Risk factors and the utility of three different kinds of prediction models for postoperative fatigue after gastrointestinal tumor surgery

Assessing Barriers and Facilitators to Return to Work for Kidney Cancer Survivors: A 6-Month Longitudinal Study

OBJECTIVES

This study aimed to investigate the factors that impact the readiness and success of kidney cancer survivors returning to work, providing insights for healthcare professionals, employers, and policymakers.

METHODS

A prospective longitudinal study was conducted at Sun Yat-sen University Cancer Center from April 2022 to June 2023. The study enrolled 282 kidney cancer survivors aged 18 to 60 who completed three surveys at 1, 3, and 6 months postsurgery. Data collection involved telephone interviews and self-administered questionnaires, capturing sociodemographic information, medical history, and employment status, while follow-up assessments tracked return-to-work readiness. The scales used for analysis included the Generalized Anxiety Disorder Scale, the Patient Health Questionnaire, the Return-to-Work Self-Efficacy Questionnaire, the Perceived Social Support Scale, and the Brief Fatigue Inventory. Generalized Estimation Equations were applied to identify significant factors, with both single-factor and multivariate analyses performed to pinpoint the most critical variables.

RESULTS

Return-to-work rates at 1, 3, and 6 months postsurgery were 26.9%, 59.9%, and 76.2%, respectively. Higher levels of anxiety, lower self-efficacy, older age, and greater fatigue were associated with reduced return-to-work rates. Physically demanding jobs posed more barriers compared to nonmanual roles. Significant factors identified in multivariate analysis included anxiety, self-efficacy, fatigue, and the nature of the patient's work.

CONCLUSION

Psychological, physical, and job-related factors play a crucial role in determining whether kidney cancer survivors can successfully return to work. Tailored support and flexible work arrangements could help kidney cancer survivors reintegrate into the workforce, leading to better long-term outcomes.

IMPLICATION FOR NURSING PRACTICE

Nursing professionals can play a vital role in assessing and supporting kidney cancer survivors during their recovery process by addressing both psychological and physical factors. Incorporating return-to-work readiness into postoperative care plans, offering mental health support, and liaising with employers to create flexible working conditions could enhance the reintegration of survivors into the workforce.

Using real-world electronic health record data to predict the development of 12 cancer-related symptoms in the context of multimorbidity

Objective

This study uses electronic health record (EHR) data to predict 12 common cancer symptoms, assessing the efficacy of machine learning (ML) models in identifying symptom influencers.

Materials and Methods

We analyzed EHR data of 8156 adults diagnosed with cancer who underwent cancer treatment from 2017 to 2020. Structured and unstructured EHR data were sourced from the Enterprise Data Warehouse for Research at the University of Iowa Hospital and Clinics. Several predictive models, including logistic regression, random forest (RF), and XGBoost, were employed to forecast symptom development. The performances of the models were evaluated by F1-score and area under the curve (AUC) on the testing set. The SHapley Additive exPlanations framework was used to interpret these models and identify the predictive risk factors associated with fatigue as an exemplar.

Results

The RF model exhibited superior performance with a macro average AUC of 0.755 and an F1-score of 0.729 in predicting a range of cancer-related symptoms. For instance, the RF model achieved an AUC of 0.954 and an F1-score of 0.914 for pain prediction. Key predictive factors identified included clinical history, cancer characteristics, treatment modalities, and patient demographics depending on the symptom. For example, the odds ratio (OR) for fatigue was significantly influenced by allergy (OR = 2.3, 95% CI: 1.8-2.9) and colitis (OR = 1.9, 95% CI: 1.5-2.4).

Discussion

Our research emphasizes the critical integration of multimorbidity and patient characteristics in modeling cancer symptoms, revealing the considerable influence of chronic conditions beyond cancer itself.

Conclusion

We highlight the potential of ML for predicting cancer symptoms, suggesting a pathway for integrating such models into clinical systems to enhance personalized care and symptom management.

Effects of esketamine on postoperative fatigue syndrome in patients after laparoscopic resection of gastric carcinoma: a randomized controlled trial

BACKGROUND

Despite the implementation of various postoperative management strategies, the prevalence of postoperative fatigue syndrome (POFS) remains considerable among individuals undergoing laparoscopic radical gastrectomy. While the N-methyl-D-aspartic acid receptor antagonist esketamine has demonstrated efficacy in enhancing sleep quality and alleviating postoperative pain, its impact on POFS remains uncertain. Consequently, the objective of this study is to ascertain whether perioperative administration of esketamine can effectively mitigate the occurrence of POFS in patients undergoing laparoscopic radical gastrectomy.

METHODS

A total of 133 patients diagnosed with gastric cancer were randomly assigned to two groups, namely the control group (Group C) (n = 66) and the esketamine group (Group E) (n = 67), using a double-blind method. The Group C received standardized anesthesia, while the Group E received esketamine in addition to the standardized anesthesia. The primary outcome measure assessed was the Christensen fatigue score at 3 days after the surgical procedure, while the secondary outcomes included the disparities in postoperative fatigue, postoperative pain, sleep quality, and adverse reactions between the two groups.

RESULTS

In the group receiving esketamine, the fatigue scores of Christensen on the third day after surgery were significantly lower compared to the Group C (estimated difference, -0.70; 95% CI, -1.37 to -0.03; P = 0.040). Additionally, there was a significant decrease in the occurrence of fatigue in the Group E compared to the Group C on the first and third days following surgery (P < 0.05). Also, compared to individuals who had distal gastrectomy, those who had entire gastrectomy demonstrated a higher degree of postoperative tiredness reduction with esketamine. Furthermore, the Group E exhibited reduced postoperative pain and improved sleep in comparison to the Group C. Both groups experienced similar rates of adverse events.

CONCLUSIONS

The use of esketamine during the perioperative period can improve POFS after laparoscopic radical gastrectomy, without adverse reactions.

TRIAL REGISTRATION

Registered in the Chinese Clinical Trial Registry (ChiCTR2300072167) on 05/06 /2023.

Fatigue, fear of being mobilized and residual limb pain limit independent basic mobility and physiotherapy for patients early after major dysvascular lower extremity amputation: A prospective cohort study

AIM

Early mobilization of patients with a major lower extremity amputation (LEA) is often a challenge because of lack of compliance. Therefore, we investigated factors limiting independent mobility and physiotherapy on the first day with physiotherapy (PTDay1) and the following 2 days after LEA.

METHODS

A total of 60 consecutive patients, mean age 73.7 years (SD 12.1 years), undergoing LEA were included over a period of 7 months. The Basic Amputee Mobility Score was used to assess basic mobility. Predefined limitations for not achieving independent mobility or not completing physiotherapy were residual limb pain, pain elsewhere, fear of being mobilized, fatigue, nausea/vomiting, acute cognitive dysfunction or "other" factors reported on PTDay1 and the following 2 days after LEA.

RESULTS

Fatigue and fear of being mobilized were the most frequent limitations for not achieving independent mobility on PTDay1 and the following 2 days after LEA. Patients (n = 55) who were not independent in the Basic Amputee Mobility Score activity transferring from bed to chair on PTDay1 were limited by fatigue (44%) and fear of being mobilized (33%). A total of 21 patients did not complete planned physiotherapy on PTDay1, and were limited by fatigue (38%), residual limb pain (24%) and "other" factors (24%).

CONCLUSION

Fatigue and fear of being mobilized were the most frequent factors that limited independent mobility early after LEA. Fatigue, residual limb pain and "other" factors limited completion of physiotherapy. Geriatr Gerontol Int 2024; 24: 470-476.

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.

Effect of propofol and sevoflurane on postoperative fatigue after laparoscopic hysterectomy

BACKGROUND

Postoperative fatigue syndrome (POFS) is an important factor in postoperative recovery. However, the effect of anesthetic drugs on postoperative fatigue in female patients has been rarely studied. This study compared the effects of maintaining general anesthesia with propofol or sevoflurane on the incidence of POFS in patients undergoing laparoscopic hysterectomy.

METHODS

This prospective, single-blind, randomized controlled trial enrolled patients scheduled for laparoscopic hysterectomy. Eligible patients were randomized into the propofol and sevoflurane groups. The primary outcome was the incidence of POFS within 30 Days, defined by a simplified identity consequence fatigue scale (ICFS-10) scores≥24 or Visual Analogue Scale (VAS) scores of fatigues>6. Secondary outcomes were perioperative grip strength, early ambulation and anal exhaust after surgery, and inpatient days.

RESULTS

32 participants were assigned to the propofol group (P) and 33 to the sevoflurane group (S). Incidence of POFS on postoperative D1 was P (8/32) vs. S (10/33) (p = 0.66, 95% confidence interval [CI]: 16.4-27.00); D3 P (2/32) vs. S (5/33) (p = 0.45,95% CI:5.96-23.76). POFS were not found on postoperative D5 and D30. There were no differences in perioperative grip strength, early ambulation and anal exhaust after surgery, and inpatient days between the two groups.

CONCLUSIONS

POFS after scheduled laparoscopic hysterectomy was unaffected by anesthesia with propofol vs. sevoflurane. The incidence of POFS was highest on the first postoperative day, at 27.7%, and declined progressively over the postoperative 30 days. Trial registration Chinese Clinical Trial Registry (No. ChiCTR 2,000,033,861), registered on 14/06/2020).

A randomized controlled trial of propofol-remifentanil total intravenous anesthesia and sevoflurane-fentanyl anesthesia on early postoperative fatigue in patients undergoing laparoscopic colorectal surgery

PURPOSE

Even after uncomplicated surgery, postoperative fatigue prevalence has been reported to be 30-80% for various surgeries. We evaluated postoperative fatigue according to anesthetic technique in patients who underwent colorectal surgery.

METHODS

One hundred thirty patients who underwent colorectal surgery were randomly assigned to either propofol-remifentanil total intravenous anesthesia (propofol-remifentanil group, n = 65) or sevoflurane-fentanyl anesthesia (sevoflurane-fentanyl group, n = 65). The primary outcome was the prevalence of postoperative fatigue, as defined by the Chalder Fatigue Questionnaire (total score ≥ 16), at 24 h postoperatively. Secondary outcomes were early postoperative complications during hospitalization and laboratory examination.

RESULTS

The final analyses included 127 patients. The prevalence of postoperative fatigue on the 1st postoperative day was lower in the propofol-remifentanil group than the sevoflurane-fentanyl group: 56.3% (36/64) in the propofol-remifentanil group and 73.0% (46/63) in the sevoflurane-fentanyl group (relative risk [RR] = 0.77, 95% confidence interval [CI] 0.59-1.00; P = 0.048). However, there was no difference between the two groups in postoperative fatigue at postoperative day 3. Other postoperative outcomes including the severity of pain and the incidence of nausea/vomiting were not different between the two groups, but postoperative atelectasis on chest X-ray was higher in the sevoflurane-fentanyl group (2/64 [3.1%] vs. 9/63 [14.3%], P = 0.025). C-reactive protein change from preoperative to postoperative day 1 and 5 was significantly lower in the propofol-remifentanil group (P = 0.044).

CONCLUSION

Propofol-remifentanil total intravenous anesthesia was associated with reduced postoperative fatigue at the 1st postoperative day compared with sevoflurane-fentanyl anesthesia. Clinical trial The Korean Clinical Research Registry (study identifier: KCT0006917, principal investigator's name: MiHye Park, date of registration: January 12, 2022).

Association between neutrophil-to-lymphocyte ratio and postoperative fatigue in elderly patients with hip fracture

Background

and purpose: Postoperative fatigue (POF) is a common and distressing post-operative symptom. This study aimed to explore the relationship between neutrophil-to-lymphocyte ratio (NLR) and POF in elderly patients with hip fracture.

Method

Elderly patients (age ≥65 years) with acute hip fracture admitted to the Department of Orthopedics of Anqing Municipal Hospital from June 2018 to June 2020 were included. Fatigue was assessed using the Fatigue Severity Scale at the 3-month follow-up postoperatively. Univariate and multivariate analyses were performed to explore the associations between NLR and POF. The diagnostic performance of NLR was analysed using Receiver Operating Characteristic (ROC) curve analysis and the Delong test.

Result

A total of 321 elderly patients with hip fractures were included; 120 (37.4 %) of them were diagnosed with POF. Univariate analysis indicated significant differences in NLR, platelet-to-lymphocyte ratio (PLR), education, neutrophil count, lymphocyte count, Hamilton Depression Scale (HAMD) and Insomnia Severity Index (ISI) scores (P < 0.05). Multivariate analysis indicated neutrophil count (odds ratio [OR], 1.46; 95 % confidence interval [CI] 1.27-1.67), lymphocyte count (OR 0.32, 95 % CI 0.19-0.53), NLR (OR1.81, 95 % CI 1.50-2.17) and PLR (OR 1.005, 95 % CI 1.001-1.009) were significantly associated with POF. The areas under the ROC curves (AUCs) of neutrophil count, lymphocyte count, NLR and PLR were 0.712, 0.667, 0.775 and 0.605, respectively. The Delong test indicated that NLR had the best diagnostic performance (p < 0.05).

Conclusion

NLR independently predicts POF in elderly patients with acute hip fracture.

A prediction model for moderate to severe cancer-related fatigue in colorectal cancer after chemotherapy: a prospective case‒control study

AIMS

The study aims to develop a model to predict the risk of moderate to severe cancer-related fatigue (CRF) in colorectal cancer patients after chemotherapy.

METHODS

The study population was colorectal cancer patients who received chemotherapy from September 2021 to June 2022 in a grade 3 and first-class hospital. Demographic, clinical, physiological, psychological, and socioeconomic factors were collected 1 to 2 days before the start of chemotherapy. Patients were followed up for 1 to 2 days after the end of chemotherapy to assess fatigue using the Piper Fatigue Scale. A random sampling method was used to select 181 patients with moderate to severe CRF as the case group. The risk set sampling method was used to select 181 patients with mild or no CRF as the control group. Logistic regression, back-propagation artificial neural network (BP-ANN), and decision tree models were constructed and compared.

RESULTS

A total of 362 patients consisting of 241 derivation samples and 121 validation samples were enrolled. Comparing the three models, the prediction effect of BP-ANN was the best, with a receiver operating characteristic (ROC) curve of 0.83. Internal and external verification indicated that the accuracy of prediction was 70.4% and 80.8%, respectively. Significant predictors identified were surgery, complications, hypokalaemia, albumin, neutrophil percentage, pain (VAS score), Activities of Daily Living (ADL) score, sleep quality (PSQI score), anxiety (HAD-A score), depression (HAD-D score), and nutrition (PG-SGA score).

CONCLUSIONS

BP-ANN was the best model, offering theoretical guidance for clinicians to formulate a tool to identify patients at high risk of moderate to severe CRF.

Development and external validation of a machine learning-based prediction model for the cancer-related fatigue diagnostic screening in adult cancer patients: a cross-sectional study in China

PURPOSE

Cancer-related fatigue (CRF) is the most common symptom in cancer patients and may interfere with patients' daily activities and decrease survival rate. However, the etiology of CRF has not been identified. Diagnosing CRF is challenging. Thus, our study aimed to develop a CRF prediction model in cancer patients, using data that healthcare professionals routinely obtained from electronic health records (EHRs) based on the 3P model and externally validate this model in an independent dataset collected from another hospital.

METHODS

Between April 2022 and September 2022, a cross-sectional study was conducted on adult cancer patients at two first-class tertiary hospitals in China. Data that healthcare professionals routinely obtained from electronic health records (EHRs) based on the 3P model were collected. The outcome measure was according to ICD-10 diagnostic criteria for CRF. Data from one hospital (n = 305) were used for model development and internal validation. An independent data set from another hospital (n = 260) was utilized for external validation. logistic regression, random forest (RF), Naive Bayes (NB), and extreme gradient boosting (XGBoost) were constructed and compared. The model performance was evaluated in terms of both discrimination and calibration.

RESULTS

The prevalence of CRF in the two centers was 57.9% and 56.1%, respectively. The Random Forest model achieved the highest AUC of 0.86 among the four types of classifiers in the internal validation. The AUC of RF and NB were above 0.7 in the external validation, suggesting that the models also have an acceptable generalization ability.

CONCLUSIONS

The incidence of CRF remains high and deserves more attention. The fatigue prediction model based on the 3P theory can accurately predict the risk of CRF. Nonlinear algorithms such as Random Forest and Naive Bayes are more suitable for diagnosing and evaluating symptoms.

Effect of a single sub-dose of ketamine on postoperative fatigue syndrome in colorectal cancer patients undergoing radical laparoscopic surgery: A double-blind, pilot study

BACKGROUND

This study aimed at examining the effect of a single sub-anesthetic dose of ketamine on postoperative fatigue syndrome (POFS) in patients undergoing radical laparoscopic surgery for colorectal cancer (CRC).

METHODS

This prospective, double-blind, pilot study enrolled patients scheduled for radical laparoscopic surgery for CRC under general anesthesia. Eligible patients were randomized into the placebo and ketamine groups. The primary outcome was christensen score change at day 3. The secondary outcomes were the difference of Identity Consequence Fatigue Scale (ICFS) score between the placebo group and ketamine group at day 3 and level of serum tumor necrosis factor (TNF)-α, interleukin (IL)-6, S100β protein, and neuron-specific enolase (NSE).

RESULTS

32 participants were assigned to the ketamine group and 31 to the placebo group. Compared with placebo group, the Christensen score was lower in ketamine group at day 3 (absolute difference, -1.13; 95 % confidence interval [CI], -2.02 to -0.24; P = 0.012). Ketamine group was superior to the placebo group with regard to the ICFS scores at day 3 (absolute difference, -6.4; 95 % CI, -11.4 to -1.4; P = 0.013). The plasma TNF-α, IL-6, S100β, and NSE levels were increased after operation compared with baseline in both groups and were significantly higher in placebo group than in ketamine group within 24 h after surgery (all P < 0.05). There was no significant difference of each safety evaluation indicator between the two groups (all P > 0.05).

CONCLUSION

A single sub-anesthetic dose of ketamine may improve POFS in patients undergoing radical laparoscopic surgery for CRC, without postoperative adverse reactions.

Survival Prediction Model for Patients with Esophageal Squamous Cell Carcinoma Based on the Parameter-Optimized Deep Belief Network Using the Improved Archimedes Optimization Algorithm

Esophageal squamous cell carcinoma (ESCC) is one of the highest incidence and mortality cancers in the world. An effective survival prediction model can improve the quality of patients' survival. Therefore, a parameter-optimized deep belief network based on the improved Archimedes optimization algorithm is proposed in this paper for the survival prediction of patients with ESCC. Firstly, a combination of features significantly associated with the survival of patients is found by the minimum redundancy and maximum relevancy (MRMR) algorithm. Secondly, a DBN network is introduced to make predictions for survival of patients. Aiming at the problem that the deep belief network model is affected by parameters in the construction process, this paper uses the Archimedes optimization algorithm to optimize the learning rate α and batch size β of DBN. In order to overcome the problem that AOA is prone to fall into local optimum and low search accuracy, an improved Archimedes optimization algorithm (IAOA) is proposed. On this basis, a survival prediction model for patients with ESCC is constructed. Finally, accuracy comparison tests are carried out on IAOA-DBN, AOA-DBN, SSA-DBN, PSO-DBN, BES-DBN, IAOA-SVM, and IAOA-BPNN models. The results show that the IAOA-DBN model can effectively predict the five-year survival rate of patients and provide a reference for the clinical judgment of patients with ESCC.