Predicting Outpatient Appointment Demand Using Machine Learning and Traditional Methods

Towards reliable forecasting of healthcare capacity needs: A scoping review and evidence mapping

BACKGROUND

The COVID-19 pandemic has highlighted the critical importance of robust healthcare capacity planning and preparedness for emerging crises. However, healthcare systems must also adapt to more gradual temporal changes in disease prevalence and demographic composition over time. To support proactive healthcare planning, statistical capacity forecasting models can provide valuable information to healthcare planners. This systematic literature review and evidence mapping aims to identify and describe studies that have used statistical forecasting models to estimate healthcare capacity needs within hospital settings.

METHOD

Studies were identified in the databases MEDLINE and Embase and screened for relevance before items were defined and extracted within the following categories: forecast methodology, measure of capacity, forecast horizon, healthcare setting, target diagnosis, validation methods, and implementation.

RESULTS

84 studies were selected, all focusing on various capacity outcomes, including number of hospital beds/ patients, staffing, and length of stay. The selected studies employed different analytical models grouped in six items; discrete event simulation (N = 13, 15 %), generalized linear models (N = 21, 25 %), rate multiplication (N = 15, 18 %), compartmental models (N = 14, 17 %), time series analysis (N = 22, 26 %), and machine learning not otherwise categorizable (N = 12, 14 %). The review further provides insights into disease areas with infectious diseases (N = 24, 29 %) and cancer (N = 12, 14 %) being predominant, though several studies forecasted healthcare capacity needs in general (N = 24, 29 %). Only about half of the models were validated using either temporal validation (N = 39, 46 %), cross-validation (N = 2, 2 %) or/and geographical validation (N = 4, 5 %).

CONCLUSION

The forecasting models' applicability can serve as a resource for healthcare stakeholders involved in designing future healthcare capacity estimation. The lack of routine performance validation of the used algorithms is concerning. There is very little information on implementation and follow-up validation of capacity planning models.

Forecasting rheumatoid arthritis patient arrivals by including meteorological factors and air pollutants

The burden of rheumatoid arthritis (RA) has gradually elevated, increasing the need for medical resource redistribution. Forecasting RA patient arrivals can be helpful in managing medical resources. However, no relevant studies have been conducted yet. This study aims to construct a long short-term memory (LSTM) model, a deep learning model recently developed for novel data processing, to forecast RA patient arrivals considering meteorological factors and air pollutants and compares this model with traditional methods. Data on RA patients, meteorological factors and air pollutants from 2015 to 2022 were collected and normalized to construct moving average (MA)- and autoregressive (AR)-based and LSTM models. After data normalization, the root mean square error (RMSE) was adopted to evaluate models' forecast ability. A total of 2422 individuals were enrolled. Not using the environmental data, the RMSEs of the MA- and AR-based models' test sets are 0.131, 0.132, and 0.117 when the training set: test set ratio is 2:1, 3:1, and 7:1, while they are 0.110, 0.130, and 0.112 for the univariate LSTM models. Considering meteorological factors and air pollutants, the RMSEs of the MA- and AR-based model test sets were 0.142, 0.303, and 0.164 when the training set: test set ratio is 2:1, 3:1, and 7:1, while they were 0.108, 0.119, and 0.109 for the multivariable LSTM models. Our study demonstrated that LSTM models can forecast RA patient arrivals more accurately than MA- and AR-based models for datasets of all three sizes. Considering the meteorological factors and air pollutants can further improve the forecasting ability of the LSTM models. This novel method provides valuable information for medical management, the optimization of medical resource redistribution, and the alleviation of resource shortages.

How to adjust the expected waiting time to improve patient's satisfaction?

BACKGROUND

Long waiting time in hospital leads to patient's low satisfaction. In addition to reducing the actual waiting time (AWT), we can also improve satisfaction by adjusting the expected waiting time (EWT). Then how much can the EWT be adjusted to attribute a higher satisfaction?

METHODS

This study was conducted though experimental with hypothetical scenarios. A total of 303 patients who were treated by the same doctor from August 2021 to April 2022 voluntarily participated in this study. The patients were randomly divided into six groups: a control group (n = 52) and five experimental groups (n = 245). In the control group, the patients were asked their satisfaction degree regarding a communicated EWT (T₀) and AWT (T_a) under a hypothetical situation. In the experimental groups, in addition to the same T₀ and T_a as the control group, the patients were also asked about their satisfaction degree with the extended communicated EWT (T₁). Patients in five experimental groups were given T₁ values with 70, 80, 90, 100, and 110 min respectively. Patients in both control and experiment groups were asked to indicate their initial EWT, after given unfavorable information (UI) in a hypothetical situation, the experiment groups were asked to indicate their extended EWT. Each participant only participated in filling out one hypothetical scenario. 297 valid hypothetical scenarios were obtained from the 303 hypothetical scenarios given.

RESULTS

The experimental groups had significant differences between the initial indicated EWT and extended indicated EWT under the effect of UI (20 [10, 30] vs. 30 [10, 50], Z = -4.086, P < 0.001). There was no significant difference in gender, age, education level and hospital visit history (χ² = 3.198, P = 0.270; χ² = 2.177, P = 0.903; χ² = 3.988, P = 0.678; χ² = 3.979, P = 0.264) in extended indicated EWT. As for patient's satisfaction, compared with the control group, significant differences were found when T₁ = 80 min (χ² = 13.511, P = 0.004), T₁ = 90 min (χ² = 12.207, P = 0.007) and T₁ = 100 min (χ² = 12.941, P = 0.005). When T₁ = 90 min, which is equal to the T_a, 69.4% (34/49) of the patients felt "very satisfied", this proportion is not only significantly higher than that of the control group (34/ 49 vs. 19/52, χ² = 10.916, P = 0.001), but also the highest among all groups. When T₁ = 100 min (10 min longer than T_a), 62.5% (30/48) of the patients felt "very satisfied", it is significantly higher than that of the control group (30/ 48 vs. 19/52, χ² = 6.732, P = 0.009). When T₁ = 80 min (10 min shorter than T_a), 64.8% (35/54) of the patients felt "satisfied", it is significantly higher than that of the control group (35/ 54 vs. 17/52, χ² = 10.938, P = 0.001). However, no significant difference was found when T₁ = 70 min (χ² = 7.747, P = 0.052) and T₁ = 110 min (χ² = 4.382, P = 0.223).

CONCLUSIONS

Providing UI prompts can extend the EWT. When the extended EWT is closer to the AWT, the patient's satisfaction level can be improved higher. Therefore, medical institutions can adjust the EWT of patient's through UI release according to the AWT of hospitals to improve patient's satisfaction.

Demand prediction of medical services in home and community-based services for older adults in China using machine learning

Background

Home and community-based services are considered an appropriate and crucial caring method for older adults in China. However, the research examining demand for medical services in HCBS through machine learning techniques and national representative data has not yet been carried out. This study aimed to address the absence of a complete and unified demand assessment system for home and community-based services.

Methods

This was a cross-sectional study conducted on 15,312 older adults based on the Chinese Longitudinal Healthy Longevity Survey 2018. Models predicting demand were constructed using five machine-learning methods: Logistic regression, Logistic regression with LASSO regularization, Support Vector Machine, Random Forest, and Extreme Gradient Boosting (XGboost), and based on Andersen's behavioral model of health services use. Methods utilized 60% of older adults to develop the model, 20% of the samples to examine the performance of models, and the remaining 20% of cases to evaluate the robustness of the models. To investigate demand for medical services in HCBS, individual characteristics such as predisposing, enabling, need, and behavior factors constituted four combinations to determine the best model.

Results

Random Forest and XGboost models produced the best results, in which both models were over 80% at specificity and produced robust results in the validation set. Andersen's behavioral model allowed for combining odds ratio and estimating the contribution of each variable of Random Forest and XGboost models. The three most critical features that affected older adults required medical services in HCBS were self-rated health, exercise, and education.

Conclusion

Andersen's behavioral model combined with machine learning techniques successfully constructed a model with reasonable predictors to predict older adults who may have a higher demand for medical services in HCBS. Furthermore, the model captured their critical characteristics. This method predicting demands could be valuable for the community and managers in arranging limited primary medical resources to promote healthy aging.

Predicting demand for long-term care using Japanese healthcare insurance claims data

BACKGROUND

Driven by the rapid aging of the population, Japan introduced public long-term care insurance to reinforce healthcare services for the elderly in 2000. Precisely predicting future demand for long-term care services helps authorities to plan and manage their healthcare resources and citizens to prevent their health status deterioration.

METHODS

This paper presents our novel study for developing an effective model to predict individual-level future long-term care demand using previous healthcare insurance claims data. We designed two discriminative models and subsequently trained and validated the models using three learning algorithms with medical and long-term care insurance claims and enrollment records, which were provided by 170 regional public insurers in Gifu, Japan.

RESULTS

The prediction model based on multiclass classification and gradient-boosting decision tree achieved practically high accuracy (weighted average of Precision, 0.872; Recall, 0.878; and F-measure, 0.873) for up to 12 months after the previous claims. The top important feature variables were indicators of current health status (e.g., current eligibility levels and age), risk factors to worsen future healthcare status (e.g., dementia), and preventive care services for improving future healthcare status (e.g., training and rehabilitation).

CONCLUSIONS

The intensive validation tests have indicated that the developed prediction method holds high robustness, even though it yields relatively lower accuracy for specific patient groups with health conditions that are hard to distinguish.

Artificial intelligence-assisted reduction in patients' waiting time for outpatient process: a retrospective cohort study

Background

Many studies suggest that patient satisfaction is significantly negatively correlated with the waiting time. A well-designed healthcare system should not keep patients waiting too long for an appointment and consultation. However, in China, patients spend notable time waiting, and the actual time spent on diagnosis and treatment in the consulting room is comparatively less.

Methods

We developed an artificial intelligence (AI)-assisted module and name it XIAO YI. It could help outpatients automatically order imaging examinations or laboratory tests based on their chief complaints. Thus, outpatients could get examined or tested before they went to see the doctor. People who saw the doctor in the traditional way were allocated to the conventional group, and those who used XIAO YI were assigned to the AI-assisted group. We conducted a retrospective cohort study from August 1, 2019 to January 31, 2020. Propensity score matching was used to balance the confounding factor between the two groups. And waiting time was defined as the time from registration to preparation for laboratory tests or imaging examinations. The total cost included the registration fee, test fee, examination fee, and drug fee. We used Wilcoxon rank-sum test to compare the differences in time and cost. The statistical significance level was set at 0.05 for two sides.

Results

Twelve thousand and three hundred forty-two visits were recruited, consisting of 6171 visits in the conventional group and 6171 visits in the AI-assisted group. The median waiting time was 0.38 (interquartile range: 0.20, 1.33) hours for the AI-assisted group compared with 1.97 (0.76, 3.48) hours for the conventional group (p < 0.05). The total cost was 335.97 (interquartile range: 244.80, 437.60) CNY (Chinese Yuan) for the AI-assisted group and 364.58 (249.70, 497.76) CNY for the conventional group (p < 0.05).

Conclusions

Using XIAO YI can significantly reduce the waiting time of patients, and thus, improve the outpatient service process of hospitals.

Prioritization criteria of patients on scheduled waiting lists for abdominal wall hernia surgery: a cross-sectional study

Purpose

Long delays in waiting lists have a negative impact on the principles of equity and providing timely access to care. This study aimed to assess waiting lists for abdominal wall hernia repair (incisional ventral vs. inguinal hernia) to define explicit prioritization criteria.

Methods

A cross-sectional single-center study was designed. Patients in the waiting list for incisional/ventral hernia (n = 42) and inguinal hernia (n = 50) repair were interviewed by phone and completed health-related quality of life (HRQoL) questionnaires (EQ-5D, COMI-hernia, HerQLes) as a measure of severity. Priority was measured as hernia complexity, patient frailty using the modified frailty index (mFI-11), and the consumption of analgesics for hernia.

Results

The mean (SD) time on the waiting list was 5.5 (3.2) months (range 1–14). Complex hernia was present in 34.8% of the patients. HRQoL was moderately poor in patients with incisional/ventral hernia (mean HerQL score 66.1), whereas it was moderately good in patients with inguinal hernia (mean COMI-hernia score 3.40). The use of analgesics was higher in patients with incisional/ventral hernia as compared with those with inguinal hernia (1.48 [0.54] vs. 1.31 [0.51], P = 0.021). Worst values of mFI were associated with inguinal hernia as compared with incisional/ventral hernia (0.21 [0.14] vs. 0.12 [0.11]; P = 0.010).

Conclusion

Explicit criteria for prioritization in the waiting lists may be the consumption of analgesics for patients with incisional/ventral hernia and frailty for patients with inguinal hernia. A reasonable approach seems to establish separate waiting lists for incisional/ventral hernia and inguinal hernia repair.

Artificial intelligence in paediatric radiology: Future opportunities

Artificial intelligence (AI) has received widespread and growing interest in healthcare, as a method to save time, cost and improve efficiencies. The high-performance statistics and diagnostic accuracies reported by using AI algorithms (with respect to predefined reference standards), particularly from image pattern recognition studies, have resulted in extensive applications proposed for clinical radiology, especially for enhanced image interpretation. Whilst certain sub-speciality areas in radiology, such as those relating to cancer screening, have received wide-spread attention in the media and scientific community, children's imaging has been hitherto neglected.In this article, we discuss a variety of possible 'use cases' in paediatric radiology from a patient pathway perspective where AI has either been implemented or shown early-stage feasibility, while also taking inspiration from the adult literature to propose potential areas for future development. We aim to demonstrate how a 'future, enhanced paediatric radiology service' could operate and to stimulate further discussion with avenues for research.

Prediction of Daily Blood Sampling Room Visits Based on ARIMA and SES Model

This paper is aimed at establishing a combined prediction model to predict the demand for medical care in terms of daily visits in an outpatient blood sampling room, which provides a basis for rational arrangement of human resources and planning. On the basis of analyzing the comprehensive characteristics of the randomness, periodicity, trend, and day-of-the-week effects of the daily number of blood collections in the hospital, we firstly established an autoregressive integrated moving average model (ARIMA) model to capture the periodicity, volatility, and trend, and secondly, we constructed a simple exponential smoothing (SES) model considering the day-of-the-week effect. Finally, a combined prediction model of the residual correction is established based on the prediction results of the two models. The models are applied to data from 60 weeks of daily visits in the outpatient blood sampling room of a large hospital in Chengdu, for forecasting the daily number of blood collections about 1 week ahead. The result shows that the MAPE of the combined model is the smallest overall, of which the improvement during the weekend is obvious, indicating that the prediction error of extreme value is significantly reduced. The ARIMA model can extract the seasonal and nonseasonal components of the time series, and the SES model can capture the overall trend and the influence of regular changes in the time series, while the combined prediction model, taking into account the comprehensive characteristics of the time series data, has better fitting prediction accuracy than a single model. The new model can well realize the short-to-medium-term prediction of the daily number of blood collections one week in advance.