Embed Analytics in a Business Processes
Limit: 250 words
Estimated time: About 1.5 hours (after completing the readings)
Deliverable: Based on your reading of the assigned articles, especially “Embed Analytics in Decision Processes”, compose a response to the following questions.
Think of an SCM-related business process in an organization that interests you which contains at least one decision task that is not presently automated but that could potentially be. Let us call it the “focal decision task”.
(For example, refer to the in the insurance claim process in the reading “Embed Analytics in Decision Processes” illustrated in Figure 7-1.)
- Describe the business process and the focal decision task and provide a truncated diagram of the business process (e.g., labeled boxes and arrows).
- Suggest a possible automation for this decision task. Include what data will be used and whether the decision should be fully automated, automated with exception/overrides, or assisted after the change – and why.
- Describe what technology(ies) and/or algorithm(s) could be put to use to inform the decision process your suggested above.
- What improvements do you expect to see in the outcome of the business process?
Tip: Be direct in your writing. Avoid overly descriptive and/or redundant statements. Use the diagram to compliment a relatively streamlined answer to point (1) of this assignment. Make sure your text and diagram symbols are legible and high-resolution. For now, your diagram should be simpler than Figure 7-1 in the case. Be specific in addressing the underlined portions of the prompt.
Data_Science_for_Business.pdf
Praise
“A must-read resource for anyone who is serious about embracing the opportunity of big data.”
— Craig Vaughan Global Vice President at SAP
“This timely book says out loud what has finally become apparent: in the modern world, Data is Business, and you can no longer think business without thinking data. Read this
book and you will understand the Science behind thinking data.” — Ron Bekkerman
Chief Data Officer at Carmel Ventures
“A great book for business managers who lead or interact with data scientists, who wish to better understand the principals and algorithms available without the technical details of
single-disciplinary books.” — Ronny Kohavi
Partner Architect at Microsoft Online Services Division
“Provost and Fawcett have distilled their mastery of both the art and science of real-world data analysis into an unrivalled introduction to the field.”
—Geoff Webb Editor-in-Chief of Data Mining and Knowledge
Discovery Journal
“I would love it if everyone I had to work with had read this book.” — Claudia Perlich
Chief Scientist of M6D (Media6Degrees) and Advertising Research Foundation Innovation Award Grand Winner (2013)
www.it-ebooks.info
“A foundational piece in the fast developing world of Data Science. A must read for anyone interested in the Big Data revolution.”
—Justin Gapper Business Unit Analytics Manager at Teledyne Scientific and Imaging
“The authors, both renowned experts in data science before it had a name, have taken a complex topic and made it accessible to all levels, but mostly helpful to the budding data scientist. As far as I know, this is the first book of its kind—with a focus on data science
concepts as applied to practical business problems. It is liberally sprinkled with compelling real-world examples outlining familiar, accessible problems in the business world: customer
churn, targeted marking, even whiskey analytics! The book is unique in that it does not give a cookbook of algorithms, rather it helps the
reader understand the underlying concepts behind data science, and most importantly how to approach and be successful at problem solving. Whether you are looking for a good
comprehensive overview of data science or are a budding data scientist in need of the basics, this is a must-read.”
— Chris Volinsky Director of Statistics Research at AT&T Labs and Winning
Team Member for the $1 Million Netflix Challenge
“This book goes beyond data analytics 101. It’s the essential guide for those of us (all of us?) whose businesses are built on the ubiquity of data opportunities and the new mandate for
data-driven decision-making.” —Tom Phillips
CEO of Media6Degrees and Former Head of Google Search and Analytics
“Intelligent use of data has become a force powering business to new levels of competitiveness. To thrive in this data-driven ecosystem, engineers, analysts, and managers
alike must understand the options, design choices, and tradeoffs before them. With motivating examples, clear exposition, and a breadth of details covering not only the “hows” but the “whys”, Data Science for Business is the perfect primer for those wishing to become
involved in the development and application of data-driven systems.” —Josh Attenberg
Data Science Lead at Etsy
www.it-ebooks.info
“Data is the foundation of new waves of productivity growth, innovation, and richer customer insight. Only recently viewed broadly as a source of competitive advantage, dealing well with data is rapidly becoming table stakes to stay in the game. The authors’ deep applied
experience makes this a must read—a window into your competitor’s strategy.” — Alan Murray
Serial Entrepreneur; Partner at Coriolis Ventures
“One of the best data mining books, which helped me think through various ideas on liquidity analysis in the FX business. The examples are excellent and help you take a deep
dive into the subject! This one is going to be on my shelf for lifetime!” — Nidhi Kathuria
Vice President of FX at Royal Bank of Scotland
www.it-ebooks.info
Foster Provost and Tom Fawcett
Data Science for Business
www.it-ebooks.info
Data Science for Business by Foster Provost and Tom Fawcett
Copyright © 2013 Foster Provost and Tom Fawcett. All rights reserved.
Printed in the United States of America.
Published by O’Reilly Media, Inc., 1005 Gravenstein Highway North, Sebastopol, CA 95472.
O’Reilly books may be purchased for educational, business, or sales promotional use. Online editions are also available for most titles (http://my.safaribooksonline.com). For more information, contact our corporate/ institutional sales department: 800-998-9938 or [email protected].
Editors: Mike Loukides and Meghan Blanchette Production Editor: Christopher Hearse Proofreader: Kiel Van Horn Indexer: WordCo Indexing Services, Inc.
Cover Designer: Mark Paglietti Interior Designer: David Futato Illustrator: Rebecca Demarest
July 2013: First Edition
Revision History for the First Edition:
2013-07-25: First release
See http://oreilly.com/catalog/errata.csp?isbn=9781449361327 for release details.
The O’Reilly logo is a registered trademark of O’Reilly Media, Inc. Many of the designations used by man‐ ufacturers and sellers to distinguish their products are claimed as trademarks. Where those designations appear in this book, and O’Reilly Media, Inc., was aware of a trademark claim, the designations have been printed in caps or initial caps. Data Science for Business is a trademark of Foster Provost and Tom Fawcett.
While every precaution has been taken in the preparation of this book, the publisher and authors assume no responsibility for errors or omissions, or for damages resulting from the use of the information contained herein.
ISBN: 978-1-449-36132-7
[LSI]
www.it-ebooks.info
Table of Contents
Preface. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xi
1. Introduction: Data-Analytic Thinking. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 The Ubiquity of Data Opportunities 1 Example: Hurricane Frances 3 Example: Predicting Customer Churn 4 Data Science, Engineering, and Data-Driven Decision Making 4 Data Processing and “Big Data” 7 From Big Data 1.0 to Big Data 2.0 8 Data and Data Science Capability as a Strategic Asset 9 Data-Analytic Thinking 12 This Book 14 Data Mining and Data Science, Revisited 14 Chemistry Is Not About Test Tubes: Data Science Versus the Work of the Data
Scientist 15 Summary 16
2. Business Problems and Data Science Solutions. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 Fundamental concepts: A set of canonical data mining tasks; The data mining process; Supervised versus unsupervised data mining. From Business Problems to Data Mining Tasks 19 Supervised Versus Unsupervised Methods 24 Data Mining and Its Results 25 The Data Mining Process 26
Business Understanding 27 Data Understanding 28 Data Preparation 29 Modeling 31 Evaluation 31
iii
www.it-ebooks.info
Deployment 32 Implications for Managing the Data Science Team 34 Other Analytics Techniques and Technologies 35
Statistics 35 Database Querying 37 Data Warehousing 38 Regression Analysis 39 Machine Learning and Data Mining 39 Answering Business Questions with These Techniques 40
Summary 41
3. Introduction to Predictive Modeling: From Correlation to Supervised Segmentation. 43 Fundamental concepts: Identifying informative attributes; Segmenting data by progressive attribute selection. Exemplary techniques: Finding correlations; Attribute/variable selection; Tree induction. Models, Induction, and Prediction 44 Supervised Segmentation 48
Selecting Informative Attributes 49 Example: Attribute Selection with Information Gain 56 Supervised Segmentation with Tree-Structured Models 62
Visualizing Segmentations 67 Trees as Sets of Rules 71 Probability Estimation 71 Example: Addressing the Churn Problem with Tree Induction 73 Summary 78
4. Fitting a Model to Data. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 81 Fundamental concepts: Finding “optimal” model parameters based on data; Choosing the goal for data mining; Objective functions; Loss functions. Exemplary techniques: Linear regression; Logistic regression; Support-vector machines. Classification via Mathematical Functions 83
Linear Discriminant Functions 85 Optimizing an Objective Function 87 An Example of Mining a Linear Discriminant from Data 88 Linear Discriminant Functions for Scoring and Ranking Instances 90 Support Vector Machines, Briefly 91
Regression via Mathematical Functions 94 Class Probability Estimation and Logistic “Regression” 96
* Logistic Regression: Some Technical Details 99 Example: Logistic Regression versus Tree Induction 102 Nonlinear Functions, Support Vector Machines, and Neural Networks 105
iv | Table of Contents
www.it-ebooks.info
Summary 108
5. Overfitting and Its Avoidance. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 111 Fundamental concepts: Generalization; Fitting and overfitting; Complexity control. Exemplary techniques: Cross-validation; Attribute selection; Tree pruning; Regularization. Generalization 111 Overfitting 113 Overfitting Examined 113
Holdout Data and Fitting Graphs 113 Overfitting in Tree Induction 116 Overfitting in Mathematical Functions 118
Example: Overfitting Linear Functions 119 * Example: Why Is Overfitting Bad? 124 From Holdout Evaluation to Cross-Validation 126 The Churn Dataset Revisited 129 Learning Curves 130 Overfitting Avoidance and Complexity Control 133
Avoiding Overfitting with Tree Induction 133 A General Method for Avoiding Overfitting 134 * Avoiding Overfitting for Parameter Optimization 136
Summary 140
6. Similarity, Neighbors, and Clusters. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 141 Fundamental concepts: Calculating similarity of objects described by data; Using similarity for prediction; Clustering as similarity-based segmentation. Exemplary techniques: Searching for similar entities; Nearest neighbor methods; Clustering methods; Distance metrics for calculating similarity. Similarity and Distance 142 Nearest-Neighbor Reasoning 144
Example: Whiskey Analytics 144 Nearest Neighbors for Predictive Modeling 146 How Many Neighbors and How Much Influence? 149 Geometric Interpretation, Overfitting, and Complexity Control 151 Issues with Nearest-Neighbor Methods 154
Some Important Technical Details Relating to Similarities and Neighbors 157 Heterogeneous Attributes 157 * Other Distance Functions 158 * Combining Functions: Calculating Scores from Neighbors 161
Clustering 163 Example: Whiskey Analytics Revisited 163 Hierarchical Clustering 164
Table of Contents | v
www.it-ebooks.info
Nearest Neighbors Revisited: Clustering Around Centroids 169 Example: Clustering Business News Stories 174 Understanding the Results of Clustering 177 * Using Supervised Learning to Generate Cluster Descriptions 179
Stepping Back: Solving a Business Problem Versus Data Exploration 182 Summary 184
7. Decision Analytic Thinking I: What Is a Good Model?. . . . . . . . . . . . . . . . . . . . . . . . . . . . 187 Fundamental concepts: Careful consideration of what is desired from data science results; Expected value as a key evaluation framework; Consideration of appropriate comparative baselines. Exemplary techniques: Various evaluation metrics; Estimating costs and benefits; Calculating expected profit; Creating baseline methods for comparison. Evaluating Classifiers 188
Plain Accuracy and Its Problems 189 The Confusion Matrix 189 Problems with Unbalanced Classes 190 Problems with Unequal Costs and Benefits 193
Generalizing Beyond Classification 193 A Key Analytical Framework: Expected Value 194
Using Expected Value to Frame Classifier Use 195 Using Expected Value to Frame Classifier Evaluation 196
Evaluation, Baseline Performance, and Implications for Investments in Data 204 Summary 207
8. Visualizing Model Performance. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 209 Fundamental concepts: Visualization of model performance under various kinds of uncertainty; Further consideration of what is desired from data mining results. Exemplary techniques: Profit curves; Cumulative response curves; Lift curves; ROC curves. Ranking Instead of Classifying 209 Profit Curves 212 ROC Graphs and Curves 214 The Area Under the ROC Curve (AUC) 219 Cumulative Response and Lift Curves 219 Example: Performance Analytics for Churn Modeling 223 Summary 231
9. Evidence and Probabilities. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 233 Fundamental concepts: Explicit evidence combination with Bayes’ Rule; Probabilistic reasoning via assumptions of conditional independence. Exemplary techniques: Naive Bayes classification; Evidence lift.
vi | Table of Contents
www.it-ebooks.info
Example: Targeting Online Consumers With Advertisements 233 Combining Evidence Probabilistically 235
Joint Probability and Independence 236 Bayes’ Rule 237
Applying Bayes’ Rule to Data Science 239 Conditional Independence and Naive Bayes 240 Advantages and Disadvantages of Naive Bayes 242
A Model of Evidence “Lift” 244 Example: Evidence Lifts from Facebook “Likes” 245
Evidence in Action: Targeting Consumers with Ads 247 Summary 247
10. Representing and Mining Text. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 249 Fundamental concepts: The importance of constructing mining-friendly data representations; Representation of text for data mining. Exemplary techniques: Bag of words representation; TFIDF calculation; N-grams; Stemming; Named entity extraction; Topic models. Why Text Is Important 250 Why Text Is Difficult 250 Representation 251
Bag of Words 252 Term Frequency 252 Measuring Sparseness: Inverse Document Frequency 254 Combining Them: TFIDF 256
Example: Jazz Musicians 256 * The Relationship of IDF to Entropy 261 Beyond Bag of Words 263
N-gram Sequences 263 Named Entity Extraction 264 Topic Models 264
Example: Mining News Stories to Predict Stock Price Movement 266 The Task 266 The Data 268 Data Preprocessing 270 Results 271
Summary 275
11. Decision Analytic Thinking II: Toward Analytical Engineering. . . . . . . . . . . . . . . . . . . . 277 Fundamental concept: Solving business problems with data science starts with analytical engineering: designing an analytical solution, based on the data, tools, and techniques available. Exemplary technique: Expected value as a framework for data science solution design.
Table of Contents | vii
www.it-ebooks.info
Targeting the Best Prospects for a Charity Mailing 278 The Expected Value Framework: Decomposing the Business Problem and
Recomposing the Solution Pieces 278 A Brief Digression on Selection Bias 280
Our Churn Example Revisited with Even More Sophistication 281 The Expected Value Framework: Structurin
Real-world Problem in U.S. Psychiatric Care PMHNPs
please follow assignment instructions and rubric that are attached, i will also post the previous assignments that will aid this assignment.
Screenshot2025-09-29at12.05.01.png
Screenshot2025-09-29at12.05.35.png
Screenshot2025-09-29at12.06.01.png
module1discussion.docx
Module2DiscussionPICO.docx
module3.docx
mod4discussion.docx
Module5Discussion.docx
Real-world Problem in U.S. Psychiatric Care
One of the most pressing current issues in U.S. psychiatric care is the profound shortage and unequal distribution of mental health providers, especially across rural and underserved urban areas. As of late 2024, over one-third of Americans, 122 million people live in federally designated Mental Health Professional Shortage Areas (HPSAs), with rural counties disproportionately affected (Mental Health America, 2025). Less than one-third of the U.S. population lives in areas with enough psychiatric providers, and more than half of the counties have none (Modi et al., 2022). These gaps delay diagnosis, limit follow-up care, and worsen symptoms, especially for serious mental diseases such as schizophrenia, bipolar disorder, and major depression. When individuals cannot access timely care, it increases psychiatric hospitalizations, emergency room visits, incarceration, and suicide.
Moreover, access problems are exacerbated by insurance inadequacies and persistent systemic fragmentation. The Mental Health Parity and Addiction Equity Act of 2008 requires equal coverage of mental and physical health services, but insurance limitations like arbitrary “medical necessity” standards, restricted provider networks, denials, and “phantom” provider listings prevent true parity (Modi et al., 2022). Patients often stop therapy due to these hurdles, especially if out-of-pocket expenditures are substantial. In addition, psychiatric services are commonly reserved from primary care, creating fragmented and poorly coordinated treatment. Patients with diabetes or heart disease may receive physical health treatment in one location but struggle to get mental health care in another. Over half of U.S. adults with mental illness go untreated, causing public health and economic issues.
PICO Question
P (Population/Patient Problem): Adults living in the U.S. Mental Health Professional Shortage Areas (HPSAs) who have untreated or undertreated mental illness
I (Intervention): Implementation of integrated telepsychiatry services
C (Comparison): Usual care (limited or in-person psychiatric referral only)
O (Outcome): Increased treatment engagement and reduced symptom severity at 6 months
PICO question: In adults with mental illness residing in U.S. Mental Health Professional Shortage Areas (P), does offering integrated telepsychiatry services through primary care clinics (I), compared with usual care (limited in-person referral only) (C), increase treatment engagement and reduce symptom severity at 6 months (O)?
Why This PICO Question Is Important to Advanced Practice Nursing
This PICO question is critically important for advanced practice registered nurses (APRN) because nurse practitioners and psychiatric nurse practitioners are poised to be frontline providers in models of integrated and technology enabled mental health care. The nationwide mental health provider deficit disproportionately impacts marginalized and rural communities, who commonly use primary care providers for psychiatric needs (Omiyefa, 2025). Telepsychiatry solutions in primary care use existing access points, clinics where patients receive physical health care to increase the APRN’s ability to provide specialized psychiatric support remotely. Telepsychiatry integration must be tested to see if it improves efficiency, reduces delays, and improves patient outcomes since primary care professionals provide most U.S. mental health treatments (Calderone et al., 2021). This concept could reduce professional isolation and increase interdisciplinary collaboration for rural and marginalized nurse practitioners by connecting them with psychiatric specialists.
Furthermore, this PICO question addresses systemic barriers beyond workforce scarcity, including insurance limitations, fragmentation of care, and stigma associated with seeking psychiatric services. Integrated telepsychiatry can reduce fragmentation by coordinating physical and mental health treatment in one location (Olawade et al., 2024). Normalizing psychiatric care in primary care may reduce stigma. Advanced practice nurses can use this research to advocate for better reimbursement policies, best practices for integrating telepsychiatry into routine care, and evidence for scaling effective programs nationwide. This PICO question highlights the APRN’s unique position in mental health equity, innovation, and quality by emphasizing measurable outcomes like treatment engagement and symptom reduction. Ultimately, answering this question empowers APRNs to expand access to psychiatric care and to directly address disparities that affect millions of Americans.
References
Calderone, J., Lopez, A., Schwenk, S., Yager, J., & Shore, J. H. (2021). Telepsychiatry and integrated primary care: setting expectations and creating an effective process for success. MHealth, 6, 29–29. https://doi.org/10.21037/mhealth.2020.02.01
Mental Health America. (2025). MHA Releases 2024 State of Mental Health in America Report | Mental Health America. Mental Health America. https://mhanational.org/news/mha-releases-2024-state-of-mental-health-in-america-report/
Modi, H., Orgera, K., & Grover, A. (2022). Exploring Barriers to Mental Health Care in the U.S. AAMC. https://www.aamc.org/about-us/mission-areas/health-care/exploring-barriers-mental-health-care-us
Olawade, A. C. D., Olawade, D. B., Ojo, I. O., Famujimi, M. E., Olawumi, T. T., & Esan, D. T. (2024). Nursing in the Digital Age: Harnessing telemedicine for enhanced patient care. Informatics and Health, 1(2), 100–110. https://doi.org/10.1016/j.infoh.2024.07.003
Omiyefa, S. (2025). Mental Healthcare Disparities in Low-Income U.S. Populations: Barriers, Policy Challenges, and Intervention Strategies. International Journal of Research Publication and Reviews, 6(3), 2277–2290. https://doi.org/10.55248/gengpi.6.0325.1186
,
2
Module 2 Discussion
Jachai Littlejohn
St. Thomas University
NUR-670-AP3
Dr. Mesa
September 4, 2025
Module 2 Discussion
Question 1
The PICO question provides psychiatric mental health nurse practitioners (PMHNPs) with a structured framework to address critical clinical issues through evidence-based practice. The PICO question defines the population, intervention, comparison, and outcome to address the pragmatic problems, such as the mental health provider shortage in underserved U.S. locations (Hallas & Lusk, 2021). It helps PMHNPs identify care gaps like psychiatric care access and devise solutions like integrated telepsychiatry. Using research, PMHNPs may improve patient outcomes, eliminate inequities, and optimize resource utilization. The PICO approach streamlines literature searches since only high-quality and recent evidence (Calderone et al., 2021; Modi et al., 2022) may guide practice, which is the PMHNP’s responsibility in delivering equitable and evidence-based care.
Furthermore, a PICO question definition allows PMHNPs to be systemic change agents. The question emphasizes the role of the PMHNP in overcoming the barriers to care, such as insurance restrictions and care fragmentation, by emphasizing the measurable outcomes, such as treatment engagement and symptom reduction. It promotes multidisciplinary collaboration, particularly in rural communities where PMHNPs are primary mental health providers. The PICO question also aids professional growth by promoting critical evaluation of evidence, making interventions viable and effective. For example, exploring telepsychiatry’s impact on underserved populations aligns with PMHNPs’ commitment to mental health equity, as noted in Omiyefa (2025). The PICO question will motivate PMHNPs to design, market, and adopt psychiatric care solutions to enhance the access and outcomes of disadvantaged populations.
Question 2
The selected PICO question— In adults with mental illness residing in U.S. Mental Health Professional Shortage Areas (P), does offering integrated telepsychiatry services through primary care clinics (I), compared with usual care (limited in-person referral only) (C), increase treatment engagement and reduce symptom severity at 6 months (O)?—serves advanced practice psychiatric nurses (APPNs) by alleviating the severe shortage of mental health providers, which impacts more than 122 million Americans (Mental Health America, 2025). The question allows APPNs to use clinic infrastructure to provide remote psychiatry by integrating it within primary care. This is crucial in rural and underserved urban regions, where over half of counties lack psychiatric physicians (Modi et al., 2022). The question helps APPNs determine whether telepsychiatry enhances treatment engagement and symptom intensity, affecting their capacity to offer timely, effective therapy. It also places APPNs as pioneers in novel care models that reduce professional isolation via specialized remote cooperation.
For patients, the PICO question addresses barriers to accessing mental health care, such as geographic isolation, insurance limitations, and stigma. By integrating psychiatric services into primary care, integrated telepsychiatry may normalize mental health treatment and reduce stigma (Olawade et al., 2024). This strategy reduces hospitalization, jail, and suicide for schizophrenia and depression patients by providing prompt treatment. The question compares telepsychiatry with the standard care (limited in-person referrals), which assesses whether the intervention enhances engagement, which is crucial since patients tend to abandon therapy because of access barriers or expenses (Modi et al., 2022). By prioritizing measurable outcomes, APNs can promote better reimbursement policies and scalable programs to serve underrepresented populations.
This PICO question is of benefit to the broader population because it can help to resolve systemic inequities in mental health care. Mental Health America (2025) reports that over half of U.S. individuals with mental illness go untreated, worsening public health and economic issues. By examining telepsychiatry’s effectiveness, the question helps APPNs design evidence-based care coordination and access strategies for underserved groups. Omiyefa (2025) states that the APPN promotes mental health equality by encouraging multidisciplinary cooperation to minimize service fragmentation and improve population-level mental health outcomes.
In conclusion, the PICO question guides PMHNPs in addressing mental health disparities through evidence-based telepsychiatry interventions. It allows APPNs to improve access, stigma, and results for underrepresented groups, improving equitable, creative psychiatric treatment while addressing structural hurdles.
References
Calderone, J., Lopez, A., Schwenk, S., Yager, J., & Shore, J. H. (2021). Telepsychiatry and integrated primary care: setting expectations and creating an effective process for success. MHealth, 6, 29–29. https://doi.org/10.21037/mhealth.2020.02.01
Hallas, D., & Lusk, P. (2021). Evidence‐based Nursing Practice. 503–511. https://doi.org/10.1002/9781119487593.ch29
Mental Health America. (2025). MHA Releases 2024 State of Mental Health in America Report | Mental Health America. Mental Health America. https://mhanational.org/news/mha-releases-2024-state-of-mental-health-in-america-report/
Modi, H., Orgera, K., & Grover, A. (2022). Exploring Barriers to Mental Health Care in the U.S. AAMC. https://www.aamc.org/about-us/mission-areas/health-care/exploring-barriers-mental-health-care-us
Olawade, A. C. D., Olawade, D. B., Ojo, I. O., Famujimi, M. E., Olawumi, T. T., & Esan, D. T. (2024). Nursing in the Digital Age: Harnessing telemedicine for enhanced patient care. Informatics and Health, 1(2), 100–110. https://doi.org/10.1016/j.infoh.2024.07.003
Omiyefa, S. (2025). Mental Healthcare Disparities in Low-Income U.S. Populations: Barriers, Policy Challenges, and Intervention Strategies. International Journal of Research Publication and Reviews, 6(3), 2277–2290. https://doi.org/10.55248/gengpi.6.0325.1186
,
4
Module 3 Discussion
Jachai Littlejohn
St. Thomas University
NUR-670-AP3
Dr. Mesa
September 11, 2025
Module 3 Discussion: Selecting Inclusion/Exclusion Criteria
PICO Question
In adults with mental illness residing in U.S. Mental Health Professional Shortage Areas (P), does offering integrated telepsychiatry services through primary care clinics (I), compared with usual care (limited in-person referral only) (C), increase treatment engagement and reduce symptom severity at 6 months (O)?
Databases Searched to Gather Evidence-Based Research
Finding the most reliable and comprehensive psychiatric, telemedicine, and integrated primary care databases is part of gathering evidence for the PICO question. Because the question involves mental health and health systems outcomes, nursing, medicine, psychology, and health informatics were examined. The key databases were PubMed/MEDLINE, CINAHL (Cumulative Index of Nursing and Allied Health Literature), PsycINFO, Cochrane Library, and Scopus. Each database ensured clinical and academically rigorous evidence for the search. PubMed/MEDLINE’s comprehensive indexing of biological and psychiatric research was crucial. Telepsychiatry, rural health inequities, and integrated care studies are on PubMed, a useful starting place. Boolean operators like “telepsychiatry AND integrated care,” “rural mental health AND outcomes,” and “primary care AND psychiatric services” limited results. To increase relevance, 2019–2025 publication dates, human subjects, peer-reviewed articles, and the English language were filtered.
Searching CINAHL for nursing focused evidence-based literature. In shortage areas, APRNs use telepsychiatry, nursing led initiatives engage patients, and care delivery paradigms change. This database offered studies. The PICO question was clinical; hence, CINAHL’s quality improvement project reports and practice-based data were applicable. Psychological and behavioral health literature illuminates patient engagement, stigma reduction, and symptom treatment, making PsycINFO beneficial. PsycINFO telepsychiatry research evaluates interventions using patient perspectives, treatment adherence, and long-term results. The database generated neglected psychiatric care systematic reviews and meta-analyses.
The Cochrane Library was searched for telepsychiatry systematic reviews and meta-analyses. Although fewer Cochrane articles directly addressed integrated models in U.S. shortage locations, it provided rigorous RCT reviews of virtual psychiatric care over regular services. These findings confirmed the intervention’s efficacy and revealed shortcomings. Scopus’ interdisciplinary health policy, informatics, and population health coverage were selected. Clinical findings, cost-effectiveness, implementation challenges, and scalability of primary care telepsychiatry were identified on Scopus. Scopus expanded the PICO question to include patient-level outcomes (engagement and symptom relief) and system-level issues (provider scarcity and access). I found hundreds of things in these databases. Pediatric research, inpatient psychiatric hospitals, and non-telehealth interventions were excluded by title and abstract review. Following eligibility filtering, 45 papers were retained for full-text review, supporting the PICO question.
Inclusion and Exclusion Criteria
Revision of the evidence needs precise inclusion and exclusion criteria to confirm the research addressed the PICO question. U.S. healthcare system, demographic comparability, intervention specificity, and recency were inclusion criteria. Exclusion criteria removed obsolete, unsuitable, or ungeneralizable PICO research. Except for 2019–2025 studies, the inclusion criteria begin with the publication date. This timeline ensured evidence matched current technology, health policy, and care paradigms. Telepsychiatry has advanced rapidly in the last five years, particularly since the COVID-19 epidemic made virtual care a standard practice (Blease et al., 2023). Including just current research captures these changes. Population relevance was another inclusion factor. Adult mental health patients, particularly those in rural or impoverished areas like Mental Health Professional Shortage, must be studied. Adult-only papers on children, adolescents, or elderly patients were removed unless their findings were generalizable. It ensured the evidence suited the PICO population. Another major inclusion criterion was intervention specificity. Only primary care or equivalent outpatient integrated telepsychiatry research was examined. We excluded publications on general telehealth use without psychiatric components or psychiatric treatments outside of primary care (such as inpatient psychiatric hospitals). This kept the results relevant for the shortage area integrated service delivery evaluation.
I selected using comparison standards. Integrated virtual services, or telepsychiatry, must be contrasted with “usual care,” mainly limited to in-person referral schemes. Telepsychiatry research without a comparison group was rejected since the PICO question requires a similar environment. The inclusion criteria required studies to measure treatment engagement (attendance, adherence, and follow-up) and symptom severity (standardized psychiatric symptom ratings, quality-of-life scores, and functional improvements). Although useful for context, provider satisfaction and cost assessments without patient outcomes were removed. Also significant was regional and systemic alignment. Because the PICO question is in the U.S. healthcare system, U.S. studies were given priority. High-income countries with similar rural health inequities and telepsychiatry infrastructures mirrored the U.S. situation (Yellowlees et al., 2020). Limited healthcare delivery model comparability excludes low-income communities.
Only peer-reviewed papers were assessed for rigor and dependability. Practice guidelines and government documents were read for context, but grey literature, opinion pieces, and editorials were omitted. Case studies with limited, non-generalizable samples or poor methodology were excluded. About 25 refined, high-quality publications directly influenced the PICO question. Included were randomized controlled trials, quasi-experimental research, systematic reviews, and implementation studies. Sharma and Devan (2021) demonstrated that integrated telepsychiatry in primary care enhanced treatment adherence over referral-only care in 2021 randomized research. Adams et al. (2022) revealed that telepsychiatry decreases symptoms as well as in-person treatment and improves accessibility for disadvantaged populations. The search technique specified inclusion and exclusion criteria to ensure the final evidence satisfied the PICO question. The study showed that primary care telepsychiatry is possible, effective, and patient-centered. They advised examining long-term sustainability, provider training, and reimbursement. Results will determine the PICO project abstract and academic poster.
References
Adams, T. C. E., Lim, C. T., & Huang, H. (2022). The practice of psychiatric e-consultation: Current state and future directions. Harvard Review of Psychiatry. https://doi.org/10.1097/hrp.0000000000000338
Blease, C., Locher, C., Leon-Carlyle, M., & Doraiswamy, M. (2020). Artificial intelligence and the future of psychiatry: Qualitative findings from a global physician survey. DIGITAL HEALTH, 6, 205520762096835. https://doi.org/10.1177/2055207620968355
O’Callaghan, E. L., McAllister, L., & Wilson, L. (2021). Telepsychiatry in rural healthcare delivery: Systematic review and policy implications. Journal of Rural Health, 37(1), 220–230. https://doi.org/10.1111/jrh.12467
Sharma, G., & Devan, K. (2021). The effectiveness of telepsychiatry: Thematic review. BJPsych Bulletin, 47(2), 1–8. https://doi.org/10.1192/bjb.2021.115
Yellowlees, P., Nakagawa, K., Pakyurek, M., Hanson, A., Elder, J., & Kales, H. C. (2020). Rapid conversion of an outpatient psychiatric clinic to a 100% virtual telepsychiatry clinic in response to COVID-19. Psychiatric Services, 71(7), 749–752. https://doi.org/10.1176/appi.ps.202000230
,
2
Module 4 Discussion
Jachai Littlejohn
St. Thomas University
NUR-670-AP3
Dr. Mesa
September 18, 2025
Creating a Search Strategy
Reliability of Evidence Using an Evidence Pyramid
Evidence-based practice requires clinicians to prioritize the strongest available evidence when making clinical decisions. The evidence pyramid visually ranks research by dependability, rigor, and bias reduction (Vatkar et al., 2025). At the base of the pyramid are background information, expert opinions, and case reports. Anecdotal evidence, lack of systematic approach, and prejudice restrict these source findings.
Moving upward, cohort studies and case-control studies provide more robust evidence by observing groups over time or retrospectively analyzing exposure and outcome relationships. These designs are nevertheless susceptible to confounding factors and lack randomization, which improves causal inference.
Higher on the pyramid are randomized controlled trials (RCTs). RCTs are the “gold standard” for intervention evaluation because randomization reduces bias and control groups strengthen causality results. RCTs have many advantages, but cost, effort, and generalizability might restrict them, particularly in rural regions with mental health needs.
At the very top of the pyramid lie systematic reviews and meta-analyses. These studies combine high-quality studies to assess an intervention’s efficacy. Systematic reviews reduce random error and boost statistical power by pooling results across populations and situations. Cochrane systematic reviews and meta-analyses on telepsychiatry are the most credible for this PICO question, followed by RCTs on integrated care models.
The pyramid encourages physicians to seek the most credible data; however, in specialized or growing domains, such as integrated telepsychiatry, RCTs, quasi-experimental studies, and implementation research may still be needed.
Search Strategy for the Literature Review
Literature Review Search Strategy
The PICO question guiding this literature search is: In adults with mental illness residing in U.S. Mental Health Professional Shortage Areas (P), does offering integrated telepsychiatry services through primary care clinics (I), compared with usual care (limited in-person referral only) (C), increase treatment engagement and reduce symptom severity at 6 months (O)?
To answer this topic, numerous databases were searched to include psychiatric, nursing, medical, and multidisciplinary research. For biological and psychological evidence, PubMed/MEDLINE was examined, whereas CINAHL focused on nursing and allied health literature relevant to integrated care delivery. PsycINFO covers psychological and behavioral health research on patient engagement, stigma, and treatment adherence. Telepsychiatry intervention systematic reviews and meta-analyses with high evidence were sought in the Cochrane Library. Finally, Scopus was used to find multidisciplinary and policy relevant scalability and health systems research.
The search used a combination of keywords and controlled vocabulary tailored to each database. Search terms included “telepsychiatry AND integrated care,” “rural mental health AND outcomes,” and “primary care AND psychiatric services.” Filters restricted findings to English-language, peer-reviewed human research from 2019 to 2025. These restrictions guaranteed that the research was recent, methodologically sound, and relevant to telepsychiatry, especially considering the fast growth of virtual care models during and after the COVID-19 epidemic.
Inclusion criteria required that studies be conducted in the U.S. healthcare system or in comparable high-income countries with similar telepsychiatry infrastructures. Interventions were limited to integrated telepsychiatry services in primary care or outpatient clinics for rural or underserved persons with mental illness. Comparisons required conventional treatment, usually in-person referral channels, and outcomes were confined to patient engagement indicators, including attendance, adherence, and follow-up, and validated mental symptom ratings. Randomized controlled trials, quasi-experimental studies, systematic reviews, and implementation research were acceptable. Studies on children or geriatric populations, unless findings were generalizable to adults, inpatient or emergency psychiatric settings, general telehealth treatments without psychiatric components, and grey literature or editorials without peer review were excluded.
The initial search retrieved hundreds of citations across the databases. Titles and abstracts were evaluated for relevance after duplicates were deleted, leaving 45 papers for full-text examination. The inclusion and exclusion criteria left 25 high-quality papers that directly influenced the PICO query. These included systematic reviews like O’Callaghan et al. (2021), on the efficacy and policy implications of telepsychiatry in rural healthcare delivery and randomized controlled trials like Sharma and Devan (2021) on how integrated telepsychiatry improves adherence and engagement compared to referral-only care. Implementation-focused studies like Yellowlees et al. (2020) showed that system-level shortages may quickly transfer psychiatric treatment to virtual modes. Adams et al. (2022) examined the changing role of psychiatric e-consultation and its ability to improve access in underserved areas, while Blease et al. (2020) examined physician perspectives on technology in psychiatry and its barriers and opportunities for telepsychiatry in primary care.
The final literature showed that integrated telepsychiatry models can improve engagement and symptom reduction in underserved populations, but implementation, provider adoption, and long-term sustainability are challenges. The retained research established a strong data basis that supports the PICO question and prepares to evaluate telepsychiatry as a solution to U.S. mental health professional shortages.
Literature Flow Diagram
References
Blease, C., Locher, C., Leon-Carlyle, M., & Doraiswamy, M. (2020). Artificial intelligence and the future of psychiatry: Qualitative findings from a global physician survey. DIGITAL HEALTH, 6, 205520762096835. https://doi.org/10.1177/2055207620968355
O’Callaghan, E. L., McAllister, L., & Wilson, L. (2021). Telepsychiatry in rural healthcare delivery: Systematic review and policy implications. Journal of Rural Health, 37(1), 220–230. https://doi.org/10.1111/jrh.12467
Sharma, G., & Devan, K. (2021). The effectiveness of telepsychiatry: thematic review. BJPsych Bulletin, 47(2), 1–8. https://doi.org/10.1192/bjb.2021.115
Thomas, Lim, C. T., & Huang, H. (2022). The Practice of Psychiatric E-Consultation: Current State and Future Directions. Harvard Review of Psychiatry. https://doi.org/10.1097/hrp.0000000000000338
Vatkar, A., Kale, S., Shyam, A., & Srivastava, S. (2025). Understanding the Levels of Evidence in Medical Research. Journal of Orthopaedic Case Reports, 15(5), 6–9. https://doi.org/10.13107/jocr.2025.v15.i05.5534
Yellowlees, P., Nakagawa, K., Pakyurek, M., Hanson, A., Elder, J., & Kales, H. C. (2020). Rapid Conversion of an Outpatient Psychiatric Clinic to a 100% Virtual Telepsychiatry Clinic in Response to COVID-19. Psychiatric Services, 71(7), 749–752. https://doi.org/10.1176/appi.ps.202000230
Records Identified Through Data Base Searching n = 300
Records Screened b
MSN5700C Advanced Practice in Primary Care I
Create a SOAP for the case attached and using the templates also attached, no AI, only 20 % plagiarism, with two or more references in APA style
SOAPanemia.docx
SOAP_NOTE_Template_20254.docx
· Semester: Fall
· Course: MSN5700C Advanced Practice in Primary Care I
· Preceptor: Rural Visit: No
· Underserved Area/Population: Yes
Patient Demographics
· Age: 42 years
· Sex: Female
· Race: Hispanic
· Insurance: PPO
· Referral: No referral
Reason for Visit: Follow-up Type of Decision-Making: Moderate Chief Complaint: “I’m here for follow-up of my anemia and fibroids; they are planning surgery.” Type of H & P: Follow-up visit
History of Present Illness (HPI): A 42-year-old Hispanic female presents for follow-up of chronic anemia related to abnormal uterine bleeding secondary to uterine fibroma. She reports history of heavy, prolonged menstrual periods for over a year, associated with fatigue and weakness. She was previously diagnosed with uterine fibroids and is scheduled for hysterectomy once her hematologic status is optimized. She continues oral iron supplementation. Denies chest pain, palpitations, or shortness of breath at rest.
Past Medical History:
· Chronic iron-deficiency anemia
· Uterine fibroma
Medications:
· Ferrous sulfate 325 mg PO daily
· Multivitamin
Physical Exam (Pertinent):
· General: Alert, oriented, in no acute distress.
· Vitals: Stable.
· Cardiovascular: Regular rate and rhythm, no murmurs.
· Respiratory: Lungs clear bilaterally.
· Abdomen: Soft, non-tender, no masses palpated.
· Extremities: No edema.
Assessment/Plan:
1. Chronic Iron-Deficiency Anemia (D50.9): Continue iron supplementation, reinforce adherence, recheck CBC in 4 weeks.
2. Uterine Leiomyoma (D25.9): Candidate for hysterectomy; optimize preoperative status with hematology clearance.
3. Menorrhagia with Regular Cycle (N92.0): Symptom management until surgical intervention.
Plan: Continue oral iron, encourage iron-rich diet, follow-up labs (CBC, iron studies). Surgery planning coordinated with gynecology. Educated patient about importance of compliance with treatment to improve hemoglobin before procedure.
Social Problems Addressed:
· Growth & Development (reproductive health)
· Income/Economic (impact on work due to fatigue, planning for surgery)
Clinical Notes (Typhon text box): Female patient with chronic anemia secondary to heavy menstrual bleeding caused by uterine fibroids. Currently managed with iron supplementation and scheduled for hysterectomy once hemoglobin is optimized. Patient reports improved energy with therapy, denies chest pain or SOB. Plan includes continued oral iron, dietary counseling, and repeat labs. Coordination with gynecology for surgical clearance.
ICD-10 Diagnosis Codes:
· D50.9 – Iron deficiency anemia, unspecified
· D25.9 – Leiomyoma of uterus, unspecified
· N92.0 – Excessive and frequent menstruation with regular cycle
CPT Codes (Billing/Labs):
· 85027 – CBC, automated
· 83540 – Iron studies
· 36415 – Venipuncture, routine
,
![A blue and black logo Description automatically generated]()
(Student Name)
Miami Regional University
Date of Encounter:
Preceptor/Clinical Site:
Clinical Instructor:
Soap Note # ____ Main Diagnosis ______________
PATIENT INFORMATION
Name:
Age:
Gender at Birth:
Gender Identity:
Source:
Allergies:
Current Medications: (including OTC and vitamins)
·
PMH:
Immunizations:
Preventive Care: Preventive Screenings: (for results already obtained before this encounter) – Pap smear: ______ – Mammogram: ______ – Colonoscopy: ______ – Lipid panel: ______ – A1C: ______ – STI screen: ______ – Depression screen (PHQ-9): ______
Surgical History:
Family History:
Social History:
Sexual Orientation:
Nutrition History:
SUBJECTIVE DATE
Chief Complaint (which must be stated between “__”)
Symptom analysis/HPI:
Clinical Tools Used (if applicable), otherwise state N/A – PHQ-9: ___ /27 – GAD-7: ___ /21 – AUDIT-C / DAST:
Review of Systems (ROS) (This section is what the patient says, therefore it should state “Pt denies… or Pt states…”)
CONSTITUTIONAL:
NEUROLOGIC:
HEENT:
RESPIRATORY:
CARDIOVASCULAR:
GASTROINTESTINAL:
GENITOURINARY:
MUSCULOSKELETAL:
SKIN:
OBJECTIVE DATA
VITAL SIGNS: LABS / DIAGNOSTICS REVIEWED (if available): – CBC: – Lipid Panel: – A1C: – EKG: – Imaging (if done):
GENERAL APPREARANCE:
NEUROLOGIC:
HEENT:
CARDIOVASCULAR:
RESPIRATORY:
GASTROINTESTINAL:
MUSKULOSKELETAL:
INTEGUMENTARY:
ASSESSMENT
Red Flags / Reasons for Escalation: – [ ] None noted – [ ] Positive suicidal ideation – [ ] Unstable vital signs – [ ] Abnormal exam requiring urgent referral
Clinical Note
(In a paragraph you should state “your encounter with your patient and your findings (including subjective and objective data)
Example: “Pt came into our clinic today c/o of ear pain. Pt states that the pain started 3 days ago after swimming. Pt denies discharge etc… On examination I noted erythema in the ear canal…, this, and that etc.)
Main Diagnosis
(Include the name of your Main Diagnosis along with its ICD10 I10. (Look at PDF example provided) Include the in-text reference/s as per APA style 6th or 7th Edition.
Differential diagnosis (minimum 3) along with the rationale behind them. (why you decide to include these differential diagnosis for this patient? What part of your assessment supports them?)
–
–
–
PLAN
Labs and Diagnostic Test to be ordered (if applicable)
· –
· –
Pharmacological treatment:
–
Non-Pharmacologic treatment:
Education (provide the most relevant ones – tailored to this specific patient – not in general)
Follow-ups/Referrals
Visit Complexity / CPT Code: _______
References (in APA Style)
Examples
Codina Leik, M. T. (2014). Family Nurse Practitioner Certification Intensive Review (2nd ed.).
ISBN 978-0-8261-3424-0
Domino, F., Baldor, R., Golding, J., Stephens, M. (2010). The 5-Minute Clinical Consult 2010
(25th ed.). Print (The 5-Minute Consult Series).
image1.png
