Overbooked and Overlooked: Machine Learning and Racial Bias in Medical Appointment Scheduling

2019 ◽  
Author(s):  
Michele Samorani ◽  
Shannon Harris ◽  
Linda Goler Blount ◽  
Haibing Lu ◽  
Michael A. Santoro
Keyword(s):  
Machine Learning ◽  
Racial Bias ◽  
Appointment Scheduling ◽  
Medical Appointment

scholarly journals Overbooked and Overlooked: Machine Learning and Racial Bias in Medical Appointment Scheduling

2021 ◽  
Author(s):  
Michele Samorani ◽  
Shannon L. Harris ◽  
Linda Goler Blount ◽  
Haibing Lu ◽  
Michael A. Santoro
Keyword(s):  
Machine Learning ◽  
Racial Disparities ◽  
Real World ◽  
Racial Disparity ◽  
Racial Bias ◽  
State Of The Art ◽  
Waiting Times ◽  
Appointment Scheduling ◽  
Racial Group ◽  
Black Patients

Problem definition: Machine learning is often employed in appointment scheduling to identify the patients with the greatest no-show risk, so as to schedule them into or right after overbooked slots. That scheduling decision maximizes the clinic performance, as measured by a weighted sum of all patients’ waiting time and the provider’s overtime and idle time. However, if a racial group is characterized by a higher no-show risk, then the patients belonging to that racial group will be scheduled into or right after overbooked slots disproportionately to the general population. Academic/Practical Relevance: That scheduling decision is problematic because patients scheduled in those slots tend to have a worse service experience than the other patients, as measured by the time they spend in the waiting room. Thus, the challenge becomes minimizing the schedule cost while avoiding racial disparities. Methodology: Motivated by the real-world case of a large specialty clinic whose black patients have a higher no-show probability than non-black patients, we analytically study racial disparity in this context. Then, we propose new objective functions that minimize both schedule cost and racial disparity and that can be readily adopted by researchers and practitioners. We develop a race-aware objective, which instead of minimizing the waiting times of all patients, minimizes the waiting times of the racial group expected to wait the longest. We also develop race-unaware methodologies that do not consider race explicitly. We validate our findings both on simulated and real-world data. Results: We demonstrate that state-of-the-art scheduling systems cause the black patients in our data set to wait about 30% longer than nonblack patients. Our race-aware methodology achieves both goals of eliminating racial disparity and obtaining a similar schedule cost as that obtained by the state-of-the-art scheduling method, whereas the race-unaware methodologies fail to obtain both efficiency and fairness. Managerial implications: Our work uncovers that the traditional objective of minimizing schedule cost may lead to unintended racial disparities. Both efficiency and fairness can be achieved by adopting a race-aware objective.

scholarly journals MODELAGEM, SIMULAÇÃO E OTIMIZAÇÃO DA DINÂMICA OPERACIONAL DO PROCESSO DE ATENDIMENTO DE UM PEQUENO POSTO DE SAÚDE

e-xacta ◽  
2013 ◽  
Vol 6 (1) ◽  
pp. 101
Author(s):  
José Airton Azevedo dos Santos ◽  
Tiago C. Dal’sotto ◽  
Wesley Schroeder
Keyword(s):  
Computer Simulation ◽  
Appointment Scheduling ◽  
Quantitative Character ◽  
Health Post ◽  
Waiting Room ◽  
Optimization Software ◽  
Simulation And Optimization ◽  
Medical Appointment ◽  
West Region ◽  
Simulation Package

<p>Este trabalho tem como objetivo analisar, através de técnicas de simulação e de otimização, a dinâmica operacional do processo de atendimento de um pequeno posto de saúde localizado na região oeste paranaense. A simulação e a otimização foram executadas utilizando o pacote de simulação Arena®, que inclui o software de otimização Optquest. A metodologia utilizada é a de modelagem através de simulação computacional, de caráter quantitativo e é caracterizada como participativa. A aplicação destas técnicas em conjunto resultaram na otimização do número de agendamento de consultas médicas do posto de saúde.</p><p>Abstract</p><p>This work aims to analyze the attending process operational dynamics of a small health post located in Paraná West Region. Another objective is connect the concepts of simulation and optimization to maximize the number of scheduling appointments for the health post, within the limits of accommodation of the waiting room. The simulation and optimization were performed using the Arena ® simulation package, which includes the OptQuest optimization software. The methodology used was the modeling through computer simulation of quantitative character and it is characterized as participative. The application of these techniques all together resulted in the optimization of the number of medical appointment scheduling of the health post</p>

scholarly journals A Racially Unbiased, Machine Learning Approach to Prediction of Mortality: Algorithm Development Study (Preprint)

2020 ◽  
Author(s):  
Angier Allen ◽  
Samson Mataraso ◽  
Anna Siefkas ◽  
Hoyt Burdick ◽  
Gregory Braden ◽  
...  
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Intensive Care ◽  
Racial Disparities ◽  
Equal Opportunity ◽  
Racial Bias ◽  
Learning Algorithm ◽  
Early Warning Score ◽  
Machine Learning Algorithm ◽  
Saps Ii

BACKGROUND Racial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups. OBJECTIVE The goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups. METHODS Bias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care–III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE). RESULTS The machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, <i>P</i>=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, <i>P</i>=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, <i>P</i>=.006 and equal opportunity difference 0.074, <i>P</i><.001, respectively). CONCLUSIONS This study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.

scholarly journals A Racially Unbiased, Machine Learning Approach to Prediction of Mortality: Algorithm Development Study

10.2196/22400 ◽  
2020 ◽  
Vol 6 (4) ◽  
pp. e22400
Author(s):  
Angier Allen ◽  
Samson Mataraso ◽  
Anna Siefkas ◽  
Hoyt Burdick ◽  
Gregory Braden ◽  
...  
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Intensive Care ◽  
Racial Disparities ◽  
Equal Opportunity ◽  
Racial Bias ◽  
Learning Algorithm ◽  
Early Warning Score ◽  
Machine Learning Algorithm ◽  
Saps Ii

Background Racial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups. Objective The goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups. Methods Bias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care–III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE). Results The machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, P=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, P=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, P=.006 and equal opportunity difference 0.074, P<.001, respectively). Conclusions This study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.

scholarly journals A Secured Medical Booking System Using Qr-Code Authentication

2019 ◽  
pp. 305-311
Author(s):  
Aderibigbe Ayodeji Azeez ◽  
Aminat Ajibola
Keyword(s):  
Health Care ◽  
Appointment Scheduling ◽  
Qr Code ◽  
Missed Appointments ◽  
Access To Health Services ◽  
Web Based ◽  
Scheduling System ◽  
Medical Appointment ◽  
Starting Point ◽  
Authentication Technique

In recent times due to the ever-increasing fast pace of life the number of missed appointments in medical institutions in Nigeria has caused problems, hence the need for a web based healthcare platform to intervene and provide seamless care for patients. Medical appointment scheduling, as the starting point of most non-urgent health care services, is undergoing major developments to support active involvement of patients. Medical appointment scheduling system lies at the intersection of providing efficiency and timely access to health services. By using the Internet as a medium, patients are given more freedom in decision making about their preferences for the appointments and have improved access. In this work a Web-based appointment scheduling system is designed to meet the needs under the current health care environment. The security of patients has been taken under consideration, QR code is been used as the e-authentication technique to protect patients’ and hospital information from unauthorized individuals. The system was developed using PHP, QR code authentication technique, VScode environment, apache and MySQL. This is to ensure that the application is robust, cheap, secured and is able to run on different platforms. The system provides the platform to facilitate the booking and management of patients’ appointment bookings. Patients can also view their appointment reports and progress. The system also provides healthcare workers an easy secured access to manage patients’ appointments, medical records and to generate relevant reports.

scholarly journals Machine Learning and Deep Learning Methods for Skin Lesion Classification and Diagnosis: A Systematic Review

Diagnostics ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 1390
Author(s):  
Mohamed A. Kassem ◽  
Khalid M. Hosny ◽  
Robertas Damaševičius ◽  
Mohamed Meselhy Eltoukhy
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Skin Lesion ◽  
Ad Hoc ◽  
Racial Bias ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Computer Aided ◽  
Aided Diagnosis

Computer-aided systems for skin lesion diagnosis is a growing area of research. Recently, researchers have shown an increasing interest in developing computer-aided diagnosis systems. This paper aims to review, synthesize and evaluate the quality of evidence for the diagnostic accuracy of computer-aided systems. This study discusses the papers published in the last five years in ScienceDirect, IEEE, and SpringerLink databases. It includes 53 articles using traditional machine learning methods and 49 articles using deep learning methods. The studies are compared based on their contributions, the methods used and the achieved results. The work identified the main challenges of evaluating skin lesion segmentation and classification methods such as small datasets, ad hoc image selection and racial bias.

Sign in / Sign up

Export Citation Format

Share Document