ABSTRACT
INTRODUCTION: Social determinants of health (SDH) are nonbiologic influencers of disease and health care disparities. This study focused on understanding the association between SDH and urology clinic "no-show" visits within a diverse urban population. METHODS: We retrospectively identified patients scheduled for urology clinic visits from October 2015 to June 2022 who completed a 10-question social needs screener. For each patient, demographic variables, and number of missed clinic appointments were abstracted. Multivariable logistic regression was performed to determine the association of unmet social needs and no-shows. RESULTS: Of 5761 unique patients seen in clinic, 5293 completed a social needs screener. Respondents were most commonly male (62.8%), Hispanic (50.3%), English-speaking (75.5%), and insured by Medicare (46.0%). Overall, 8.2%, 4.6%, and 6.1% reported 1, 2, and 3+ unmet social needs, respectively. Most patients (61.7%) had 0 no-shows; 38.3% had 1+ no-shows. Between the 0 and 1+ no-show groups, we found significant differences with respect to gender (P =.05), race/ethnicity (P = .002), preferred language (P = .006), insurance payer (P < .001), SDH status (P = .003), and total number of unmet social needs (P = .006). On multivariable analysis, patients concerned about housing quality (odds ratio [OR] = 1.50, P = .002), legal help (OR = 1.53, P = .009), and with 3+ unmet social needs (OR = 1.39, P = .006) were more likely to have 1+ no-shows. CONCLUSIONS: Unmet social needs were associated with increased no-show urology clinic visits. Routine social needs screening could identify at-risk patients who would benefit from services. This may be particularly pertinent for patients with urgent diagnoses or those requiring frequent office visits where missing appointments could impact morbidity and mortality.
Subject(s)
Appointments and Schedules , No-Show Patients , Social Determinants of Health , Humans , Male , Female , Retrospective Studies , Middle Aged , Aged , No-Show Patients/statistics & numerical data , Adult , Urology/statistics & numerical data , Ambulatory Care Facilities/statistics & numerical data , United StatesABSTRACT
OBJECTIVES: Women's attendance to cervical cancer screening (CCS) is a major concern for healthcare providers in community. This study aims to use the various algorithms that can accurately predict the most barriers of women for nonattendance to CS. DESIGN: The real-time data were collected from women presented at OPD of primary health centers (PHCs). About 1046 women's data regarding attendance and nonattendance to CCS were included. In this study, we have used three models, classification, ensemble, and deep learning models, to compare the specific accuracy and AU-ROC for predicting non-attenders for CC. RESULTS: The current model employs 22 predictors, with soft voting in ensemble models showing slightly higher specificity (96%) and sensitivity (93%) than weighted averaging. Bagging excels with the highest accuracy (98.49%), specificity (97.3%), and ideal sensitivity (100%) with an AUC of 0.99. Classification models reveal Naive Bayes with higher specificity (97%) but lower sensitivity (91%) than Logistic Regression. Random Forest and Neural Network achieve the highest accuracy (98.49%), with an AUC of 0.98. In deep learning, LSTM has an accuracy of 95.68%, higher specificity (97.60%), and lower sensitivity (93.42%) compared to other models. MLP and NN showed the highest AUC values of 0.99. CONCLUSION: Employing ensemble and deep learning models proved most effective in predicting barriers to nonattendance in cervical screening.
Subject(s)
Deep Learning , Early Detection of Cancer , Uterine Cervical Neoplasms , Humans , Female , Uterine Cervical Neoplasms/diagnosis , Adult , Middle Aged , Public Health Nursing , Mass Screening/methods , Nurses, Public Health , No-Show Patients/statistics & numerical dataABSTRACT
Objective: To assess the rate of missed postpartum appointments at a referral center for high-risk pregnancy and compare puerperal women who did and did not attend these appointments to identify related factors. Methods: This was a retrospective cross-sectional study with all women scheduled for postpartum consultations at a high-risk obstetrics service in 2018. The variables selected to compare women were personal, obstetric, and perinatal. The variables of interest were obtained from the hospital's electronic medical records. Statistical analyses were performed using the Chi-square, Fisher's exact, or Mann-Whitney tests. For the variable of the interbirth interval, a receiver operating characteristic curve (ROC) was used to best discriminate whether or not patients attended the postpartum consultation. The significance level for the statistical tests was 5%. Results: A total of 1,629 women scheduled for postpartum consultations in 2018 were included. The rate of missing the postpartum consultation was 34.8%. A shorter interbirth interval (p = 0.039), previous use of psychoactive substances (p = 0.027), current or former smoking (p = 0.003), and multiparity (p < 0.001) were associated with non-attendance. Conclusion: This study showed a high rate of postpartum appointment non-attendance. This is particularly relevant because it was demonstrated in a high-risk obstetric service linked to clinical severity or social vulnerability cases. This highlights the need for new approaches to puerperal women before hospital discharge and new tools to increase adherence to postpartum consultations, especially for multiparous women.
Subject(s)
Pregnancy, High-Risk , Humans , Female , Cross-Sectional Studies , Retrospective Studies , Adult , Pregnancy , Postpartum Period , Referral and Consultation/statistics & numerical data , No-Show Patients/statistics & numerical data , Postnatal Care/statistics & numerical data , Young Adult , Risk FactorsABSTRACT
The use of telemedicine has rapidly expanded in the wake of the COVID pandemic, but its effect on patient attendance remains unknown for different clinicians. This study compared traditional in-clinic visits with telehealth visits by retrospectively reviewing all scheduled orthopaedic clinic visits. Results demonstrated lower rates of cancellations in patients scheduled for telehealth visits as compared to in-clinic visits, during the initial COVID pandemic. In general, physicians can expect a lower cancellation rate than non-physician practitioners.
Subject(s)
COVID-19 , Orthopedics , Telemedicine , Humans , Telemedicine/statistics & numerical data , COVID-19/epidemiology , Retrospective Studies , Orthopedics/statistics & numerical data , Appointments and Schedules , Female , Male , SARS-CoV-2 , No-Show Patients/statistics & numerical data , Middle Aged , Pandemics , Adult , MissouriABSTRACT
OBJECTIVE: To determine if patient factors related to ethnicity, socioeconomic status (SES), medical comorbidities, or appointment characteristics increase the risk of missing an initial adult otolaryngology appointment. METHODS: This study is a retrospective case control study at Boston Medical Center (BMC) in Boston, Massachusetts, that took place in 2019. Patient demographic and medical comorbidity data as well as appointment characteristic data were collected and compared between those that attended their initial otolaryngology appointment versus those who missed their initial appointment. Chi-square and ANOVA tests were used to calculate differences between attendance outcomes. Multivariate analysis was used to compare the odds of missing an appointment based on various patient- and appointment-related factors. RESULTS: Patients who were more likely to miss their appointments were more often female, of lower education, disabled, not employed, Black or Hispanic, and Spanish-speaking. Spring and Fall appointments were more likely to be missed. When a multivariate regression was conducted to control for social determinants of health (SDOH) such as race, insurance status, employment, and education status, the odds of females, Spanish-speaking, students, and disabled patients missing their appointment were no longer statistically significant. CONCLUSION: A majority of patients at BMC come from lower SES backgrounds and have multiple medical comorbidities. Those who reside closer to BMC, often areas of lower average income, had higher rates of missed appointments. Interventions such as decreasing lag time, providing handicap-accessible free transportation, and increasing accessibility of telemedicine for patients could help improve attendance rates at BMC. LEVEL OF EVIDENCE: IV Laryngoscope, 134:4003-4010, 2024.
Subject(s)
Appointments and Schedules , Otolaryngology , Safety-net Providers , Humans , Female , Male , Retrospective Studies , Safety-net Providers/statistics & numerical data , Middle Aged , Boston , Adult , Case-Control Studies , Otolaryngology/statistics & numerical data , No-Show Patients/statistics & numerical data , Aged , Hospitals, Urban/statistics & numerical dataABSTRACT
The coronavirus disease of 2019 (COVID-19) pandemic exacerbated barriers to care for people living with human immunodeficiency virus (HIV) (PLWH). The quick uptake of telemedicine in the outpatient setting provided promise for care continuity. In this study, we compared appointment and laboratory no-show rates in an urban outpatient HIV clinic during three time periods: (1) Pre-COVID-19: 9/15/2019-3/14/2020 (predominately in-person), (2) "Early" COVID-19: 3/15/2020-9/14/2020 (predominately telemedicine), and (3) "Later" COVID-19: 9/15/2020-3/14/2021 (mixed in-person/telemedicine). Multivariable logistic regression models evaluated the two study hypotheses: (i) equivalence of Period 2 with Period 1 and of Period 3 with Period 1 and (ii) improved outcomes with telemedicine over in-person visits. No-show rates were 1% in Period 1, 4% in Period 2, and 18% in Period 3. Compared to the pre-pandemic period, individuals had a higher rate of appointment no-shows during Period 2 [OR (90% CI): 7.67 (2.68, 21.93)] and 3 [OR (90% CI): 30.91 (12.83 to 75.06). During the total study period, those with telemedicine appointments were less likely to no-show than those with in-person appointments [OR (95% CI): 0.36 (0.16-0.80), p = 0.012]. There was no statistical difference between telemedicine and in-person appointments for laboratory completion rates. Our study failed to prove that no-show rates before and during the pandemic were similar; in fact, no-show rates were higher during both the early and later pandemic. Overall, telemedicine was associated with lower no-show rates compared to in-person appointments. In future pandemics, telemedicine may be a valuable component to maintain care in PLWH.
Subject(s)
COVID-19 , HIV Infections , SARS-CoV-2 , Telemedicine , Humans , COVID-19/epidemiology , HIV Infections/epidemiology , Female , Male , Middle Aged , Adult , Pandemics , No-Show Patients/statistics & numerical data , Appointments and Schedules , Continuity of Patient Care/organization & administration , Ambulatory Care FacilitiesABSTRACT
INTRODUCTION: Missed appointments also known as no-shows adversely affect clinical outcomes, clinic efficiency, and quality of care and have been attributed to barriers such as work schedule conflicts and lack of transportation. The widespread telemedicine implementation and adoption that has occurred as a consequence of the COVID-19 pandemic has the potential to address these barriers and improve missed appointment rates. This study aims to analyze the relationship between telemedicine and missed appointments. METHODS: This retrospective cohort study used electronic health records data from a safety-net academic health center with federally qualified clinics (March 2020-December 2022). Bivariate and multivariable generalized estimating equations were used to analyze the relationship between no-show and appointment type (in-person versus telemedicine appointment). Stratified adjusted regression analyses were used to calculate the average change in the marginal effect of telemedicine appointments on no-shows across covariates. The data were analyzed from September 2023 to October 2023. RESULTS: Hispanic patients accounted for 60% of the 474,212 appointments, followed by non-Hispanic White (22.5%), non-Hispanic Black (13.3%), Asian (2.7%), Native American (1%), and other race/ethnicity patients (0.6%). The no-show rate for telemedicine appointments was 12% compared with 25% for in-person appointments. Multivariable analysis showed that telemedicine appointment was associated with a decreased likelihood of no-show compared with in-person appointments (OR=0.40, 95% CI=0.40, 0.41). The average change in the marginal effect of telemedicine appointments on the reduction of no-shows across race/ethnicity was greatest for Native American and non-Hispanic Black patients. CONCLUSIONS: Telemedicine appointments were associated with a decreased likelihood of no-shows, and the protective effect of telemedicine appointments on missed appointments was greatest for underserved groups. Strategies to increase telemedicine uptake, especially for underserved groups, are critical.
Subject(s)
Appointments and Schedules , COVID-19 , No-Show Patients , Telemedicine , Humans , Telemedicine/statistics & numerical data , Retrospective Studies , Female , Male , COVID-19/epidemiology , Middle Aged , Adult , No-Show Patients/statistics & numerical data , Healthcare Disparities/statistics & numerical data , SARS-CoV-2 , AgedABSTRACT
PURPOSE: To assess the efficacy of electronic health record (EHR) messaging for re-engaging patients with ophthalmology care after a missed appointment. DESIGN: Prospective, randomized clinical trial. METHODS: The study setting was an academic ophthalmology department. The patient population comprised of return patients age 18 years or older with an appointment "no show," or missed appointment. Over 2 phases of recruitment, 362 patients with an active patient portal in the EHR were selected consecutively each business day. Patients were randomized using a web-based tool to receive a reminder to reschedule via a standard mailed letter only (control) or the mailed letter plus an electronic message through the EHR within 1 business day of the missed appointment (intervention). Reengagement with eye care was defined as attendance of a rescheduled appointment within 30 days of the no-show visit. Patient charts were reviewed for demographic and clinical data. RESULTS: The average age of recruited patients was 59.9 years, just under half of the sample was male (42.5%, 154/362), and most patients were White (56.9%, 206/362) or Black (36.2%, 131/362). Patients were most commonly recruited from the retina service (39.2%, 142/362) followed by the glaucoma service (29.3%, 106/362). Many patients in this study had previous no-show appointments, with an average no-show rate of 18.8% out of all scheduled visits across our health system. In total, 22.2% (42/189) of patients in the intervention group attended a follow-up appointment within 30 days of their no-show visit compared to 11.6% (20/173) of the control group (OR, 2.186; 95% CI, 1.225-3.898; P = .008). When including only the 74 patients in the intervention group who read the intervention message in the patient portal, 28.4% (21/74) attended a follow-up compared to 11.6% (20/173) of the control group (P = .001). CONCLUSIONS: EHR-based reminder messages sent within a business day of a missed appointment may promote re-engagement in ophthalmology care after appointment no-show.
Subject(s)
Appointments and Schedules , No-Show Patients , Ophthalmology , Patient Portals , Reminder Systems , Humans , Male , Middle Aged , Female , Prospective Studies , Ophthalmology/organization & administration , No-Show Patients/statistics & numerical data , Aged , Adult , Patient Compliance/statistics & numerical data , Electronic Health RecordsABSTRACT
BACKGROUND: Appointment non-attendance has clinical, operational, and financial implications for patients and health systems. How telehealth services are associated with non-attendance in primary care is not well-described, nor are patient characteristics associated with telehealth non-attendance. OBJECTIVE: We sought to compare primary care non-attendance for telehealth versus in-person visits and describe patient characteristics associated with telehealth non-attendance. DESIGN: An observational study of electronic health record data. PARTICIPANTS: Patients with primary care encounters at 23 adult primary care clinics at a large, urban public healthcare system from November 1, 2019, to August 31, 2021. MAIN MEASURES: We analyzed non-attendance by modality (telephone, video, in-person) during three time periods representing different availability of telehealth using hierarchal multiple logistic regression to control for patient demographics and variation within patients and clinics. We stratified by modality and used hierarchal multiple logistic regression to assess for associations between patient characteristics and non-attendance in each modality. KEY RESULTS: There were 1,219,781 scheduled adult primary care visits by 329,461 unique patients: 754,149 (61.8%) in-person, 439,295 (36.0%) telephonic, and 26,337 (2.2%) video visits. Non-attendance for telephone visits was initially higher than that for in-person visits (adjusted odds ratio 1.04 [95% CI 1.02, 1.07]) during the early telehealth availability period, but decreased later (0.82 [0.81, 0.83]). Non-attendance for video visits was higher than for in-person visits during the early (4.37 [2.74, 6.97]) and later (2.02 [1.95, 2.08]) periods. Telephone visits had fewer differences in non-attendance by demographics; video visits were associated with increased non-attendance for patients who were older, male, had a primary language other than English or Spanish, and had public or no insurance. CONCLUSIONS: Telephonic visits may improve access to care and be more easily adoptable among diverse populations. Further attention to implementation may be needed to avoid impeding access to care for certain populations using video visits.
Subject(s)
No-Show Patients , Telemedicine , Adult , Humans , Language , Odds Ratio , Primary Health Care , No-Show Patients/statistics & numerical dataABSTRACT
BACKGROUND: Appointment no-show and early dropout from treatment represent major challenges in outpatient substance use disorder treatment, adversely affecting clinical outcomes and health care productivity. In this quasi-experimental study, we examined how a brief reminder intervention for new patients before their first appointment affected treatment participation and retention. No-shows (not attending any sessions) and dropouts (discontinuation of initiated treatment because of three consecutively missed appointments) were compared between a period with pre-admission telephone calls (intervention) and a period without such reminders (non-intervention). METHODS: Participants were all eligible patients (N = 262) admitted to a Norwegian specialist clinic for substance use disorder treatment. We used the Chi-square test for the no-show analysis. Of the eligible patients, 147 were included in a subsequent dropout analysis. We used the number of visits up to 10 appointments as a measure for time to event. Group differences were analyzed using a Kaplan-Meier plot and the log-rank test. To control for relevant sociodemographic variables, as well as substance use and mental distress severity, we used Cox regression. RESULTS: No-show rates did not differ between the two periods (12% for non-intervention vs. 14% for intervention; χ2 = 0.20, p = 0.653). Of those consenting to participate in the dropout analysis (n = 147), 28 (19%) discontinued treatment within the time frame of 10 appointments, with no differences between the two periods (log-rank test = 0.328, p = 0.567). Controlling for baseline characteristics did not alter this finding. In fact, of the registered covariates at baseline, only higher education level was associated with attrition, linked to a reduced risk for dropout (hazard ratio = 0.85, 95% CI = 0.74-0.98, p = 0.025). CONCLUSION: These findings do not provide support for the systematic use of a brief pre-admission telephone reminder in the current treatment setting. TRIAL REGISTRATION: The study was retrospectively registered 13 Jan 2021 at ClinicalTrials.gov, NCT04707599.
Subject(s)
Reminder Systems , Substance-Related Disorders , Telephone , Ambulatory Care Facilities , Appointments and Schedules , Humans , No-Show Patients/statistics & numerical data , Norway , Patient Dropouts/statistics & numerical data , Substance-Related Disorders/therapyABSTRACT
INTRODUCTION: The cancer burden in the Middle East is high and growing. Colorectal cancer (CRC) is the second most common cancer for both men and women in the UAE. Although early diagnosis of malignancy reduces morbidity and increases the survival rates, non-attendance of gastroenterology (GI) endoscopic procedures is a significant global problem, which can lead to delay in cancer diagnosis and treatment. Several factors have been found to contribute to non-attendance behavior, including socioeconomic, cultural, and organizational related barriers. The purpose of this study was to identify factors contributing to non-attendance behavior among outpatients scheduled for GI endoscopic procedures in a tertiary hospital in the United Arab Emirates. We conclude with recommendations that can help in reducing the rate of patient no-shows for GI endoscopic procedures in the region. METHODS: In a tertiary medical center in the Middle East, we surveyed patients who did not attend their scheduled GI endoscopic procedures over a period of one year. The questionnaire sought to identify possible reasons for patient's non-attendance. Descriptive measures including means, standard deviation, frequencies, and percentages were used to analyze the demographic characteristics of the study participants. The chi-square test was performed to analyze gender differences. RESULTS: Of 314 outpatients who met study inclusion criteria, 168 agreed to participate (53.5% response rate). The majority of participants were women (n=96, 60.4 %), aged 18 to 73, with a mean of 42 years. The largest age group was between 35 and 44 (n=46, 28.9 %). Approximately equal numbers of non-attendance appointments were scheduled for combined colonoscopy and upper endoscopy (36.3 %), colonoscopy alone (31.3 %), or upper endoscopy alone (31.3 %). The most common causes for cancellation or non-attendance included concerns about the appointment (35.5%), inconvenient timing of the appointment (27.9%) and changes in medical status (26.4%). Gender differences were noted for non-attendance behaviors, with women significantly more likely than men to report feelings of embarrassment (Chi-square 6.261, df=1, p=.012). CONCLUSION: Our study has identified several barriers to patient attendance of endoscopic procedures, as well as opportunities to reduce the rate of patient no-shows, including patient education, scheduling options, and protocols to minimize discomfort and misconceptions around GI endoscopic procedures, particularly accommodating for same gender endoscopists, with the ultimate goal of increasing early cancer screening and prevention.
Subject(s)
Colorectal Neoplasms/diagnosis , Early Detection of Cancer/statistics & numerical data , Endoscopy, Gastrointestinal/statistics & numerical data , No-Show Patients/statistics & numerical data , Patient Acceptance of Health Care/psychology , Adolescent , Adult , Aged , Colonoscopy/psychology , Colonoscopy/statistics & numerical data , Early Detection of Cancer/psychology , Endoscopy, Gastrointestinal/psychology , Female , Humans , Male , Middle Aged , No-Show Patients/psychology , Outpatients/psychology , Outpatients/statistics & numerical data , Tertiary Care Centers , United Arab Emirates , Young AdultABSTRACT
Importance: Black patients with hypertension often have the lowest rates of blood pressure (BP) control in clinical settings. It is unknown to what extent variation in health care processes explains this disparity. Objective: To assess whether and to what extent treatment intensification, scheduled follow-up interval, and missed visits are associated with racial and ethnic disparities in BP control. Design, Setting, and Participants: In this cohort study, nested logistic regression models were used to estimate the likelihood of BP control (defined as a systolic BP [SBP] level <140 mm Hg) by race and ethnicity, and a structural equation model was used to assess the association of treatment intensification, scheduled follow-up interval, and missed visits with racial and ethnic disparities in BP control. The study included 16â¯114 adults aged 20 years or older with hypertension and elevated BP (defined as an SBP level ≥140 mm Hg) during at least 1 clinic visit between January 1, 2015, and November 15, 2017. A total of 11 safety-net clinics within the San Francisco Health Network participated in the study. Data were analyzed from November 2019 to October 2020. Main Outcomes and Measures: Blood pressure control was assessed using the patient's most recent BP measurement as of November 15, 2017. Treatment intensification was calculated using the standard-based method, scored on a scale from -1.0 to 1.0, with -1.0 being the least amount of intensification and 1.0 being the most. Scheduled follow-up interval was defined as the mean number of days to the next scheduled visit after an elevated BP measurement. Missed visits measured the number of patients who did not show up for visits during the 4 weeks after an elevated BP measurement. Results: Among 16 114 adults with hypertension, the mean (SD) age was 58.6 (12.1) years, and 8098 patients (50.3%) were female. A total of 4658 patients (28.9%) were Asian, 3743 (23.2%) were Black, 3694 (22.9%) were Latinx, 2906 (18.0%) were White, and 1113 (6.9%) were of other races or ethnicities (including American Indian or Alaska Native [77 patients (0.4%)], Native Hawaiian or Pacific Islander [217 patients (1.3%)], and unknown [819 patients (5.1%)]). Compared with patients from all racial and ethnic groups, Black patients had lower treatment intensification scores (mean [SD], -0.33 [0.26] vs -0.29 [0.25]; ß = -0.03, P < .001) and missed more visits (mean [SD], 0.8 [1.5] visits vs 0.4 [1.1] visits; ß = 0.35; P < .001). In contrast, Asian patients had higher treatment intensification scores (mean [SD], -0.26 [0.23]; ß = 0.02; P < .001) and fewer missed visits (mean [SD], 0.2 [0.7] visits; ß = -0.20; P < .001). Black patients were less likely (odds ratio [OR], 0.82; 95% CI, 0.75-0.89; P < .001) and Asian patients were more likely (OR, 1.13; 95% CI, 1.02-1.25; P < .001) to achieve BP control than patients from all racial or ethnic groups. Treatment intensification and missed visits accounted for 21% and 14%, respectively, of the total difference in BP control among Black patients and 26% and 13% of the difference among Asian patients. Conclusions and Relevance: This study's findings suggest that racial and ethnic inequities in treatment intensification may be associated with more than 20% of observed racial or ethnic disparities in BP control, and racial and ethnic differences in visit attendance may also play a role. Ensuring more equitable provision of treatment intensification could be a beneficial health care strategy to reduce racial and ethnic disparities in BP control.
Subject(s)
Aftercare/statistics & numerical data , Blood Pressure , Healthcare Disparities/ethnology , Hypertension/drug therapy , No-Show Patients/statistics & numerical data , Adult , Black or African American/statistics & numerical data , Aged , Aged, 80 and over , Asian/statistics & numerical data , Cohort Studies , Female , Hispanic or Latino/statistics & numerical data , Humans , Logistic Models , Male , Middle Aged , Safety-net Providers , Treatment Outcome , White People/statistics & numerical data , Young AdultABSTRACT
Public health and its related facilities are crucial for thriving cities and societies. The optimum utilization of health resources saves money and time, but above all, it saves precious lives. It has become even more evident in the present as the pandemic has overstretched the existing medical resources. Specific to patient appointment scheduling, the casual attitude of missing medical appointments (no-show-ups) may cause severe damage to a patient's health. In this paper, with the help of machine learning, we analyze six million plus patient appointment records to predict a patient's behaviors/characteristics by using ten different machine learning algorithms. For this purpose, we first extracted meaningful features from raw data using data cleaning. We applied Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling Method (Adasyn), and random undersampling (RUS) to balance our data. After balancing, we applied ten different machine learning algorithms, namely, random forest classifier, decision tree, logistic regression, XG Boost, gradient boosting, Adaboost Classifier, Naive Bayes, stochastic gradient descent, multilayer perceptron, and Support Vector Machine. We analyzed these results with the help of six different metrics, i.e., recall, accuracy, precision, F1-score, area under the curve, and mean square error. Our study has achieved 94% recall, 86% accuracy, 83% precision, 87% F1-score, 92% area under the curve, and 0.106 minimum mean square error. Effectiveness of presented data cleaning and feature selection is confirmed by better results in all training algorithms. Notably, recall is greater than 75%, accuracy is greater than 73%, F1-score is more significant than 75%, MSE is lesser than 0.26, and AUC is greater than 74%. The research shows that instead of individual features, combining different features helps make better predictions of a patient's appointment status.
Subject(s)
Algorithms , Appointments and Schedules , Machine Learning , No-Show Patients/statistics & numerical data , Area Under Curve , Bayes Theorem , Computational Biology , Data Interpretation, Statistical , Databases, Factual , Decision Trees , Humans , Logistic Models , Neural Networks, Computer , Stochastic Processes , Support Vector MachineABSTRACT
OBJECTIVES: Nonattendance of appointments in outpatient clinics results in many adverse effects including inefficient use of valuable resources, wasted capacity, increased delays, and gaps in patient care. This research presents a modeling framework for designing positive incentives aimed at decreasing patient nonattendance. METHODS: We develop a partially observable Markov decision process (POMDP) model to identify optimal adaptive reinforcement schedules with which financial incentives are disbursed. The POMDP model is conceptually motivated based on contingency management evidence and practices. We compare the expected net profit and trade-offs for a clinic using data from the literature for a base case and the optimal positive incentive design resulting from the POMDP model. To accommodate a less technical audience, we summarize guidelines for reinforcement schedules from a simplified Markov decision process model. RESULTS: The results of the POMDP model show that a clinic can increase its net profit per recurrent patient while simultaneously increasing patient attendance. An increase in net profit of 6.10% was observed compared with a policy with no positive incentive implemented. Underlying this net profit increase is a favorable trade-off for a clinic in investing in a targeted contingency management-based positive incentive structure and an increase in patient attendance rates. CONCLUSIONS: Through a strategic positive incentive design, the POMDP model results show that principles from contingency management can support decreasing nonattendance rates and improving outpatient clinic efficiency of its appointment capacity, and improved clinic efficiency can offset the costs of contingency management.
Subject(s)
Appointments and Schedules , Models, Statistical , Motivation , No-Show Patients/statistics & numerical data , Ambulatory Care Facilities , Humans , Time FactorsABSTRACT
Few studies have directly targeted nonparticipants in colorectal cancer screening to identify effective engagement strategies. We undertook a randomized controlled trial that targeted nonparticipants in a previous trial of average-risk subjects which compared participation rates for mailed invitations offering a fecal test, a blood test or a choice of either. Nonparticipants (n = 899) were randomized to be offered a kit containing a fecal immunochemical test (FIT), directions on how to arrange a blood DNA test, or the option of doing either. Screening participation was assessed 12 weeks after the offer. To assess the cognitive and attitudinal variables related to participation and invitee choice, invitees were surveyed after 12 weeks, and associations were investigated using multinomial logistic regression. Participation rates were similar between groups (P = 0.88): 12.0% for FIT (35/292), 13.3% for the blood test (39/293), and 13.4% for choice (39/290). Within the choice group, participation was significantly higher with FIT (9.7%, 28/290) compared with the blood test (3.8%, 11/290, P = 0.005). The only variable significantly associated with participation was socioeconomic status when offered FIT, and age when offered choice but there was none when offered the blood test. Survey respondents indicated that convenience, time-saving, comfort, and familiarity were major influences on participation. There was no clear advantage between a fecal test, blood test, or choice of test although, when given a choice, the fecal test was preferred. Differences in variables associated with participation according to invitation strategy warrant consideration when deciding upon an invitation strategy for screening nonparticipants. PREVENTION RELEVANCE: This trial of screening for those at average risk for colorectal cancer targeted past fecal-test nonparticipants and compared participation rates for mailed invitations offering a fecal test, blood test, or choice of either. Although there was no clear advantage between strategies, factors associated with participation differed between each strategy.
Subject(s)
Colorectal Neoplasms/diagnosis , Early Detection of Cancer , No-Show Patients , Patient Participation/methods , Aged , Australia/epidemiology , Choice Behavior , Colonoscopy/psychology , Colonoscopy/statistics & numerical data , Colorectal Neoplasms/epidemiology , Colorectal Neoplasms/prevention & control , Early Detection of Cancer/methods , Early Detection of Cancer/psychology , Early Detection of Cancer/statistics & numerical data , Female , Health Services Needs and Demand/statistics & numerical data , Humans , Male , Mass Screening , Middle Aged , No-Show Patients/psychology , No-Show Patients/statistics & numerical data , Occult Blood , Refusal to Participate/psychology , Refusal to Participate/statistics & numerical dataABSTRACT
BACKGROUND: Fear of contracting coronavirus disease 2019 may be the latest addition to the barriers to clinic attendance. This study aimed to examine the impact of coronavirus disease 2019 and other variables on non-attendance rate at an out-patient clinic. METHODS: Clinic attendance at the Department of Otolaryngology and Head and Neck Surgery, Waikato Hospital, New Zealand, was assessed. For each appointment, the impact of coronavirus disease 2019 and other variables on non-attendance rate were analysed. RESULTS: In total, 1963 appointments were scheduled, with 194 non-attendances (9.9 per cent). Patients who had their appointments confirmed beforehand were 10.0 times more likely to attend their appointment. Sex, socioeconomic status, ethnicity and age were found to impact non-attendance rate. CONCLUSION: In New Zealand, coronavirus disease 2019 does not appear to be a barrier to out-patient clinic appointment attendance. The patient's age, sex, ethnicity, socioeconomic status and prior appointment confirmation were found to influence clinic attendance.
Subject(s)
Ambulatory Care , COVID-19 , No-Show Patients/statistics & numerical data , Otorhinolaryngologic Diseases , Adolescent , Adult , Aged , Demography , Female , Humans , Male , Middle Aged , New Zealand , Retrospective Studies , Weather , Young AdultABSTRACT
ABSTRACT: This study explored demographic and clinical features, plus clinical outcomes, in a smoke-free acute partial hospital (PH) among current smokers, former smokers, and those who had never smoked (nonsmokers). Compared with nonsmokers, current smokers were younger and more likely to be unmarried and unpartnered, unemployed, or receiving disability benefits. They had more prior inpatient (IP) and PH episodes. They also had more problems with interpersonal relationships, mood lability, psychosis, and substance use. Compared with nonsmokers, current smokers were more likely to miss PH treatment days and drop out. They also had longer time to readmission to PH or IP. Former smokers resembled nonsmokers, except that former smokers also had a high rate of dropout. Changes in symptoms and functioning for patients who completed PH were the same among all groups. In an acute PH setting, smoking is a marker for psychiatric and psychosocial impairment plus treatment interruption.
Subject(s)
Cigarette Smoking , Day Care, Medical/statistics & numerical data , Hospitals, Psychiatric/statistics & numerical data , Mental Disorders/therapy , No-Show Patients/statistics & numerical data , Outcome Assessment, Health Care/statistics & numerical data , Patient Dropouts/statistics & numerical data , Socioeconomic Factors , Acute Disease , Adult , Anxiety Disorders/epidemiology , Anxiety Disorders/therapy , Bipolar Disorder/epidemiology , Bipolar Disorder/therapy , Cigarette Smoking/epidemiology , Comorbidity , Depressive Disorder/epidemiology , Depressive Disorder/therapy , Employment/statistics & numerical data , Female , Humans , Male , Marital Status/statistics & numerical data , Mental Disorders/epidemiology , Middle Aged , Residence Characteristics/statistics & numerical data , Schizophrenia/epidemiology , Schizophrenia/therapy , Sex FactorsABSTRACT
BACKGROUND: Non-adherence is an important aspect of transplantation that affect outcomes. This study aims to investigate the impact of non-adherence to laboratory and clinic appointments on medication non-adherence and outcomes in kidney transplant (KT) recipients. METHODS: We analyzed KT recipients between 2005-14 with a detailed review of the medical records for non-adherence to laboratory and clinic appointments, as well as medication regimens. Baseline characteristics and clinical outcomes were compared between adherent and non-adherent groups. RESULTS: A total of 1413 KT recipients were included: 754 who were adherent and 659 who were non-adherent. Non-adherent recipients tend to be younger, African American, and have private insurance. Adherent patients tend to have a history of DM, heart disease, and receive an ECD kidney. Non-adherence to appointments was a strong predictor of medication non-adherence (OR 3.1), acute rejection (OR 1.4), and subsequent rejection episodes (OR 3.3 and 8.1 respectively for ≥ 1 and ≥ 2 rejection episodes). Subset analysis of patients who had early non-adherence within 1-year post-transplant showed predominance of younger, African American patients. The same patients had higher prevalence of medication non-compliance, overall and ≥ 1-year post-transplant, and mean number of readmissions. Kaplan-Meier analysis showed a trend towards lower graft survival in this group. CONCLUSIONS: Early non-adherence to laboratory and clinic appointments is a strong predictor of late medication non-adherence, acute rejection, and graft loss. Targeting patients that demonstrate early non-adherence to appointments with focused interventions may help improve kidney transplant outcomes in this high risk group.
Subject(s)
Kidney Transplantation/statistics & numerical data , Medication Adherence/statistics & numerical data , No-Show Patients/statistics & numerical data , Treatment Outcome , Adult , Aged , Appointments and Schedules , Female , Graft Survival , Humans , Kidney , Male , Middle Aged , Socioeconomic FactorsABSTRACT
OBJECTIVE: The objective of this study was to examine primary factors that may predict patients' failure to show at initial physical therapist evaluation in an orthopedic and sports outpatient setting. METHODS: A retrospective analysis of patients' demographic data for physical therapist evaluations between January 2013 and April 2015 was performed. A binary logistic regression model was used to evaluate the odds of a no-show at evaluation. Demographic variables of age, employment status, days waited for the appointment, payer source, and distance traveled to the clinic were analyzed. Independent variables were considered significant if the 95% CIs of the odds ratios (ORs) did not include 1.0. RESULTS: A total of 6971 patients were included in the final analysis, with 10% (n = 698) of the scheduled patients having a no-show event for their initial evaluation. The following factors increased the odds of patients having a no-show event: days to appointment (OR = 1.058; 95% CI = 1.042-1.074), unemployment status (OR = 1.96; 95% CI = 1.41-2.73), unknown employment status (OR = 3.22; 95% CI = 1.12-8.69), Medicaid insurance (OR = 4.87; 95% CI = 3.43-6.93), Medicare insurance (OR = 2.22; 95% CI = 1.10-4.49), unknown payer source (OR = 262.84; 95% CI = 188.72-366.08), and distance traveled 8 or more kilometers (OR = 1.31; 95% CI = 1.01-1.70). Female sex (OR = 0.73; 95% CI = 0.57-0.95) and age 40 years or older (OR = 0.44; 95% CI = 0.33-0.60) decreased the odds of a no-show event. CONCLUSIONS: Results from this study indicate there may be some demographic factors that are predictive of patients failing to attend their first physical therapist visit. IMPACT: Understanding the predictive factors and identifying potential opportunities for improvements in scheduling processes might help decrease the number of patients failing to show for their initial physical therapy appointment, with the ultimate goal of positively influencing patient outcomes.
Subject(s)
No-Show Patients/statistics & numerical data , Physical Therapy Modalities , Adult , Ambulatory Care , Female , Humans , Male , Middle Aged , Retrospective StudiesABSTRACT
AIMS: We aimed to determine the patient and screening-level factors that are associated with non-attendance in the Irish National Diabetic Retinal screening programme (Diabetic RetinaScreen). To accomplish this, we modelled a selection of predictors derived from the historical screening records of patients with diabetes. METHODS: In this cohort study, appointment data from the national diabetic retinopathy screening programme (RetinaScreen) were extracted and augmented using publicly available meteorological and geospatial data. A total of 653,969 appointments from 158,655 patients were included for analysis. Mixed-effects models (univariable and multivariable) were used to estimate the influence of several variables on non-attendance to screening appointments. RESULTS: All variables considered for analysis were statistically significant. Variables of note, with meaningful effect, were age (OR: 1.23 per decade away from 70; 95% CI: [1.22-1.24]), type 2 diabetes (OR: 1.10; 95% CI: [1.06-1.14]) and socio-economic deprivation (OR: 1.12; 95% CI: [1.09-1.16]). A majority (52%) of missed appointments were from patients who had missed three or more appointments. CONCLUSIONS: This study is the first to outline factors that are associated with non-attendance within the Irish national diabetic retinopathy screening service. In particular, when corrected for age and other factors, patients with type 2 diabetes had higher rates of non-attendance. Additionally, this is the first study of any diabetic screening programme to demonstrate that weather may influence attendance. This research provides unique insight to guide the implementation of an optimal and cost-effective intervention strategy to improve attendance.