A Smartphone-Based Decision Support Tool for Predicting Patients at Risk of Chemotherapy-Induced Nausea and Vomiting: Retrospective Study on App Development Using Decision Tree Induction

Applying AI to Structured Real-World Data for Pharmacovigilance Purposes: Scoping Review

BACKGROUND

Artificial intelligence (AI) applied to real-world data (RWD; eg, electronic health care records) has been identified as a potentially promising technical paradigm for the pharmacovigilance field. There are several instances of AI approaches applied to RWD; however, most studies focus on unstructured RWD (conducting natural language processing on various data sources, eg, clinical notes, social media, and blogs). Hence, it is essential to investigate how AI is currently applied to structured RWD in pharmacovigilance and how new approaches could enrich the existing methodology.

OBJECTIVE

This scoping review depicts the emerging use of AI on structured RWD for pharmacovigilance purposes to identify relevant trends and potential research gaps.

METHODS

The scoping review methodology is based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology. We queried the MEDLINE database through the PubMed search engine. Relevant scientific manuscripts published from January 2010 to January 2024 were retrieved. The included studies were "mapped" against a set of evaluation criteria, including applied AI approaches, code availability, description of the data preprocessing pipeline, clinical validation of AI models, and implementation of trustworthy AI criteria following the guidelines of the FUTURE (Fairness, Universality, Traceability, Usability, Robustness, and Explainability)-AI initiative.

RESULTS

The scoping review ultimately yielded 36 studies. There has been a significant increase in relevant studies after 2019. Most of the articles focused on adverse drug reaction detection procedures (23/36, 64%) for specific adverse effects. Furthermore, a substantial number of studies (34/36, 94%) used nonsymbolic AI approaches, emphasizing classification tasks. Random forest was the most popular machine learning approach identified in this review (17/36, 47%). The most common RWD sources used were electronic health care records (28/36, 78%). Typically, these data were not available in a widely acknowledged data model to facilitate interoperability, and they came from proprietary databases, limiting their availability for reproducing results. On the basis of the evaluation criteria classification, 10% (4/36) of the studies published their code in public registries, 16% (6/36) tested their AI models in clinical environments, and 36% (13/36) provided information about the data preprocessing pipeline. In addition, in terms of trustworthy AI, 89% (32/36) of the studies followed at least half of the trustworthy AI initiative guidelines. Finally, selection and confounding biases were the most common biases in the included studies.

CONCLUSIONS

AI, along with structured RWD, constitutes a promising line of work for drug safety and pharmacovigilance. However, in terms of AI, some approaches have not been examined extensively in this field (such as explainable AI and causal AI). Moreover, it would be helpful to have a data preprocessing protocol for RWD to support pharmacovigilance processes. Finally, because of personal data sensitivity, evaluation procedures have to be investigated further.

The effect of self-care education with smart phone applications on the severity of nausea and vomiting after stem cell transplantation in leukemia patients

INTRODUCTION

Common side effects after stem cell transplantation (SCT), such as anorexia, nausea, and vomiting, can disrupt the quality of life of patients. Therefore, this study aimed to determine the effect of self-care education with smart phone applications on the severity of nausea and vomiting after SCT in leukemia patients.

MATERIALS AND METHODS

In this clinical trial study, using the blocked randomization method 104 leukemia patients undergoing SCT were assigned to two groups, intervention and control. The patients of the Control Group received routine care, and the Intervention Group received self-care education with a smart mobile phone application, in addition to routine care. Two weeks, one month, and three months after the start of the intervention, the severity of nausea and vomiting was evaluated using the visual analog scale (VAS) and the Khavar Oncology scale, both of which were completed by both Control and Intervention Groups. Data were analyzed using chi-square, Fisher's exact, Mann-Whitney, and Friedman tests using the Statistical Package for Social Sciences version 25 software.

RESULTS

The severity of nausea and vomiting in leukemia patients undergoing SCT was significantly different in the two groups at all three timepoints (two weeks, one month, and three months) after transplantation (p-value = 0.000).

CONCLUSION

The severity of nausea and vomiting after SCT in leukemia patients was improved by self-care education with a smart phone application. Therefore, this method is recommended to reduce the severity of nausea and vomiting in leukemia patients who undergo transplantation.

Development and validation of a risk prediction model and prediction tools for post-thrombotic syndrome in patients with lower limb deep vein thrombosis

PURPOSE

Our research aims to compare the predictive performance of decision tree algorithms (DT) and logistic regression analysis (LR) in constructing models, and develop a Post-Thrombotic Syndrome (PTS) risk stratification tool.

METHODS

We retrospectively collected and analyzed relevant case information of 618 patients diagnosed with DVT from January 2012 to December 2021 in three different tertiary hospitals in Jiangxi Province as the modeling group. Additionally, we used the case information of 212 patients diagnosed with DVT from January 2022 to January 2023 in two tertiary hospitals in Hubei Province and Guangdong Province as the validation group. We extracted electronic medical record information including general patient data, medical history, laboratory test indicators, and treatment data for analysis. We established DT and LR models and compared their predictive performance using receiver operating characteristic (ROC) curves and confusion matrices. Internal and external validations were conducted. Additionally, we utilized LR to generate nomogram charts, calibration curves, and decision curves analysis (DCA) to assess its predictive accuracy.

RESULTS

Both DT and LR models indicate that Year, Residence, Cancer, Varicose Vein Operation History, DM, and Chronic VTE are risk factors for PTS occurrence. In internal validation, DT outperforms LR (0.962 vs 0.925, z = 3.379, P < 0.001). However, in external validation, there is no significant difference in the area under the ROC curve between the two models (0.963 vs 0.949, z = 0.412, P = 0.680). The validation results of calibration curves and DCA demonstrate that LR exhibits good predictive accuracy and clinical effectiveness. A web-based calculator software of nomogram (https://sunxiaoxuan.shinyapps.io/dynnomapp/) was utilized to visualize the logistic regression model.

CONCLUSIONS

The combination of decision tree and logistic regression models, along with the web-based calculator software of nomogram, can assist healthcare professionals in accurately assessing the risk of PTS occurrence in individual patients with lower limb DVT.

Machine Learning Approaches to Predict Symptoms in People With Cancer: Systematic Review

BACKGROUND

People with cancer frequently experience severe and distressing symptoms associated with cancer and its treatments. Predicting symptoms in patients with cancer continues to be a significant challenge for both clinicians and researchers. The rapid evolution of machine learning (ML) highlights the need for a current systematic review to improve cancer symptom prediction.

OBJECTIVE

This systematic review aims to synthesize the literature that has used ML algorithms to predict the development of cancer symptoms and to identify the predictors of these symptoms. This is essential for integrating new developments and identifying gaps in existing literature.

METHODS

We conducted this systematic review in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist. We conducted a systematic search of CINAHL, Embase, and PubMed for English records published from 1984 to August 11, 2023, using the following search terms: cancer, neoplasm, specific symptoms, neural networks, machine learning, specific algorithm names, and deep learning. All records that met the eligibility criteria were individually reviewed by 2 coauthors, and key findings were extracted and synthesized. We focused on studies using ML algorithms to predict cancer symptoms, excluding nonhuman research, technical reports, reviews, book chapters, conference proceedings, and inaccessible full texts.

RESULTS

A total of 42 studies were included, the majority of which were published after 2017. Most studies were conducted in North America (18/42, 43%) and Asia (16/42, 38%). The sample sizes in most studies (27/42, 64%) typically ranged from 100 to 1000 participants. The most prevalent category of algorithms was supervised ML, accounting for 39 (93%) of the 42 studies. Each of the methods-deep learning, ensemble classifiers, and unsupervised ML-constituted 3 (3%) of the 42 studies. The ML algorithms with the best performance were logistic regression (9/42, 17%), random forest (7/42, 13%), artificial neural networks (5/42, 9%), and decision trees (5/42, 9%). The most commonly included primary cancer sites were the head and neck (9/42, 22%) and breast (8/42, 19%), with 17 (41%) of the 42 studies not specifying the site. The most frequently studied symptoms were xerostomia (9/42, 14%), depression (8/42, 13%), pain (8/42, 13%), and fatigue (6/42, 10%). The significant predictors were age, gender, treatment type, treatment number, cancer site, cancer stage, chemotherapy, radiotherapy, chronic diseases, comorbidities, physical factors, and psychological factors.

CONCLUSIONS

This review outlines the algorithms used for predicting symptoms in individuals with cancer. Given the diversity of symptoms people with cancer experience, analytic approaches that can handle complex and nonlinear relationships are critical. This knowledge can pave the way for crafting algorithms tailored to a specific symptom. In addition, to improve prediction precision, future research should compare cutting-edge ML strategies such as deep learning and ensemble methods with traditional statistical models.

Real-World Treatment Outcomes, Healthcare Resource Use, and Costs Associated with Antiemetics Among Cancer Patients on Cisplatin-Based Chemotherapy

INTRODUCTION

Chemotherapy-induced nausea and vomiting (CINV) is a recognized adverse outcome among patients with cancer. This retrospective study aimed to quantify the treatment outcomes, resource utilization, and costs associated with antiemetic use to prevent CINV in a broad US population who received cisplatin-based chemotherapy.

METHODS

Data from the STATinMED RWD Insights Database was collected from January 1, 2015 to December 31, 2020. Cohorts included any patients that had at least one claim for fosnetupitant + palonosetron (NEPA) or fosaprepitant + palonosetron (APPA) and evidence of initiating cisplatin-based chemotherapy. Logistic regression was used to evaluate nausea and vomiting visits within 14 days after chemotherapy, and generalized linear models were used to examine all-cause and CINV-related healthcare resource utilization (HCRU) and costs.

RESULTS

NEPA was associated with significantly lower rates of nausea and vomiting visits after chemotherapy (p = 0.0001), including 86% greater odds of nausea and vomiting events for APPA during the second week after chemotherapy (odds ratio [OR] = 1.86; p = 0.0003). The mean numbers of all-cause inpatient visits (p = 0.0195) and CINV-related inpatient and outpatient visits were lower among NEPA patients (p < 0.0001). These differences corresponded to 57% of NEPA patients and 67% of APPA patients having one or more inpatient visits (p = 0.0002). All-cause outpatient costs and CINV-related inpatient costs were also significantly lower for NEPA (p < 0.0001). The mean number of all-cause outpatient visits, all-cause inpatient costs, and CINV-related outpatient costs was not significantly different between groups (p > 0.05).

CONCLUSION

In this retrospective study based on claims data, NEPA was associated with lower rates of nausea and vomiting and lower CINV-related HCRU and costs compared to APPA following cisplatin-based chemotherapy. These results complement clinical trial data and published economic models supporting the use of NEPA as a safe, effective, and cost-saving antiemetic for patients undergoing chemotherapy.