Lect_4.pdf

Data Processing Lect_4 Data Processing Data processing is any operation or set of operations performed upon data, whether or not by automatic means, such as collection, recording, organization, storage, adaptation, or alteration to convert it into useful information. Data processing cycle Once data...

Data Processing Lect_4 Data Processing Data processing is any operation or set of operations performed upon data, whether or not by automatic means, such as collection, recording, organization, storage, adaptation, or alteration to convert it into useful information. Data processing cycle Once data is collected, it is processed to convert it into useful information. The data is processed again and again until an accurate result is achieved. This is called the data processing cycle. Data processing is a very important activity and involves very careful planning. Data Processing Data Processing is a method of manipulation of data. The conversion of raw data into meaningful and machine-readable content. The term processing denotes the actual data manipulation techniques such as classifying, sorting, calculating, summarizing, comparing, etc. The process of converting data into useful information. Classification; The data is classified into different groups and subgroups, so each data group or sub-group can be handled separately. Sorting; The data is arranged into an order so that it can be accessed very quickly as and when required. Calculations; The arithmetic operations are performed on the numeric data to get the required results. Summarizing; The data is processed to represent it in a summarized form. it means that the summary of data is prepared for top management. Data Editing Editing of the data can be done in the following two stages: Field Editing; views the writing of individuals Central Editing; where the edition of all the data is done carefully and thoroughly The objective of editing is to ensure Accuracy of data Normalization of data Consistency of data Completeness of data Coherence of aggregated data The best possible data Classification of Data Arrangement of the data into groups and classes depending on the similarities so that the various important characteristics can be very easily noticed and the various features of the variables can be compared. Types of Classification Geographical Classification – classification of data takes place on the basis of a particular area or a particular region. Chronological classification – involves classification of the data on the basis of the time of its occurrence. Qualitative classification – classification is done based on some of the features, which do not have the ability of measure. Quantitative classification – classification is done based on the attributes or the features that can be measured. Quantitative data can be further divided into two stages, namely discrete and continuous. Classification features Data should be classified in such a way that it can be easily altered or changed with time, depending on the various situations and environments. Classification of the data should be objective-oriented. Data classification should always be simple in nature and should also be very clear. Should also be homogeneous i.e. data being kept in a particular class should be homogeneous. Classification should be stable; Stability in classification can be only achieved if a minimum number of changes are done in the data. Tabulation of Data Involves orderly arrangement of the data in columns and rows after the classification of data has been done. Tabulating helps in the condensation of the data and also in the analysis of the relations, trends, etc. Tabulation can be of two types: Frequency table; consists of two columns, in one column the qualities or values of the different attributes are entered and in the other column, the frequency of the occurrence against each category is entered. Response table; this type of table involves the indication of the reaction in a positive or a negative manner. Data Processing Methods Batch processing; Involves the storage of the information in a group or a batch till such a time when it is efficient or necessary to process them. One major drawback of this type is the delay in the detection and correction of the different errors Online processing; where processing of the data from the input to computation and updating of the status in the various files is done immediately. Real-time processing; the stored data is updated simultaneously as the transaction takes place. Distributed data processing; Involves the distribution of the computer processing among geographically and functionally multiple locations, linked with the help of the communications network. For stages of data processing cycle Data storage Data Input Data Processing & Analysis Information Output Data Input During the data input stage, health data is captured and converted to machine-processible form. Health data is consistent but not all data are created equally. Health data is coming from different sources, facilities, systems, and devices. (data quality varies). Health data input can be structured or unstructured, which should be treated differently at first, but standardized in the end. For example. health specialists fill in the fields with drop-down lists, they tick the checkboxes, but sometimes they input information in free text Health data variation Patient-generated health data (PGHD) Symptoms (skin rash, stomachache, cough, etc.) Medical imaging data Vitals (temperature, pulse rate, respiration rate) Lab results (blood, urine, other body fluids tests) Inpatient health monitoring data type Treatment (medications, procedures, etc.) Childhood diseases Family diseases Allergies Patient-generated health data (PGHD) PGHD is provided by the patient or their family members using portable medical devices / smart wearables watches, insulin pumps, fitness trackers, oximeters, and other gadgets to capture data. There can be objective and subjective PGHD: Objective data includes weight, heart rate, blood pressure, blood glucose, temperature, oximetry results, and more. Subjective implies the patient’s mood, sleep, pain, itching, etc. PGHD is especially valuable for chronic disease management and post-operative rehabilitation. Laboratory results data type Fluid or tissue: Blood Urine Stool Semen Saliva Sweat Amniotic fluid Exudate Transudate and more Characteristics: Type of scale: Mass Quantitative Volume Ordinal Chemical components Nominal (enzymes, hormones, lipids) Narrative Time stamp Method or procedure used for the test Time aspect (interval of time for observation) Medical imaging Data type Radiology: Radiography MRI Ultrasound CT Fluoroscopy Mammography Angiography Nuclear medicine: Positron emission tomography (PET) Single photon emission computed tomography (SPECT) Optical imaging: Optical coherence tomography (OCT) Inpatient health monitoring data type Implies continuous data accumulation and provides critical information for such care areas as Anesthesia, Critical Care, and Emergency Care. Specific monitoring technologies are involved to measure and track a variety of vitals, e.g. Temperature Total hemoglobin Arrhythmia analysis Cardiac status Anesthesia parameters Next lecture Data Analysis Purpose of Analysis of data Data Analysis Procedure Analyzation Steps Types of Analysis Descriptive Analysis Casual analysis Co – Relative Analysis Inferential Analysis Statistical analysis.