Electronic Health Records Quotes

We've searched our database for all the quotes and captions related to Electronic Health Records. Here they are! All 78 of them:

The parents in these groups were often caricatured as poorly informed, anti-science “denialists,” but they were generally better acquainted with the state of autism research than the outsiders presuming to judge them. They obsessively tracked the latest developments in the field on electronic mailing lists and websites. They virtually transformed their homes into labs, keeping meticulous records of their children’s responses to the most promising alternative treatments. They believed that the fate of their children’s health was too important to the alleged experts who had betrayed and misled families like theirs for decades. Motivated by the determination to relieve their children’s suffering, they became amateur researchers themselves, like the solitary man who calculated the density of the earth in his backyard with the help of his global network of correspondents.
Steve Silberman (NeuroTribes: The Legacy of Autism and How to Think Smarter About People Who Think Differently)
In 2006, researchers Brendan Nyhan and Jason Reifler created fake newspaper articles about polarizing political issues. The articles were written in a way that would confirm a widespread misconception about certain ideas in American politics. As soon as a person read a fake article, experimenters then handed over a true article that corrected the first. For instance, one article suggested that the United States had found weapons of mass destruction in Iraq. The next article corrected the first and said that the United States had never found them, which was the truth. Those opposed to the war or who had strong liberal leanings tended to disagree with the original article and accept the second. Those who supported the war and leaned more toward the conservative camp tended to agree with the first article and strongly disagree with the second. These reactions shouldn’t surprise you. What should give you pause, though, is how conservatives felt about the correction. After reading that there were no WMDs, they reported being even more certain than before that there actually were WMDs and that their original beliefs were correct. The researchers repeated the experiment with other wedge issues, such as stem cell research and tax reform, and once again they found that corrections tended to increase the strength of the participants’ misconceptions if those corrections contradicted their ideologies. People on opposing sides of the political spectrum read the same articles and then the same corrections, and when new evidence was interpreted as threatening to their beliefs, they doubled down. The corrections backfired. Researchers Kelly Garrett and Brian Weeks expanded on this work in 2013. In their study, people already suspicious of electronic health records read factually incorrect articles about such technologies that supported those subjects’ beliefs. In those articles, the scientists had already identified any misinformation and placed it within brackets, highlighted it in red, and italicized the text. After they finished reading the articles, people who said beforehand that they opposed electronic health records reported no change in their opinions and felt even more strongly about the issue than before. The corrections had strengthened their biases instead of weakening them. Once something is added to your collection of beliefs, you protect it from harm. You do this instinctively and unconsciously when confronted with attitude-inconsistent information. Just as confirmation bias shields you when you actively seek information, the backfire effect defends you when the information seeks you, when it blindsides you. Coming or going, you stick to your beliefs instead of questioning them. When someone tries to correct you, tries to dilute your misconceptions, it backfires and strengthens those misconceptions instead. Over time, the backfire effect makes you less skeptical of those things that allow you to continue seeing your beliefs and attitudes as true and proper.
David McRaney (You Are Now Less Dumb: How to Conquer Mob Mentality, How to Buy Happiness, and All the Other Ways to Outsmart Yourself)
The US traded its manufacturing sector’s health for its entertainment industry, hoping that Police Academy sequels could take the place of the rustbelt. The US bet wrong. But like a losing gambler who keeps on doubling down, the US doesn’t know when to quit. It keeps meeting with its entertainment giants, asking how US foreign and domestic policy can preserve its business-model. Criminalize 70 million American file-sharers? Check. Turn the world’s copyright laws upside down? Check. Cream the IT industry by criminalizing attempted infringement? Check. It’ll never work. It can never work. There will always be an entertainment industry, but not one based on excluding access to published digital works. Once it’s in the world, it’ll be copied. This is why I give away digital copies of my books and make money on the printed editions: I’m not going to stop people from copying the electronic editions, so I might as well treat them as an enticement to buy the printed objects. But there is an information economy. You don’t even need a computer to participate. My barber, an avowed technophobe who rebuilds antique motorcycles and doesn’t own a PC, benefited from the information economy when I found him by googling for barbershops in my neighborhood. Teachers benefit from the information economy when they share lesson plans with their colleagues around the world by email. Doctors benefit from the information economy when they move their patient files to efficient digital formats. Insurance companies benefit from the information economy through better access to fresh data used in the preparation of actuarial tables. Marinas benefit from the information economy when office-slaves look up the weekend’s weather online and decide to skip out on Friday for a weekend’s sailing. Families of migrant workers benefit from the information economy when their sons and daughters wire cash home from a convenience store Western Union terminal. This stuff generates wealth for those who practice it. It enriches the country and improves our lives. And it can peacefully co-exist with movies, music and microcode, but not if Hollywood gets to call the shots. Where IT managers are expected to police their networks and systems for unauthorized copying – no matter what that does to productivity – they cannot co-exist. Where our operating systems are rendered inoperable by “copy protection,” they cannot co-exist. Where our educational institutions are turned into conscript enforcers for the record industry, they cannot co-exist. The information economy is all around us. The countries that embrace it will emerge as global economic superpowers. The countries that stubbornly hold to the simplistic idea that the information economy is about selling information will end up at the bottom of the pile. What country do you want to live in?
Cory Doctorow (Content: Selected Essays on Technology, Creativity, Copyright, and the Future of the Future)
The ultimate goal of gathering big data in electronic medical records (EMR) ¬managed by professionals, and personal health records (PHR) updated by patients is creating smart alerts in natural language. That is, the system would understand the actual meaning of words and expressions in the records, thereby making it simpler to intervene in a patient’s affairs when needed.
Bertalan Meskó (The Guide to the Future of Medicine: Technology AND The Human Touch)
Medical records at many hospitals had been kept in manila folders rather than electronically, so health care providers typically had little information about what medications displaced patients with life-threatening ailments like cancer or heart disease were taking,
Linda Marsa (Fevered: Why a Hotter Planet Will Hurt Our Health-and How We Can Save Ourselves)
11.2.3 Quantitative and Qualitative Data Data is often described as being either quantitative or qualitative. Quantitative data is data that can be measured, written down
Mit Critical Data (Secondary Analysis of Electronic Health Records)
general recommendation is to follow the definition for CSVs set out by the Internet Engineering
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Task Force in the RFC 4180 specification document [5]. Summarized briefly, RFC 4180 specifies that: files may optionally begin with a header row, with each field separated by a comma; Records should be
Mit Critical Data (Secondary Analysis of Electronic Health Records)
When working with a version control system, a commit log provides a record of changes to code by contributor, providing transparency
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Github provide a simple mechanism for backing up content, helping to reduce the risk of data loss, and also provide tools for tracking issues and tasks [8, 9].
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Be able to apply basic techniques for dealing with common problems with raw data including missing data inconsistent data, and data from multiple sources.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Understand the requirements for a “clean” database that is “tidy” and ready for use in statistical analysis. Understand the steps of cleaning raw data, integrating data, reducing and reshaping
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Here, we describe three possible ways to deal with missing data [1]: Ignore the record. This method is not very effective, unless the record (observation/row) contains
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Determine and fill in the missing value manually. In general, this approach is the most accurate but it is also time-consuming and often is not feasible in a large dataset with many missing
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Use an expected value. The missing values can be filled in with predicted values (e.g. using the mean of the available data or some prediction method). It must be
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Noisy Data We term noise a random error or variance in an observed variable—a common
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Knowledge engineering tools may also be used to detect the violation of known data constraints. For example, known functional dependencies among attributes can be used to find values contradicting the functional
Mit Critical Data (Secondary Analysis of Electronic Health Records)
strictly stores data in several different data types, called ‘classes’: Numeric – e.g.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Integer – e.g. -1, 0, 1, 2, 3 Character – e.g. “vancomycin”, “metronidazole” Logical – TRUE, FALSE Factors/categorical – e.g. male or female under
Mit Critical Data (Secondary Analysis of Electronic Health Records)
critical part of the research process is deciding what types of data are needed to answer the research question. Administrative/claims data, secondary use of clinical trial data, prospective epidemiologic studies, and electronic
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Administrative databases tend to provide very large sample sizes and, in some cases, can be representative of an entire population. However, they lack granular patient-level data from the hospitalization such
Mit Critical Data (Secondary Analysis of Electronic Health Records)
these types of databases often have detailed, granular information not available in other clinical databases. However, researchers are often bound by the scope of data collection from the original research study which limits the questions
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Fewer than 10 % of clinical decisions are supported by high level evidence [22]. Clinical questions arise approximately in every other patient [23] and provide a large cache of research
Mit Critical Data (Secondary Analysis of Electronic Health Records)
When formulating a research question, investigators must carefully select the appropriate sample of subjects, exposure variable, outcome variable, and confounding variables. Once the research question is clear, study design becomes the next pivotal
Mit Critical Data (Secondary Analysis of Electronic Health Records)
For example, subject_id in the admissions table is a foreign key, because it references the primary key in the patients table.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
aware of the source of error and can repeat the measurement then ignore the known incorrect outlier value when planning care. However, clinicians cannot remove the erroneous measurement from the medical record
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Clinicians are often aware of the source of error and can repeat the measurement then ignore the known incorrect outlier value when planning care. However, clinicians cannot remove the erroneous measurement from the medical record
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Binning methods. Binning methods
Mit Critical Data (Secondary Analysis of Electronic Health Records)
may be detected by clustering, that is by grouping a set of values in such a way that the ones in the same group (i.e., in the same cluster) are more similar to each other than to those in other groups. Machine learning. Data can be smoothed
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Inconsistent Data There may be inconsistencies or duplications in the data. Some of them may be corrected manually using external references. This is the case,
Mit Critical Data (Secondary Analysis of Electronic Health Records)
EHR result from information being entered into the database by thousands of individual clinicians and hospital staff members, as well as captured from a variety of automated interfaces between the EHR and everything from
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Data integration is the process of combining data derived from various data sources (such as databases, flat files, etc.) into a consistent dataset. There are a number of issues to consider
Mit Critical Data (Secondary Analysis of Electronic Health Records)
complete dataset it will be necessary to integrate the patient’s full set of lab values (including those not associated with the same MIMIC ICUSTAY identifier) with the record of that ICU admission without repeating or missing records. Using shared
Mit Critical Data (Secondary Analysis of Electronic Health Records)
more effective representation of the dataset without compromising the integrity of the original data. The objective of this step is to provide a version of the dataset on which the subsequent statistical analysis will be more effective. Data reduction
Mit Critical Data (Secondary Analysis of Electronic Health Records)
columns and rows of a dataset so that it conforms with the following 3 rules of a “tidy” dataset [2, 3]: 1. Each variable forms a column 2. Each observation forms a row 3. Each value has its
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Tidy” datasets have the advantage of being more easily visualized and manipulated for later statistical analysis. Datasets exported from MIMIC usually are fairly “tidy” already; therefore, rule 2 is hardly ever broken. However,
Mit Critical Data (Secondary Analysis of Electronic Health Records)
12.3 PART 2—Examples of Data Pre-processing in R There are many tools for doing data pre-processing available, such as R, STATA, SAS, and Python; each differs in
Mit Critical Data (Secondary Analysis of Electronic Health Records)
also usually does not allow mixing of data types for a variable, except in a: List – as a one dimensional vector, e.g. c(“vancomycin”, 1.618, “red”) Data-frame – as a
Mit Critical Data (Secondary Analysis of Electronic Health Records)
table with rows (observations) and columns (variables) Lists and data-frames are treated as their own ‘class’ in R. Query output from MIMIC commonly will be in the form of data tables with different
Mit Critical Data (Secondary Analysis of Electronic Health Records)
R usually stores these tables as ‘data-frames’ when they are read into R. Special Values in R NA – ‘not available’, usually a default placeholder for missing values.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
NAN – ‘not a number’, only applying to numeric vectors. NULL – ‘empty’ value or set. Often returned by expressions where the value is undefined. Inf – value for ‘infinity’ and
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Setting Working Directory This step tells R where to read in the source files. Command: setwd(“directory_path”) Example: (If all data files are saved in directory “MIMIC_data_files
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Viewing the Dataset There are several commands in R that are very useful for getting a ‘feel’ of your datasets and see what they look like before you start manipulating them. View the first and last
Mit Critical Data (Secondary Analysis of Electronic Health Records)
One is Augmedix, an app that helps doctors do their charting more efficiently. The doctor wears Google Glass during the office visit and has a normal conversation with the patient—without a computer between them. Augmedix sends the audio-video feed from Google Glass to a remote, HIPAA secure location, where a trained scribe uses it to enter patient notes in the patient’s electronic health record.
Robin Farmanfarmaian (The Patient as CEO: How Technology Empowers the Healthcare Consumer)
Emergency department physicians spent 44 percent of their time entering data into electronic medical records, clicking up to 4,000 times during a 10-hour shift. —Becker’s Health IT & CIO Review magazine, October 11, 2013
Robert M. Wachter (The Digital Doctor: Hope, Hype, and Harm at the Dawn of Medicine’s Computer Age)
One common MIMIC database example is collapsing the ICD9 codes into broad clinical categories or variables of interest and assigning patients to them.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
and Collaboration One of the greatest challenges of working with medical data is gaining knowledge of
Mit Critical Data (Secondary Analysis of Electronic Health Records)
context in which data is collected. For this reason we cannot emphasize enough the importance of collaboration between both hospital staff and research analysts. Some examples of common issues to consider when
Mit Critical Data (Secondary Analysis of Electronic Health Records)
In short, observational studies may be more prone to bias (problems with internal validity) than RCTs due to difficulty obtaining the counterfactual control
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Several types of biases have been identified in observational studies. Selection bias occurs when the process of selecting exposed and unexposed patients introduces a bias into the study. For example, the time between starting MV and receiving IAC may introduce a type of “survivor treatment selection bias” since patients who received IAC could not have died prior to receiving IACs.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Information bias stems from mismeasurement or misclassification of certain variables. For retrospective studies, the data has already been collected and sometimes it is difficult to evaluate for errors in
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Another major bias in observational studies is confounding. As stated, confounding occurs when a third variable is correlated with both the exposure and outcome. If the third variable is not taken into consideration, a spurious relationship between the
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Several methods have been developed to attempt to address confounding in observational research such as adjusting for the confounder in regression equations if it is known and measured
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Over time, a cumulative sum of multiple high quality observational studies coupled with other mechanistic evidence
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Type of observational research Purpose Epidemiological Define incidence, prevalence, and risk factors for disease Predictive modeling Predict future outcomes Comparative effectiveness Identify intervention associated with superior outcomes Pharmacovigilance Detect rare drug adverse events occurring in the long-term
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Pharmacovigilance studies are yet another form of observational research. As many drug and device trials end after 1 or 2 years, observational methods are used to evaluate if there are patterns of rarer adverse events occurring
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Moseley ET, Hsu D, Stone DJ, Celi LA (2014) Beyond data liberation: addressing the problem of unreliable research. J Med Internet Res 16(11):e259
Mit Critical Data (Secondary Analysis of Electronic Health Records)
The Joint Commission (2014) National Patient safety goal on alarm management 2013
Mit Critical Data (Secondary Analysis of Electronic Health Records)
intensive care units (ICUs) are physiologically fragile and unstable, generally have life-threatening conditions, and require close monitoring and rapid therapeutic interventions. They are connected to an array of equipment and monitors, and are carefully attended by the clinical staff. Staggering amounts of data are collected daily on each patient in an ICU: multi-channel waveform data sampled hundreds of times each second, vital sign time series updated each second or minute, alarms and alerts, lab results, imaging results, records of medication and fluid administration, staff notes and more.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Physiology at MIT recognized that the richness and detail of the collected data opened the feasibility of creating a new generation of monitoring systems to track the physiologic state of the patient, employing the power of modern signal processing, pattern recognition, computational modeling, and knowledge-based clinical reasoning. In the long term, we hoped to design monitoring systems that not only synthesized and reported all relevant measurements to clinicians, but also formed pathophysiologic hypotheses that best explained the observed data. Such systems would permit early detection of complex problems, provide useful guidance on therapeutic interventions, and ultimately lead to improved patient outcomes.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
It was also clear that although petabytes of data are captured daily during care delivery in the country’s ICUs, most of these data were not being used to generate evidence or to discover new knowledge. The challenge, therefore, was to employ existing technology to collect, archive and organize finely detailed ICU data, resulting in a research resource of enormous potential to create new clinical knowledge, new decision support tools, and new ICU technology. We proposed to develop and make public a “substantial and representative” database gathered from complex medical and surgical ICU patients.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Fiscal Numbers (the latter uniquely identifies a particular hospitalization for patients who might have been admitted multiple times), which allowed us to merge information from many different hospital sources. The data were finally organized into a comprehensive relational database. More information on database merger, in particular, how database integrity was ensured, is available at the MIMIC-II web site [1]. The database user guide is also online [2]. An additional task was to convert the patient waveform data from Philips’ proprietary format into an open-source format. With assistance from the medical equipment vendor, the waveforms, trends, and alarms were translated into WFDB, an open data format that is used for publicly available databases on the National Institutes of Health-sponsored PhysioNet web site [3]. All data that were integrated into the MIMIC-II database were de-identified in compliance with Health Insurance Portability and Accountability Act standards to facilitate public access to MIMIC-II. Deletion of protected health information from structured data sources was straightforward (e.g., database fields that provide the patient name, date of birth, etc.). We also removed protected health information from the discharge summaries, diagnostic reports, and the approximately 700,000 free-text nursing and respiratory notes in MIMIC-II using an automated algorithm that has been shown to have superior performance in comparison to clinicians in detecting protected health information [4]. This algorithm accommodates the broad spectrum of writing styles in our data set, including personal variations in syntax, abbreviations, and spelling. We have posted the algorithm in open-source form as a general tool to be used by others for de-identification of free-text notes [5].
Mit Critical Data (Secondary Analysis of Electronic Health Records)
records: selection bias, confounding, and missing data. These are explored in greater depth in other chapters of this text. Selection bias, or the failure of the population of study to represent the generalizable population, can occur if all the patients, including controls, are already seeking medical
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Missing data or unevenly sampled data collected as part of the EHR creates its own complex set of challenges for health services research. For example,
Mit Critical Data (Secondary Analysis of Electronic Health Records)
KeywordsBig data​ – ​Confounding variables​ – ​Residual confounding​ – ​Selection bias​ – ​Pathophysiology​ – ​Propensity scores Take Home Messages Any observational study may have unidentified confounding variables that influence the effects of the primary exposure, therefore we must rely on research transparency along with thoughtful and careful examination of the limitations to
Mit Critical Data (Secondary Analysis of Electronic Health Records)
8.2 Confounding Variables in Big Data Confounding is often referred to as a “mixing of effects” [5] wherein the effects of the exposure on a particular outcome are associated with an additional factor, thereby distorting the true relationship. In this manner, confounding may falsely suggest an apparent association when no real association exists. Confounding is a particular threat in observational data, as is often the case with Big Data, due to the inability to
Mit Critical Data (Secondary Analysis of Electronic Health Records)
8.2Concept map of the association of renal function and cardiovascular mortality revealing more of the confounding influences Since many of these variables are rarely measured or quantified in large epidemiologic studies, significant residual confounding
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Chapters 11 and 12 deal with the essential task of data preparation and pre-processing, which is mandatory before any data can be fed into a statistical analysis tool.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Chapter 11 explains how a database is structured, what type of data they can contain and how to extract the variables of interest using queries;
Mit Critical Data (Secondary Analysis of Electronic Health Records)
As patients progress in time, their records must be properly and timely updated with new data while concurrently, old data are modified and/or deleted as the latter become irrelevant or no longer accurate.
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Non-clinical factors make a significant contribution to an individual’s health and providing this data to clinicians could inform context, counseling, and treatments. Data stewardship will be essential to protect confidential health information while still yielding the benefits of an integrated health system. 6.1 Introduction The definition of “clinical” data is expanding, as a datum becomes clinical once it has a relation to a disease process. For example: the accessibility
Mit Critical Data (Secondary Analysis of Electronic Health Records)
activity, diet, smoking and alcohol consumption are highly related to epidemic of obesity [2]. Some of this information, such as alcohol and tobacco use, is regularly documented by clinicians. Other information, such as dietary behaviors and physical activity, isn’t typically captured, but may be tracked by new technology (such as wearable computers commonly referred to as “wearables”) and integrated into electronic health records (EHRs).
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Patient ID Place Date (MM/DD/YYYY) Pressure (mmHg) Cycle 1 Random, RA 1/1/2015 130 Systole 1 Random, RA 1/1/2015 75 Diastole 1 Random, RA 1/7/2015 139 Systole 1 Random, RA 1/7/2015 83 Diastole 1 Randomly, RA 1/1/2015 141 Systole 1 Randomly, RA 1/1/2015 77 Diastole 1 Randomly, RA 1/7/2015 146 Systole 1 Randomly, RA 1/7/2015 82 Diastole 2 Random, RA 1/1/2015 158 Systole 2 Random, RA 1/1/2015 95 Diastole 2 Random, RA 1/7/2015 151 Systole 2 Random, RA 1/7/2015 91 Diastole 2 Randomly, RA 1/1/2015 150 Systole 2 Randomly, RA 1/1/2015 81 Diastole 2 Randomly, RA 1/7/2015 141 Systole 2 Randomly, RA 1/7/2015 84 Diastole
Mit Critical Data (Secondary Analysis of Electronic Health Records)
United States Zip Code system to approximate the patients’ area of residence. This method reports the first three digits of the patient’s zip code, while omitting the last two digits [18]. The first three digits of a zip code contain two pieces of information: the first integer in the code refers to a number of states, the following two
Mit Critical Data (Secondary Analysis of Electronic Health Records)
Fundamental to the feasibility of multidimensional collaborations is the ability to ensure accuracy of large-scale data and integrate it across multiple health record technologies and platforms. Efforts to ensure data quality and accessibility must be promoted
Mit Critical Data (Secondary Analysis of Electronic Health Records)
You can keep the Office of Personnel Management records, I don't need Electronic Health Records, give me the metadata, big data analytics and a custom tailored algorithm and a budget and during election time, I can cut to the psychological core of any population, period!
James Scott, Senior Fellow, Institute for Critical Infrastructure Technology
One of the major obstacles to using patient information to make clinical decisions is the fact that so much of it is "trapped" in an unstructured form. To clinicians unfamiliar with how computers interpret patient data, this will no doubt sound like technobabble, but the simple truth is that computers have a hard time interpreting data that is not neatly packaged in an electronic health record (EHR) system's drop-down menus and other structured entry points. Doctors' narrative notes, summaries of clinical research, and other "messy" text pose a problem that, until recently, could not be solved. Natural language processing (NLP), which is familiar to any physician who uses a speech recognition program to record their dictation, serves as the basis for Amazon Comprehend Medical (ACM) as well. Details on ACM are available on their web site.
Paul Cerrato
In the domain of mental health, huge pools of data are being used to train algorithms to identify signs of mental illness—a threat I call “surveillance psychiatry.” Electronic health records, data mining social networks, and even algorithmically classifying video surveillance will significantly amplify this approach. Corporations and governments are salivating at the prospect of identifying psychological vulnerability and dissent.
L.D. Green (We've Been Too Patient: Voices from Radical Mental Health--Stories and Research Challenging the Biomedical Model)