Comparison of hierarchical clustering and neural network clustering: an analysis on precision dominance.

A comparison of neural network clustering (NNC) and hierarchical clustering (HC) is conducted to assess computing dominance of two machine learning (ML) methods for classifying a populous data of large number of variables into clusters. An accurate clustering disposition is imperative to investigate assembly-influence of predictors on a system over a course of time. Moreover, categorically designated representation of variables can assist in scaling down a wide data without loss of essential system knowledge. For NNC, a self-organizing map (SOM)-training was used on a local aqua system to learn distribution and topology of variables in an input space. Ternary features of SOM; sample hits, neighbouring weight distances and weight planes were investigated to institute an optical inference of system's structural attributes. For HC, constitutional partitioning of the data was executed through a coupled dissimilarity-linkage matrix operation. The validation of this approach was established through a higher value of cophenetic coefficient. Additionally, an HC-feature of stem-division was used to determine cluster boundaries. SOM visuals reported two locations' samples for remarkable concentration analogy and presence of 4 extremely out of range concentration parameter from among 16 samples. NNC analysis also demonstrated that singular conduct of 18 independent components over a period of time can be comparably inquired through aggregate influence of 6 clusters containing these components. However, a precise number of 7 clusters was retrieved through HC analysis for segmentation of the system. Composing elements of each cluster were also distinctly provided. It is concluded that simultaneous categorization of system's predictors (water components) and inputs (locations) through NNC and HC is valid to the precision probability of 0.8, as compared to data segmentation conducted with either of the methods exclusively. It is also established that cluster genesis through combined HC's linkage and dissimilarity algorithms and NNC is more reliable than individual optical assessment of NNC, where varying a map size in SOM will alter the association of inputs' weights to neurons, providing a new consolidation of clusters.

A proficiency assessment of integrating machine learning (ML) schemes on Lahore water ensemble.

A synthesis of statistical inference and machine learning (ML) tools has been employed to establish a comprehensive insight of a coarse data. Water components' data for 16 central distributing locations of Lahore, the capital of second most populated province of Pakistan, has been analyzed to gauge current water stature of the city. Moreover, a classification of surplus-response variables through tolerance manipulation was incorporated to debrief dimension aspect of the data. By the same token, the influence of supererogatory variables' renouncement through identification of clustering movement of constituents is inquired. The approach of building a spectrum of colluding results through application of comparable methods has been experimented. To test the propriety of each statistical method prior to its execution on a huge data, a faction of ML schemes have been proposed. The supervised learning tools pca, factoran and clusterdata were implemented to establish an elemental character of water at elected locations. A location 'LAH-13' was highlighted for containing an out of normal range Total Dissolved Solids (TDS) concentration in the water. The classification of lower and higher variability parameters carried out by Sample Mean (XBAR) control identified a set of least correlated variables pH, As, Total Coliforms and E. Coli. The analysis provided four locations LAH-06, LAH-10, LAH-13 and LAH-14 for extreme concentration propensity. An execution of factoran demonstrated that specific tolerance of independent variability '0.005' could be employed to reduce dimension of a system without loss of fundamental data information. A higher value of cophenetic coefficient, c = 0.9582 provided the validation for an accurate cluster division of similar characteristics' variables. The current approach of mutually validating ML and SA (statistical analysis) schemes will assist in preparing the groundwork for state of the art analysis (SOTA) analysis. The advantage of our approach can be examined through the fact that the related SOTA will further refine the predictive precision between two comparable methods, unlike the SOTA analysis between two random ML methods. Conclusively, this study featured the locations LAH-03, LAH-06, LAH-12, LAH-13, LAH-14 and LAH-15 with compromised water quality in the region.

An assessment of subject-comprehension and subject-command attained through digital learning platforms.

A synthesized investigation, employing graphical and analytical approach, has been conducted to examine inadequacy of electronic education and limitations posed by transformative mode of learning from students' perspective. Moreover, the breadth of subject understanding through digital mode and students' preference for physical or electronic mode of learning in the future were examined. A descriptive analysis was executed through R programming for the obtained numeric-characteristic statistics. For computational analysis of the data to determine proportion of deteriorating virtual-assessment performance attributed to conditioned subject-command, a machine learning approach of interaction-regression is adopted. It is implied through the obtained results that a majority of students felt discontented at not being able to achieve optimized learning outcomes post-virtual-attendance of study programs. It is also concluded that blended influence of online learning and partial subject-command resulted in insufficient assessment performance. Additionally, the current study highlights the importance of need-based adaptations to facilitate automated mode of learning and virtual platforms' uniform access to students.

"Risk factors of birth asphyxia".

BACKGROUND: Birth asphyxia is an insult to the fetus or newborn due to failure to breath or breathing poorly, leads to decrease oxygen perfusion to various organs. According to WHO, 4 million neonatal deaths occurred each year due to birth asphyxia. Our goal was to evaluate antepartum, intrapartum, and fetal risk factors of birth asphyxia. METHODS: It was a Retrospective Case control study, conducted at Neonatal Intensive Care Unit of pediatric ward (I, II, III) and in Gynecology wards (I, II, III) of Civil Hospital Karachi, Dow University of Health Sciences. Study was conducted from January 2011-November 2012. Neonates diagnosed with birth asphyxia were considered as "cases" while neonates born either with normal vaginal delivery or by cesarean section having no abnormality were considered as "control". Demographics of both the mother and neonate were noted and Questions regarding possible risk factors were asked from mother. Ethical issues were confirmed from Institutional review board of Civil Hospital Karachi, Dow University of Health Sciences. All data was entered and analyzed through SPSS 19. RESULT: Out of total 240 neonates, 123 were "cases" and 117 were "control". Mean maternal age in "case" group was 24.22 ± 3.38 while maternal age of control group was 24.30 ± 4.04. Significant antepartum risk factors were maternal age of 20-25 (OR 0.30 CI 95% 0.07-1.21), booking status (OR 0.20 CI 95% 0.11-0.37), pre-eclampsia (OR 0.94 CI 95% 0.90-0.98) and primigravidity (OR 2.64 CI 95% 1.56-4.46). Significant Intrapartum risk factors were breech presentation (OR 2.96 CI 95% 1.25-7.02), home delivery (OR 16.16 CI 95% 3.74-69.75) and maternal fever (OR 10.01 CI95% 3.78-26.52). Significant Fetal risk factors were resuscitation of child (OR 23 CI 95% 31.27-1720.74), pre-term babies(OR 0.34 CI 95% 0.19-0.58), fetal distress (OR 0.01 CI 95% 0.00-0.11) and baby weight (OR 0.13 CI 95% 0.05-0.32). CONCLUSION: Measures should be taken to prevent neonatal mortality with great emphasis on skilled attendance at birth and appropriate care of preterm and low birth weight neonates.

Spectrum of prostatic lesions.

BACKGROUND: Prostate gland of male reproductive system is about the size of walnut and surrounds the urethra. Most frequently encountered diseases affecting prostate are Prostatitis, Benign prostatic hyperplasia and Prostatic cancer .Our objective of study was to evaluate the spectrum and correlation of prostatic lesions with presenting complaints of patient. METHODS: It was a cross-sectional study conducted in Pathology Department of Dow Medical College, Dow University of Health Sciences during the period of 1st January 2010 to December 2012. Pathology department of Dow Medical College collected specimens from both Civil Hospital and Lyari General Hospital Karachi, Pakistan. Specimens were taken through transurethral resection of prostate (TURP), simple prostatectomy and radical prostatectomy. A questionnaire was made and information including name, age, ward name of hospital, laboratory number, clinical diagnosis and symptoms were noted in it. Data was entered and analyzed through SPSS 19. RESULT: During the targeted months, 48 prostatic specimens were received with a mean age of 65.7 + -7.6 years. Common presenting complains were urinary retention in 23(47.9%) patients, followed by dribbling in 12(25%). Out of 48 patients, 42 have Benign Prostatic Hyperplasia and 6 have Prostatic Adenocarcinoma. Both Benign Prostatic Hyperplasia and Prostatic Adenocarcinoma were more prevalent in the age group of 60-70 years. CONCLUSION: Frequency of prostatic cancer is on the rise and measures should be taken for its early detection. Screening protocols and awareness programs need to be introduced. Screening programs should be focused on level of androgens and molecular pathogenesis.

Clinico- pathological profile of patients with breast diseases.

BACKGROUND: To evaluate the spectrum of breast diseases and their association with presenting complains of patients. METHODOLOGY: It was a cross sectional study conducted from 1st January 2010 - 30th December 2012. A total of 254 breast specimens of patients, who were admitted in Civil Hospital Karachi with breast complaints, were included. Specimens were collected either from mastectomy, lumpectomy or needle biopsy from the admitted patients. Informed written consent was taken from all the patients. All patients with primary breast diseases were included. Patients undergoing chemotherapy or with secondary breast disease and slides with insufficient specimen were excluded. All data was entered and analyzed through SPSS 19. RESULT: There were 254 breast lesions, histologically diagnosed in 3 year review period. The overall mean age of patients with breast lesion was 25.18, SD ± 11.73 with a wide age range of 12-74 years. Most common cases identified are benign 191(75.3%), followed by inflammatory 30(11.8%) and malignant lesions 30(11.8%). Most patients presenting with the complain of pain have diagnosis of fibroadenoma 24 (63.2%) while patient with complain of lump also have the most common diagnosis of fibroadenoma 147 (72.8%). CONCLUSIONS: Study shows that in Pakistani females, mostly encountered breast lesion was fibroadenoma. Due to lack of awareness breast diseases present lately. Awareness must be created among women to reduce the mortality and morbidity with breast lesions. VIRTUAL SLIDES: The virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/1037059088969395.