Use Of Prognostic Tools Research Articles

Pearls for counseling older adults on the indications for stopping colon cancer screening

Colorectal cancer remains a leading cause of mortality, making effective screening procedures like colonoscopy essential in reducing associated risks. The cessation of colorectal cancer screening in older adults presents complex challenges, particularly as guidelines recommend screening initiation at age 45 and emphasize individualized decision-making for older populations. Key considerations include balancing procedural risks, cancer risk, overall health prognosis, and patient preferences. The risks associated with colonoscopy are especially pertinent for older patients with comorbidities, necessitating the use of prognostic tools like ePrognosis and the Charlson Comorbidity Index to inform screening decisions. High-risk individuals may experience increased anxiety about cancer, complicating the decision-making process, as many have historically relied on regular surveillance. Perspectives from both physicians and patients reveal significant uncertainty regarding screening cessation, highlighting the importance of patient involvement in these discussions. Effective communication strategies are crucial, advocating for recommendations that align with patients' broader health goals rather than focusing solely on age-related actuarial data. Ultimately, navigating the intricacies of colorectal cancer screening cessation in older adults requires a patient-centered approach that minimizes risks while respecting individual values and health goals.

428. Risk Stratification and Clinical Outcomes in a Mixed Vaccination Cohort of COVID-19 Patients Admitted in a Tertiary Hospital Using ISARIC 4C Scores

Abstract Background The risk of clinical deterioration and death with the use of prognostic tools remain necessary for strategic planning among COVID-19 patients. The International Severe Acute Respiratory and Emerging Infections Consortium (ISARIC) developed and validated Coronavirus Clinical Characterization Consortium (4C) scores to predict clinical deterioration and mortality. ISARIC 4C scores uses readily available clinical parameters. With the increasing uptake of COVID-19 vaccine, there is a need to evaluate these tools. The study examined a cohort of fully vaccinated (FV), partially vaccinated (PV) and unvaccinated (UV) COVID-19 patients and determined their clinical outcomes and stratified risks using ISARIC 4C scores. Methods We reviewed medical records of confirmed COVID-19 patients admitted to a single tertiary hospital between May 2021 and April 2022. Vaccination status were classified as FV, PV and UV. The primary outcome was in-hospital mortality. Baseline data were collected and predictors recorded upon admission were used to calculate the 4C scores. Multiple logistic regression analysis was used to determine the association of vaccination status and 4C Deterioration and Mortality scores with in-hospital mortality. STATA 14 was used for data analysis and p< 0.05 was considered statistically significant. Results A total of 301 confirmed COVID-19 patients were included and 46.5% were fully vaccinated. FV patients had significantly lower CRP (p< 0.0001), had higher mean oxygen saturation (p< 0.0001), had lower mean mortality score (p=0.004), had lower mean % risk for deterioration (p< 0.0001) and had significantly lower 30-day mortality (< 0.0001) compared to those UV and PV. Patient who died had significantly higher mean age (p=0.001), lower mean lymphocyte ratio (p=0.0004), had significantly higher mean deterioration and mortality score (p< 0.0001). Being fully vaccinated was associated with lower risk for mortality (OR=0.4, 95%CI=0.2 to 0.7). Conclusion Fully vaccinated patients were at lower risk for deterioration and mortality. High ISARIC 4C scores were also significantly associated with higher risk for mortality. Risk stratification tools should be utilized in COVID-19 management as they provide a helpful means to identify patients at risk for worse outcomes. Disclosures All Authors: No reported disclosures

Machine learning for survival analysis in cancer research: A comparative study

OverviewSurvival analysis is at the basis of every study in the field of cancer research. As every endeavor in this field aims primarily and eventually to improve patients’ survival time or reduce the potential for recurrence. This article presents a summary of some cancer survival analysis techniques and an up-to-date overview of different implementations of Machine Learning in this area of research. This paper also presents an empirical comparison of selected statistical and Machine Learning approaches on different types of cancer medical datasets. MethodsIn this paper we explore a selection of recent articles that: review the use of Machine Learning in cancer research and/or benchmark the different Machine Learning techniques used in cancer survival analysis. This search resulted in 12 papers that were selected following certain criteria. Our aim is to assess the importance of the use of Machine Learning for survival analysis in cancer research, compared to the statistical methods, and how different Machine Learning techniques may perform in different settings in the context of cancer survival analysis. The techniques were selected based on their popularity. Cox Proportional Hazards with Ridge penalty, Random Survival Forests, Gradient Boosting for Survival Analysis with a CoxPh loss function, linear and kernel Support Vector Machines were applied to 10 different cancer survival datasets. The mean Concordance Index and standard deviation were used to compare the performances of these techniques and the results of these implementations were summarized and analyzed for noticeable patterns or trends. Kaplan-Meier plots were used for the non-parametric survival analysis of the different datasets. ResultsCox Proportional Hazards delivers comparable results with Machine Learning techniques thanks to the Ridge penalty and the different methods for dealing with tied events but fails to produce results in higher dimensional datasets. All techniques benchmarked in the study had comparable performances. The use of prognostic tools when there is a mismatch between the patients and the populations used to train the models may not be advisable since each dataset provides a differently shaped survival curve even when presenting a similar cancer type.

Dynamics of Mortality and Transformation Risk within Different Risk Groups of Patients with Myelodysplastic Syndromes Stratified According to the IPSS-R - Comparison of Treated and Untreated Patients and Consequences for the Description of Risk Categories

Background In MDS, most risk assessment tools such as the IPSS-R estimate risk at time of diagnosis. Risk assigned by the IPSS-R categories, however, is not constant over time. Changes in hazard (= time specific risk in a short time interval) during course of the disease affect the use of prognostic tools and may influence clinical decisions. We have previously shown time related hazard changes in untreated patients leading to declining risk in higher risk groups and diminution of differences between risk groups over time. Aim of this study was to investigate hazard changes in patients undergoing disease-modifying treatment. Patients and methods 16 international partners of the IWG-PM contributed data from 9179 primary MDS patients of which 2015 had disease modifying treatment: median age 70.0 yrs, 60% male, median follow up 4.1 yrs, median OS 3.8 yrs, IPSS-R categories: very low 16%, low 35%, intermediate 22%, high 15%, very high 12%. Treatment modalities included hypomethylating agents, lenalidomide, cytotoxic therapy, 17% had stem cell transplantation. Time variations were described by smoothed hazard graphs and by the Cox zph test including rho, a measure for a linear time dependent impact of a feature on hazard. Semiparametric accelerated failure time models were estimated by direct optimization procedures. Results and discussion Using hazard graphs and the Cox zph-test we confirmed changes in hazard relations over time in the untreated subsample (rho -0.20 for OS). In treated patients a similar diminution was observed (rho -0.26 for OS). Results from treated patients revealed temporary increased hazard after some months especially in higher risk patients. Possible reasons are decision to start treatment when hazard increases or transient risk by therapy-associated toxicity, as well as a "guarantee time bias", induced by delayed treatment start, which in treated patients implicitly guarantees survival until start of treatment. To account for the latter, analyses were repeated excluding "guarantee time” in treated patients, again showing hazard reduction in higher risk patients and diminution between risk categories: untreated: rho -0.20 for OS, treated: rho -0.08 (fig A-B). Differently developing changes in hazards over time contradict the proportional hazards assumption of the Cox model. Therefore, as an alternative we investigated accelerated failure time models - fitting semi parametric models for IPSS-R risk categories: results show that patients in different risk categories share similar course of hazards - only at different "speeds” (speed-factors excluding guarantee time to achieve average survival: VERY LOW 0.34, LOW 0.63, INT 1.15, HIGH 2.23, VERY HIGH 5.11.) Transforming time accordingly makes common patterns visible, as in figure C, where most risk categories show hazard peaks before reaching the time of their median survival. Conclusions In MDS, hazards are not constant over time, possibly slightly rising until around the category specific median survival times and later clearly falling, except for the very high risk category. Longitudinal changes of hazards are not proportional between IPSS-R categories, instead diminution of hazard proportions between risk categories is observed. To describe the development of hazard for different IPSS-R categories the concept of different "speeds” of the disease development may be appropriate. Clinicians need to be aware of the dynamics of hazards in MDS when counselling patients both treated or those receiving supportive care only. Risk assessment at time of diagnosis by the IPSS-R assigns average group differences but changes over time need to be taken into account. Our data suggest that median survival times for IPSS-R categories approximately express different speeds and also indicate the time, when survival hazards are declining. Figure 1View largeDownload PPTFigure 1View largeDownload PPT Close modal

Simulation of consumer behavior in the market of medical products

Methods. The formation of theoretical and methodological foundations for modeling consumer behavior in the market of medical products by the author's method is based on the use of prognostic tools, the creation of complex agency models of consumer behavior. Results. The paper presents a classification of types of purchasing behavior of the segment of industry experts, which includes 7 classes, with each of which the manufacturer must establish a separate communication. Each presented class is characterized by the corresponding parameters of behavior: speed of decision-making on purchase, possibility of repeated purchase, authority in the eyes of other groups of consumers. The classification of types of purchasing behavior of individuals was carried out according to such parameters as consumption intensity, level of education and income level, which allowed to form 9 classes of consumers. Novelty. In the process of research, a new methodological approach to consumer analysis is substantiated, which reveals the stages of formation and expansion of target segments taking into account the specifics of the product market, which allows to differentiate or concentrate marketing efforts when launching a new product. This is due to the fact that there are important differences in the purchasing behavior of consumers (individuals) and organizations. Practical value. The proposed approach allows to take into account the heterogeneity of the market in terms of innovation in relation to a new product and the impact of interpersonal communications in the formation of consumer awareness when launching new products in online environments.

Mastering Prognostic Tools: An Opportunity to Enhance Personalized Care and to Optimize Clinical Outcomes in Physical Therapy.

In health care, clinical decision making is typically based on diagnostic findings. Rehabilitation clinicians commonly rely on pathoanatomical diagnoses to guide treatment and define prognosis. Targeting prognostic factors is a promising way for rehabilitation clinicians to enhance treatment decision-making processes, personalize rehabilitation approaches, and ultimately improve patient outcomes. This can be achieved by using prognostic tools that provide accurate estimates of the probability of future outcomes for a patient in clinical practice. Most literature reviews of prognostic tools in rehabilitation have focused on prescriptive clinical prediction rules. These studies highlight notable methodological issues and conclude that these tools are neither valid nor useful for clinical practice. This has raised the need to open the scope of research to understand what makes a quality prognostic tool that can be used in clinical practice. Methodological guidance in prognosis research has emerged in the last decade, encompassing exploratory studies on the development of prognosis and prognostic models. Methodological rigor is essential to develop prognostic tools, because only prognostic models developed and validated through a rigorous methodological process should guide clinical decision making. This Perspective argues that rehabilitation clinicians need to master the identification and use of prognostic tools to enhance their capacity to provide personalized rehabilitation. It is time for prognosis research to look for prognostic models that were developed and validated following a comprehensive process before being simplified into suitable tools for clinical practice. New models, or rigorous validation of current models, are needed. The approach discussed in this Perspective offers a promising way to overcome the limitations of most models and provide clinicians with quality tools for personalized rehabilitation approaches.ImpactPrognostic research can be applied to clinical rehabilitation; this Perspective proposes solutions to develop high-quality prognostic models to optimize patient outcomes.

Uptake of Clinical Prognostic Tools in COPD Exacerbations Requiring Hospitalisation

Clinical prognostic tools are used to objectively predict outcomes in many fields of medicine. Whilst over 400 have been developed for use in chronic obstructive pulmonary disease (COPD), only a minority have undergone full external validation and just one, the DECAF score, has undergone an implementation study supporting use in clinical practice. Little is known about how such tools are used in the UK. We distributed surveys at two time points, in 2017 and 2019, to hospitals included in the Royal College of Physicians of London national COPD secondary care audit program. The survey assessed the use of prognostic tools in routine care of hospitalized COPD patients. Hospital response rates were 71/196 in 2017 and 72/196 in 2019. The use of the DECAF and PEARL scores more than doubled in decisions about unsupported discharge (7%–15.3%), admission avoidance (8.1%–17%) and readmission avoidance (4.8%–13.1%); it more than tripled (8.8%–27.8%) in decisions around hospital-at-home or early supported discharge schemes. In other areas, routine use of clinical prognostic tools was uncommon. In palliative care decisions, the use of the Gold Standards Framework Prognostic Indicator Guidance fell (5.6%–1.4%). In 2017, 43.7% of hospitals used at least one clinical prognostic tool in routine COPD care, increasing to 52.1% in 2019. Such tools can help challenge prognostic pessimism and improve care. To integrate these further into routine clinical care, future research should explore current barriers to their use and focus on implementation studies. Supplemental data for this article is available online at https://dx.doi.org/10.1080/15412555.2021.1959540

Low performance of prognostic tools for predicting dialysis in elderly people with advanced CKD.

Clinical decision-making about care plans can be difficult for very elderly people with advanced chronic kidney disease (CKD). Current guidelines propose the use of prognostic tools predicting end stage renal disease (ESRD) to assist in a patient-centered shared decision-making approach. Our objective was to evaluate the existing risk model scores predicting ESRD, from data collected for a French prospective multicenter cohort of mainly octogenarians with advanced CKD. We performed a rapid review to identify the risk model scores predicting ESRD developed from CKD patient cohorts and evaluated them with data from a prospective multicenter French cohort of elderly (> 75years) patients with advanced CKD (estimated glomerular filtration rate [eGFR] < 20mL/min/1.75m2), followed up for 5years. We evaluated these scores (in absolute risk) for discrimination, calibration and the Brier score. For scores using the same time frame, we made a joint calibration curve and compared areas under the curve (AUCs). The PSPA cohort included 573 patients; their mean age was 83years and their median eGFR was 13mL/min/1.73m2. At the end of follow-up, 414 had died and 287 had started renal replacement therapy (RRT). Our rapid review found 12 scores that predicted renal replacement therapy. Five were evaluated: the TANGRI 4-variable, DRAWZ, MARKS, GRAMS, and LANDRAY scores. No score performed well in the PSPA cohort: AUCs ranged from 0.57 to 0.65, and Briers scores from 0.18 to 0.25. The low predictiveness for ESRD of the scores tested in a cohort of octogenarian patients with advanced CKD underlines the need to develop new tools for this population.

Organophosphate poisoning at Chris Hani Baragwanath Academic Hospital 2012 - 2015

Background. Patients with acute organophosphate poisoning are frequently admitted to the Chris Hani Baragwanath Academic Hospital (CHBAH), and yet there is little literature assessing aspects of these admissions. Objectives . To determine the demographic profile, common clinical and biochemical findings, use of prognostic tools (APACHE II), management and outcome of adult patients admitted to the high care area (HCA) and intensive care unit (ICU) at CHBAH. Methods . A retrospective data analysis of hospital records for 129 patients admitted to the HCA and ICU at CHBAH for the period 2012 - 2015 was undertaken. The demographic profiles and clinical and biochemical presentations of the patients were determined, together with their subsequent management and outcomes. Use of the APACHE II score as a prognostic tool was evaluated, and the average enzyme inhibition levels demonstrated by the patients was assessed. Results. The median age of the group was 30 years, with 68.2% being male. The most common clinical finding was pinpoint pupils (96.1%) followed by a Glasgow Coma Score &lt;13 (85.3%), fasciculations (60.5%), diarrhoea (37.2%) and seizures (10.1%). Admissions to the HCA (52.7%) predominated, with the majority of patients requiring ventilator support (99.2%). The mean (SD) duration of stay was 6.8 days for ICU (6.4) and 3.7 days for HCA (5.2). The overall mortality rate was 5.4%. Standard treatment was intravenous atropine. Blood results reflected low levels of acetylcholinesterase enzyme activity. The APACHE II score was underutilised. Conclusion. The findings of the study underscore the frequent use of organophosphate compounds in our area. Further studies across the country will help to highlight the magnitude of the consequences of organophosphate poisoning, as well as the burden imposed on limited healthcare resources.

Organophosphate poisoning at Chris Hani Baragwanath Academic Hospital 2012 - 2015.

Background Patients with acute organophosphate poisoning are frequently admitted to the Chris Hani Baragwanath Academic Hospital (CHBAH), and yet there is little literature assessing aspects of these admissions. Objectives To determine the demographic profile, common clinical and biochemical findings, use of prognostic tools (APACHE II), management and outcome of adult patients admitted to the high care area (HCA) and intensive care unit (ICU) at CHBAH. Methods A retrospective data analysis of hospital records for 129 patients admitted to the HCA and ICU at CHBAH for the period 2012 - 2015 was undertaken. The demographic profiles and clinical and biochemical presentations of the patients were determined, together with their subsequent management and outcomes. Use of the APACHE II score as a prognostic tool was evaluated, and the average enzyme inhibition levels demonstrated by the patients was assessed. Results The median age of the group was 30 years, with 68.2% being male. The most common clinical finding was pinpoint pupils (96.1%) followed by a Glasgow Coma Score <13 (85.3%), fasciculations (60.5%), diarrhoea (37.2%) and seizures (10.1%). Admissions to the HCA (52.7%) predominated, with the majority of patients requiring ventilator support (99.2%). The mean (SD) duration of stay was 6.8 days for ICU (6.4) and 3.7 days for HCA (5.2). The overall mortality rate was 5.4%. Standard treatment was intravenous atropine. Blood results reflected low levels of acetylcholinesterase enzyme activity. The APACHE II score was underutilised. Conclusion The findings of the study underscore the frequent use of organophosphate compounds in our area. Further studies across the country will help to highlight the magnitude of the consequences of organophosphate poisoning, as well as the burden imposed on limited healthcare resources.

Use of Prognostic Tools in the Hospital, Assessment of Factors Behind Their Use or lack Thereof Through a Physician-Oriented Survey

Physician's use of prognostic tools may help to decide on the intensity of therapies provided and communicate with patients and their caregivers in a timely fashion. However, literature that describes knowledge, perceived limitations and overall use of these tools by doctors is lacking. By way of a physician survey, we attempted to look at the use of prognostic tools in our community of doctors in our department of internal medicine. Our results showed that overall physicians have superficial knowledge of prognostic tools. We also discovered that physicians believe these tools to be helpful, yet their availability is compromised by lack of exposure during formative years, their cumbersome structure and the impracticalities of remembering them at bedside.

Hodgkin's lymphoma therapy: past, present, and future

Importance of the field: The treatment of Hodgkin's lymphoma (HL) with the use of radiotherapy and systemic chemotherapy has been one of the success stories of modern oncology. HL therapy has been the paradigm for the systematic evaluation of different curative modalities, resulting in cure for the majority of patients. The current focus is on designing initial therapeutic strategies that retain efficacy and minimize long-term toxicity. Appropriate use of pathologic, clinical, biologic and radiologic prognostic factors in identification of aggressive HL is paramount in designing a successful therapeutic strategy.Areas covered in this review: This review addresses the current and future use of prognostic tools, including PET scanning and other biomarkers, in identifying patients with aggressive HL, with reference to publications from the last two decades. The current standard approaches with the use of combined modality therapy and systemic chemotherapy as well as the promising role of future response-adapted strategies is reviewed.What the reader will gain: The reader will obtain a comprehensive review of risk assessment strategies as well as current and investigational therapeutic approaches in the management of HL.Take home message: In HL, appropriate utilization of risk assessment strategies is required to maximize therapeutic outcomes while minimizing toxicity, especially long-term toxicity. Response-adapted therapy utilizing PET has the potential to profoundly improve the therapeutic landscape in HL.