A predictive analytics framework for identifying patients at risk of developing multiple medical complications caused by chronic diseases

Risk Factors for Disease Aggravation in Older Patients With Non-communicable Diseases: Interpretive Structural and Hierarchical Holographic Modelling

AIMS

This study aimed to analyse and determine the risk factors of disease aggravation faced by older patients with non-communicable diseases (NCDs) and their interwoven correlations.

DESIGN

We employed a descriptive and cross-sectional study, which followed the STROBE guidelines for reporting.

METHODS

We conducted a semi-structured in-depth interview with 26 older patients with NCDs from a hospital in Qingdao, China between July and August 2022 on the basis of the literature review. Then, we analysed data using the directed content analysis and determined risk factors through a focus group discussion and the Delphi consultation. Afterward, we combined interpretive structural modelling and hierarchical holographic modelling to construct a hierarchical structure model and drew relationship framework diagrams to exhibit diversified risk factors and complex interwoven correlations.

RESULTS

We identified 30 risk factors from individual, interpersonal, organisational, community and policy levels. The hierarchical structure model constructed by interpretive structural modelling demonstrated a four-layer structure, and the individual and interpersonal levels were at the highest layer. The relationship framework diagrams demonstrated the identification process of risk factors and interwoven correlations at individual and organisational levels.

CONCLUSIONS

Risk factors causing disease aggravation amongst older patients with NCDs are diverse. To delay the progression of NCDs, we should comprehensively explore risk factors, interpret the root causes and effects of risks from multiple perspectives and consider the interaction amongst multi-level risk factors to develop precise measures related to risk control.

IMPACT

Controlling risk factors is an effective measure to postpone disease aggravation. Through this study, we provide a scientific and comprehensive basis for clinical risk screening so that healthcare providers can sense potential risk factors for disease aggravation in older patients' surroundings and formulate targeted nursing measures according to the risk factors faced by different patients.

PATIENT OR PUBLIC CONTRIBUTION

Patients participated in interviews to supplement risk factors included in our study. Experts provided opinions on the inclusion, exclusion and modification of risk factors.

Otolaryngic Allergy Patient Journey Mapping: A Framework for Allergy Immunotherapy Adherence

OBJECTIVES

Allergen-specific immunotherapy (AIT) is an effective treatment for allergic disease but requires long treatment duration and premature cessation is of significant concern. Drivers of premature cessation remain poorly understood and no predictive models currently exist. We hypothesized that a novel patient journey map and de novo real-time patient electronic health status instruments (eHSIs) could effectively capture patient perceived cost, commitment, and treatment benefit to identify individual patients at risk for premature AIT cessation.

STUDY TYPE

Cross-Sectional Observational Study.

METHODS

A single Otolaryngology allergy immunotherapy (AIT) program was studied over 5 years. Instances of premature cessation were classified. An Otolaryngic Allergy Patient Journey Map was developed to identify and target automated, real-time, patient-reported, electronic health status instrument responses.

RESULTS

Data capture was robust, with 61,406 data points collected and an eHSI survey completion rate of 81.3%. However, based on correlation analysis and logistic regression alone, real-time eHSI responses were not predictive of individual patient premature AIT cessation. A total of 597 AIT patients discontinued treatment prematurely: 64.4% stopping within the first year. Specifically, 74.0%-76.3% of subcutaneous AIT patients and 88.5%-100% of sublingual AIT patients did not complete the minimum recommended treatment duration of 3 years.

CONCLUSION

Patient journey mapping can aid in the design of longitudinal care models and patient engagement strategies. Yet, eHSI patient responses of perception of AIT cost, benefit, and convenience did not correlate with the likelihood of premature treatment cessation. Our imperfect clinical intuition may not account for the dynamic drivers of premature AIT discontinuation. Future development of predictive tools feed by large patient-centric data sets may be incorporated into routine practice resulting in delivery of a more streamlined and personalized approach with reduced premature AIT cessation, improved outcomes, and reduced health care expenditures.

LEVEL OF EVIDENCE

NA Laryngoscope, 2024.

Improve individual treatment by comparing treatment benefits: cancer artificial intelligence survival analysis system for cervical carcinoma

Purpose

The current study aimed to construct a novel cancer artificial intelligence survival analysis system for predicting the individual mortality risk curves for cervical carcinoma patients receiving different treatments.

Methods

Study dataset (n = 14,946) was downloaded from Surveillance Epidemiology and End Results database. Accelerated failure time algorithm, multi-task logistic regression algorithm, and Cox proportional hazard regression algorithm were used to develop prognostic models for cancer specific survival of cervical carcinoma patients.

Results

Multivariate Cox regression identified stage, PM, chemotherapy, Age, PT, and radiation_surgery as independent influence factors for cervical carcinoma patients. The concordance indexes of Cox model were 0.860, 0.849, and 0.848 for 12-month, 36-month, and 60-month in model dataset, whereas it were 0.881, 0.845, and 0.841 in validation dataset. The concordance indexes of accelerated failure time model were 0.861, 0.852, and 0.851 for 12-month, 36-month, and 60-month in model dataset, whereas it were 0.882, 0.847, and 0.846 in validation dataset. The concordance indexes of multi-task logistic regression model were 0.860, 0.863, and 0.861 for 12-month, 36-month, and 60-month in model dataset, whereas it were 0.880, 0.860, and 0.861 in validation dataset. Brier score indicated that these three prognostic models have good diagnostic accuracy for cervical carcinoma patients. The current research lacked independent external validation study.

Conclusion

The current study developed a novel cancer artificial intelligence survival analysis system to provide individual mortality risk predictive curves for cervical carcinoma patients based on three different artificial intelligence algorithms. Cancer artificial intelligence survival analysis system could provide mortality percentage at specific time points and explore the actual treatment benefits under different treatments in four stages, which could help patient determine the best individualized treatment. Cancer artificial intelligence survival analysis system was available at: https://zhangzhiqiao15.shinyapps.io/Tumor_Artificial_Intelligence_Survival_Analysis_System/.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12967-022-03491-8.