical and demographic features, as predictors of the diagnosis. The highest predictive performance was achieved by a 'back propagation' ANN, which was consistently 100% accurate in identifying the correct diagnosis compared with 78% obtained by traditional discriminant analysis. CONCLUSION: On the basis of this preliminary work, the use of ANN seems to be a promising approach for predicting diagnosis without the need for invasive diagnostic methods in patients suffering from GORD symptoms.

Adult↗

PubMed2004

Recognition of patients with cardiovascular disease by artificial neural networks.

BACKGROUND: Artificial neural networks (ANNs) are computer algorithms inspired by the highly interactive processing of the human brain. When exposed to complex data sets, ANNs can learn the mechanisms that correlate different variables and perform complex classification tasks. AIMS: A database, of 949 patients and 54 variables, was analysed to evaluate the capacity of ANNs to recognise patients with (VE+, n = 196) or without (VE-, n = 753) a history of vascular events on the basis of vascular risk factors (VRFs), carotid ultrasound variables (UVs) or both. METHOD: The performance of ANN was assessed by calculating the percentage of correct identifications of VE+ and VE- patients (sensitivity and specificity, respectively) and the prediction accuracy (weighted mean between sensitivity and specificity). RESULTS: The results showed that ANNs can be trained to identify VE+ and VE- subjects more accurately than discriminant analyses. When VRFs and UVs were used as input variables, the prediction accuracies of the ANN providing the best results were 80.8% and 79.2%, respectively. The addition of gender, age, weight, height and body mass index to UVs increased accuracy of prediction to 83.0%. When the ANNs were allowed to choose the relevant input data automatically (I.S. system-Semeion), 37 variables were selected among 54, five of which were UVs. Using this set of variables as input data, the performance of the ANNs in the classification task reached a prediction accuracy of 85.0%. with the 92.0% correct classification of VE+ patients. CONCLUSIONS: Artificial neural network technology is highly promising in the development of accurate diagnostic tools designed to recognize patients at high risk of cardiovascular diseases.

Adult↗

PubMed2004

Artificial neural networks and artificial organisms can predict Alzheimer pathology in individual patients only on the basis of cognitive and functional status.

Data from several studies have pointed out the existence of a strong correlation between Alzheimer's disease (AD) neuropathology and cognitive state. However, because of their highly complex and nonlinear relationship, it has been difficult to develop a predictive model for individual patient classification through traditional statistical approaches. When exposed to complex data sets, artificial neural networks (ANNs) can recognize patterns, learn the relationship of different variables, and address classification tasks. To predict the results of postmortem brain examinations, we applied ANNs to the Nun Study data set, a longitudinal epidemiological study, which includes annual cognitive and functional evaluation. One hundred seventeen subjects from the study participated in this analysis. We determined how demographic data and the cognitive and functional variables of each subject during the last year of her life could predict the presence of brain pathology expressed as Braak stages, neurofibrillary tangles (NFTs) and neuritic plaques (NPs) count in the neocortex and hippocampus, and brain atrophy. The result of this analysis was then compared with traditional statistical models. ANNs proved to be better predictors than Linear Discriminant Analysis in all experimentations (+ approximately 10% in overall accuracy), especially when assembled in Artificial Organisms (+ approximately 20% in overall accuracy). Demographic, cognitive, and clinical variables were better predictors of tangles count in the neocortex and in the hippocampus when compared to NPs count. These findings strengthen the hypothesis that neurofibrillary pathology may represent the major anatomic substrate of the cognitive impairment found in AD.

Alzheimer Disease↗

PubMed2003

Thyroid hemiagenesis: prevalence in normal children and effect on thyroid function.

Thyroid hemiagenesis prevalence was studied by neck ultrasound examination in 24,032 unselected 11- to 14-yr-old schoolchildren from southeastern Sicily. Twelve cases of thyroid hemiagenesis were identified, with a prevalence of 0.05%. The female to male ratio was 1:1.4. Thyroid hemiagenesis was always due to the absence (11 cases) or severe hypoplasia (1 case) of the left lobe. The hemiagenetic thyroid volume was within the normal total thyroid volume range normalized to age in 4 of 12 cases, enlarged in 3, and significantly reduced in 5. Thyroid function (thyroid hormones and TSH, both basal and 30 min after administration of 200 micro g TRH, iv) was evaluated in 9 of 12 children and was always within the normal range. However, children with thyroid hemiagenesis had an average serum TSH significantly higher than that of 18 matched controls (2.8 +/- 0.6 vs. 1.9 +/- 0.5 mU/liter; P < 0.001). This study confirms that thyroid hemiagenesis is nearly always due to left lobe defect, and that its prevalence is similar to the cumulative prevalence of thyroid agenesis and ectopia. Compensatory hypertrophy of the residual thyroid lobe occurs in most, but not all, cases and is due to thyroid tissue overstimulation by TSH. The high risk of goiter and hypothyroidism suggests systematic follow-up of all identified cases of thyroid hemiagenesis.

Adolescent↗

PubMed2002

Use of artificial networks in clinical trials: a pilot study to predict responsiveness to donepezil in Alzheimer's disease.

OBJECTIVES: To evaluate the accuracy of artificial neural networks compared with discriminant analysis in classifying positive and negative response to the cholinesterase inhibitor donepezil in a group of Alzheimer's disease (AD) patients. DESIGN: Convenience sample. SETTING: Patients with mild to moderate AD consecutively admitted to a geriatric day hospital and treated with donepezil 5 mg/day. PARTICIPANTS: Sixty-one older patients of both sexes with AD. MEASUREMENTS: Accuracy in detecting subjects sensitive (responders) or not (nonresponders) to 3-month therapy with ANNs. The criterion standard for evaluation of efficacy was the scores of Alzheimer's Disease Assessment Scale-Cognitive portion and Clinician's Interview Based Impression of Change-plus scales. RESULTS: ANNs were more effective in discriminating between responders and nonresponders than other advanced statistical methods, particularly linear discriminant analysis. The total accuracy in predicting the outcome was 92.59%. CONCLUSIONS: ANNs appear to be a useful tool in detecting patient responsiveness to pharmacological treatment in AD.

Aged↗

PubMed2002

Genetics of specific phenotypes of congenital hypothyroidism: a population-based approach.

Congenital hypothyroidism (CH) may cause severe and irreversible neurologic and developmental abnormalities when not recognized early. Many millions of newborns have now been screened and many thousands of patients with CH have been identified. Approximately 80%-85% have defects of thyroid gland development, while 15%-20% have congenital errors of thyroid hormone biosynthesis. An entire population screened for CH over a long period of time, was studied in the present report, using a population-based approach. In particular, two CH phenotypes, both presenting with in situ thyroid gland (patients with either goiter or with thyroid gland volume ranging from normal to hypoplasic) were analyzed. Mutations were searched in some of the most likely candidate genes: thyroperoxidase (TPO) in patients with CH goiter, Pax8 and thyrotropin receptor (TSHR) in the other group. In the former group (n = 8), four TPO gene mutations were identified in three patients. One patient was a compound heterozygous. In two cases an already described mutation (1277(insGGCC)) was present; in two other cases mutations not previously described (1996(G-->T) and 2295(G-->A)), which induced aminoacid variations with a Glu --> Stop and Val --> Ile changes, respectively, were identified. In all patients mutations were inherited from one of the parents. In the case of the compound heterozygous patient, one mutation was inherited from the mother (1277(insGGCC)) and the other from the father (1996(G-->T), Glu --> Stop). In the latter group (n = 8), a patient with a 16-base pair C(T)(13)CC deletion in TSHR gene intron 8, 42-bp distal to exon/intron 8 splice junction, was identified. No mutation was identified in Pax8 gene.

Congenital Hypothyroidism↗

PubMed2002

False-positive findings on (131)I whole-body scans because of posttraumatic superficial scabs.

UNLABELLED: Nonspecific (131)I uptake may affect both the specificity and the accuracy of whole-body scanning (WBS) performed after (131)I administration in the follow-up of thyroid carcinoma after thyroidectomy. We report a newly identified cause of false-positive WBS findings: posttraumatic superficial scabs. METHODS: Four patients who underwent thyroidectomy for differentiated thyroid carcinoma were studied after therapeutic administration of 3,700 MBq (131)I. RESULTS: WBS revealed an area of uptake in the lower limbs, in a site corresponding to a slight abrasion of the skin that had incidentally occurred between a few hours before and 24 h after radioiodine administration. In 2 patients, a radioiodine concentration in the scab was shown by the disappearance of the radioactivity in the leg after removal of the scab and by detection of radioactivity in the collected material. CONCLUSION: Posttraumatic superficial scabs may be a cause of false-positive WBS findings. High (131)I doses, although providing increased sensitivity, may also increase the number of false-positive results.

Adenocarcinoma, Follicular↗

PubMedDate not supplied

A brief overview and introduction to artificial neural networks.

This article is designed to acquaint professionals working in the field of substance use intervention with a range of artificial intelligence nonlinear, powerful tools, artificial neural networks, concepts, and paradigms. The family of ANNs, when appropriately selected and used, permits the maximization of what can be derived from available data as well as our studying and understanding the many people, processes, and phenomena which comprise substance use and its intervention. The latter represent complex, dynamic, multidimensional phenomena which are unpredictable and uncontrollable in the traditional "cause and effect" sense. As such they are likely to be nonlinear in their very essence. Using linear-based paradigms for planned intervention with nonlinear phenomena brooks the all-too-common possibility of using inappropriate intervention paradigms and/or drawing misleading conclusions about what is and/or has happened.

Alcoholism↗