Patient profiled data for treatment decision-making: valuable as an add-on to hepatitis C clinical guidelines?

BACKGROUND AND AIMS: Systematic reviews and medical guidelines are widely used in clinical practice. However, these are often not up-to-date and focussed on the average patient. We therefore aimed to evaluate a guideline add-on, TherapySelector (TS), which is based on monthly updated data of all available high-quality studies, classified in specific patient profiles. METHODS: We evaluated the TS for the treatment of hepatitis C (HCV) in an international cohort of patients treated with direct-acting antivirals between 2015 and 2020. The primary outcome was the number of patients receiving one of the two preferred treatment options of the HCV TS, based on the highest level of evidence, cure rate, absence of ribavirin-associated adverse effects, and treatment duration. RESULTS: We enrolled 567 patients. The number of patients treated with one of the two preferred treatment options according to the HCV TS ranged between 27% (2015) and 60% (2020; p < 0.001). Most of the patients received a regimen with a longer treatment-duration (up to 34%) and/or addition of ribavirin (up to 14%). The effect on the expected cure-rate was minimal (1-6% higher) when the first preferred TherapySelector option was given compared to the actual treatment. CONCLUSIONS: Medical decision-making can be optimised by a guideline add-on; in HCV its use appears to minimise adverse effects and cost. The use of such an add-on might have a greater impact in diseases with suboptimal cure-rates, high costs or adverse effects, for which treatment options rely on specific patient characteristics.

Profiles, Correlates and Outcomes Among Patients Experiencing an Onset of Mental Disorder Based on Outpatient Care Received Following Index Emergency Department Visits.

OBJECTIVE: This 5-year longitudinal study evaluated patients with an onset of mental disorder (MD) following index emergency department (ED) visits, in terms of (1) patient profiles based on 12-month outpatient follow-up care received, (2) sociodemographic and clinical correlates, and (3) adverse health outcomes for the subsequent 2 years. METHODS: Data from administrative databases were collected for 2541 patients with an onset of MD, following discharge from Quebec ED. Latent class analysis was performed to identify patient profiles based on the adequacy of follow-up care after ED discharge. Bivariate analyses examined associations between class membership and sociodemographic and clinical correlates, high ED use (3 + visits/yearly), hospitalizations, and suicidal behaviors. RESULTS: Five classes of patients were identified. Class 1, the smallest, labeled "patient psychiatrist only," included mainly young patients with serious MD. Classes 2 and 3, roughly 20%, were labeled "high use of patient general practitioner (GP) and psychiatrist" and "low use of patient GP and psychiatrist," respectively. Both included patients with complex MD, but Class 2 had more women and older patients with chronic physical illnesses. The 2 largest classes were labeled "no usual patient service provider" (Class 5) and "patient GP only" (Class 4). Class 5 included more younger men with substance-related disorders, while Class 4 had the older patients living in rural areas, many with common MD and chronic physical illnesses. Class 3 patients had the poorest outcomes, followed by Classes 1 and 2, while Classes 4 and 5 had the best outcomes. CONCLUSIONS: Results revealed that nearly 40% of patients experiencing an onset of MD received little or no outpatient care following ED discharge. Higher severity or complexity of MD and, to a lesser extent, no or low GP follow-up may explain these adverse outcomes. More adequate, continuous care, including collaborative care, is needed for these vulnerable, high-needs patients.

Profiles of high emergency department users with mental disorders.

BACKGROUND: This study aimed to (1) identify profiles of high emergency department (ED) users (3+ visits/year) among 5409 patients with mental disorders (MD) based on their patterns of ED use and clinical characteristics; (2) identify sociodemographic and service use correlates linked to high ED user profiles; and (3) assess risks of death in a 12-month follow-up period, controlling for sex and age. METHODS: Using varied medico-administrative databases, this 5-year study collected patient data for six Quebec (Canada) ED. Latent class analysis was used to distinguish profiles of high ED users for a 3-year period, while bivariate analyses subsequently assessed associations between high ED user profiles and sociodemographic and service use correlates. Survival analysis were also applied to examine relationships between profile memberships of high ED users and risk of death in the 12 months following period of high ED use. RESULTS: Three profiles of high ED use were identified, Profile 1: 3-year recurrent very high ED users (10+ ED visits/year), Profile 2: 2-year recurrent high ED users, and Profile 3: 1-year high ED users. Profiles differed according to severity of health conditions, intensity of service use, particularly frequent hospitalizations, and risk of death: high in Profile 1, moderate in Profile 2, and low in Profile 3. Compared to 1-year high ED users, 3-year recurrent very high ED users and 2-year recurrent high ED users had poorer health and higher risk of death. CONCLUSIONS: More targeted interventions may be improved for especially recurrent high ED users and recurrent very high ED use.

Profiling for the good: Patient profile tests and informed, autonomous decision making.

It is commonly held that, given multiple medically permissible ways of proceeding, each with a different impact on the patient's future, it is extremely important, and part of respecting patient autonomy, that patients not be under substantial pressure to defer to their physicians' presumed authority. Some, however, worry that the focus on patient autonomy can be detrimental and that, at least in cases where it is hard to grasp what it is really like to live with certain outcomes without any first-hand or second-hand experience, it is best if patient choice is firmly directed, or at least effectively nudged, by the recommendation of an experienced medical professional. The idea seems to be that, since physicians cannot get their patients to promptly assimilate a large amount of information and experience, physicians must, if they are to really help their patients make good decisions in hard cases, exert non-argumentative influence on them. But this neglects an interesting possibility, namely the possibility of influencing patients by providing them with evidence regarding what decisions have proved most satisfactory for patients with their profile. Approximations of patient profile tests are already employed in medical practice. But the potential of the profile-test approach in medical practice (and research) has been obscured by ongoing debate that neglects the significance of the approach with respect to the apparent dilemma faced by patients who need to make informed, autonomous decisions but cannot be expected to fully assimilate, in short order, the knowledge and experience of their physicians.

[Decision criteria and patient characteristics for patient-oriented treatment of field cancerization : Standardized algorithm for personalized treatment concepts]. / Entscheidungskriterien und Patientencharakteristika zur patientenorientierten Therapie der Feldkanzerisierung : Ein standardisierter Bewertungsalgorithmus für individuelle Behandlungskonzepte.

BACKGROUND: Actinic keratosis (AK), which frequently affects larger skin areas (field cancerization), is characterized by chronic course. Weighing therapy-specific advantages and disadvantages of field-oriented therapy for individual patients is challenging. OBJECTIVES: The main objective was the development of patient-oriented decision criteria for the pragmatic classification of field-directed AK treatment options in patients with a predisposition for field cancerization (patient types 1-3). MATERIALS AND METHODS: The development of the decision criteria and patient typology was based on a nominal respectively structured multilevel group process. The developed algorithm was then subsequently applied for the systematic evaluation of field-directed AK therapies. RESULTS: Patient-relevant criteria for the treatment decision included (among others): effectiveness, selectivity, safety, duration of therapy, cosmesis, patient preference and comorbidities. With regard to the decision criteria and patient types in which field therapy was the treatment of choice, daylight photodynamic therapy notably met the requirement profile. CONCLUSION: The definition of patient-relevant and therapy-related decision criteria in AK field therapy allows a systematic yet practice-oriented approach to classify specific treatment options and to derive individual treatment decisions.

Investigating the healthcare pathway through patients' experience and profiles: implications for breast cancer healthcare providers.

BACKGROUND: Healthcare systems are facing many changes. Particularly, patients are more engaged in the care process. The medical perspective of the process is insufficient to provide patients with high quality care and service personalisation. This research presents an attempt to complete this medical perspective through an experiential perspective, especially for chronic diseases such as cancer. We investigated patients' experiences and profiles to reach a deeper understanding of their needs and expectations when they confront the disease. The objectives of this research were to model the key stages underling the patient pathway and to identify the challenging touch points of the interactions between patients and healthcare providers. Bringing together findings of patient experience, pathway, and profiles would help all the stakeholders involved to develop better practices for the healthcare process. METHODS: A qualitative observational nethnography on a French specialized forum for breast cancer patients "les Impatientes" was conducted. A total of 967 reviews were collected over a complete year period from all over France. Thematic and lexicometric content analysis were performed according to the experience dimensions, the pathway stages and touch points, as well as the patients' profiles. RESULTS: Data analysis shows that the healthcare pathway experienced by the patients is built around three stages. The discovery stage is closely related to the emotional dimension regarding the patient and physician relationship. The examination stage is characterized by a more technical and informational needs for the types of treatments. The follow-up and survivorship stage illustrates the patients' need to assess the treatments' effectiveness and the quality of the follow-up. Moreover, three profiles of patients were identified. The newcomers, the altruists and the autonomous are characterized by different attitudes depending on the stage of the healthcare pathway they were living. CONCLUSIONS: Our research presents an original modelling of the patient pathway and profiles beyond the medical process. It gives practical tracks to improve the healthcare pathway. Patients expect healthcare providers to integrate and strengthen several challenging touch points in order to create satisfactory patient experiences and high quality service.

Patient profiles as organizing HIV clinicians' ART adherence management: a qualitative analysis.

The effectiveness of antiretroviral therapy (ART) depends on optimal clinical management and patient adherence. Little is known about patient characteristics that clinicians consider in the management of ART adherence. Exploring this issue, five focus groups were conducted with 31 HIV-clinicians from across France. A qualitative typological analysis suggests that clinician management of patient adherence is based on characteristics that coalesce into seven patient profiles. For the "passive" patient, described as taking ART exactly as prescribed without questioning their doctor's expertise, a directive and simple management style was preferred. The "misleading" patient is characterized as concerned with social desirability and as reporting no adherence difficulties for fear of displeasing their doctor. If clinical outcomes are suboptimal, the clinicians' strategy is to remind them of the importance of open patient-clinician communication. The "stoic" patient is described as requesting and adequately taking the most potent ART available. Here, clinicians emphasize assessment of side effects, which the patient may minimize. The "hedonistic" patient's festive lifestyle and sexual risk-taking are seen as compromising adherence; with them, clinicians stress the patient's responsibility for their own health and that of their sexual partners. The "obsessive" patient is portrayed as having an irrational fear of ART failure and an inability to distinguish illusory from genuine adherence barriers. With this patient, clinicians seek to identify the latter. The "overburdened" patient is recognized as coping with life priorities that interfere with adherence and, with them, a forgiving ART is favored. The "underprivileged" patient is presented as having limited education, income and housing. In this case, clinicians seek to improve the patient's living conditions and access to care. These results shed light on HIV clinicians' ART adherence management. The value of these profiles for HIV care and patients should be investigated.

Developing a patient-reported outcome measure for HIV care on perceived barriers to antiretroviral adherence: assessing the needs of HIV clinicians through qualitative analysis.

PURPOSE: To identify HIV clinicians' needs for the clinical use of a new patient-reported outcome measure (PRO) on barriers to antiretroviral therapy (ART) adherence. METHODS: In 2015, five focus groups with 31 clinicians from France were transcribed, coded with Atlas.ti, and submitted to a typological analysis. RESULTS: The analysis identified seven patient profiles, each tied to distinct barriers to adherence and to specific needs for the PRO's content, data collection and transmission. Clinicians preferred, for the patient who is: (1) 'passive,' that the PRO collect information on ART knowledge, to ensure that the prescription's instructions are being respected; (2) 'misleading,' that it be able to detect adherence to ART and socially desirable responses; (3) 'stoic,' that questions challenge the patient to recognize treatment-specific side effects; (4) 'hedonistic,' that the PRO contains content on lifestyle and risk-taking; (5) 'obsessive,' that the PRO captures quality of life and stressful life events; (6) 'overburdened,' that the PRO provides information on the person's home environment, socioeconomic status and cultural constraints. For all or most patient profiles, the clinicians wished that the PRO be completed, minimally, prior to the medical consultation and to receive alerts, under varying conditions, when problematic scores were detected. Depending on the profile, there was preference for the inclusion of open-ended questions and transmission of cross-sectional, periodic or longitudinal PRO data. CONCLUSION: Overall, this study's findings suggest that to support the clinical management of ART adherence, our PRO must meet the needs of a wide variety of patients and must perform multiple functions.

A comparative retrospective exploration of the profiles of patients in South Africa diagnosed with epileptic and psychogenic non-epileptic seizures.

Psychogenic non-epileptic seizures (PNES) have a high prevalence globally but the accurate diagnosis of this condition still remains a challenge. This is particularly the case in countries where there is scarce expertise and insufficient affordable medical facilities to which patients have access. The rate of PNES diagnosis in epilepsy units is typically within the range of 20 to 30%. In the context of developing countries, this rate tends to be higher and increases demand on the existing scarce health care capacities. Although the profiling of patients with different seizure presentations is essential for informing appropriate treatment, to date there has been no comparative analysis of the profiles of patients with PNES and epilepsy in South Africa. The aim of the present study was to explore retrospectively the demographic and medication characteristics of these patients and to compare these characteristics to those reported in patient populations from other countries and regions. The total sample of 246 participants included 85 (35%) male and 161 (65%) female patients who were admitted to the Epilepsy Monitoring Unit (EMU) at Milpark Hospital, South Africa. Following the video-EEG monitoring assessment, 123 patients (50%) were diagnosed with PNES, and for 123 patients (50%) the diagnosis of epilepsy was confirmed. The results indicated that the demographic profiles of the groups of patients with epilepsy and PNES were similar with reference to age and self-ascribed ethnicity. In both groups, the majority of the patients were females, but proportionally their prevalence was higher in the PNES patient group than in the epilepsy patient group, which is compatible with the trends found in the PNES patient populations internationally. Pre-diagnostically, the type and the number of medications prescribed to patients with PNES and epilepsy were comparable. Subsequent to the diagnosis at the EMU, there was a significant reduction of overall medications in each group, but this reducton was more pronounced in the group with PNES. It is concluded that the rate of misdiagnosis of PNES in South Africa surpasses the rates reported for the patient populations in other countries and is one of the highest documented worldwide. Considering that post-diagnostically, there was reduction in central nervous system (CNS) medications as well as anti-epileptic drugs (AEDs) in both patients with epilepsy and those with PNES, it is likely that pre-diagnostically a significant proportion of all patients were over medicated. Compared to the epilepsy diagnosis, the PNES diagnosis resulted in a more substantial reduction of medication. These findings outline important dimensions of the diagnostic and medication treatment practices of epilepsy and PNES and point to the urgent need to improve these practices in South Africa and the African continent.

French patients on daily hemodialysis: clinical characteristics and treatment trajectories.

BACKGROUND: Increasing the weekly frequency of hemodialysis sessions has positive effects, on the control of several biological data of patients. However, knowledge about Daily HemoDialysis (DHD) practices is limited in France. The aim of the present study was to describe the characteristics and treatment trajectories of all French patients undergoing DHD. METHODS: All patients older than 18 years who started DHD between 2003 and 2012 in France were included and followed until December 31, 2013. The patients' demographic and clinical characteristics and treatment modalities were extracted from the French Renal Epidemiological and Information Network (REIN) registry. RESULTS: During the inclusion period, 753 patients started DHD in France. Based on their median age (64 years), patients were classified in two groups: "old" group (≥64 years) and "young" group (<64 years). Patients in the old group had more comorbidities than in the young group: 48 % had diabetes (vs 29 % in the young group), 17 % an active malignancy (vs 10 %) and 80 % ≥1 cardiovascular disease (vs 41 %). Concerning patients' treatment trajectories, 496 (66 %) patients started with another dialysis before switching to DHD and 257 (34 %) directly with DHD. At the end of the follow-up, 69 % of patients in the old group were dead (27.4 % in the young group) and kidney transplantation was more frequent in the young group (30.4 % vs 0.5 %). CONCLUSION: In France, DHD is proposed not only to young in rather good clinical conditions and waiting for kidney transplantation, but also to old and frail patients with higher mortality.

Recognition of patients with medically unexplained physical symptoms by family physicians: results of a focus group study.

BACKGROUND: Patients with medically unexplained physical symptoms (MUPS) form a heterogeneous group and frequently attend their family physician (FP). Little is known about how FPs recognize MUPS in their patients. We conducted a focus group study to explore how FPs recognize MUPS and whether they recognize specific subgroups of patients with MUPS. Targeting such subgroups might improve treatment outcomes. METHODS: Six focus groups were conducted with in total 29 Dutch FPs. Two researchers independently analysed the data applying the principles of constant comparative analysis in order to detect characteristics to recognize MUPS and to synthesize subgroups. RESULTS: FPs take into account various characteristics when recognizing MUPS in their patients. More objective characteristics were multiple MUPS, frequent and long consultations and many referrals. Subjective characteristics were negative feelings towards patients and the feeling that the FP cannot make sense of the patient's story. Experience of the FP, affinity with MUPS, consultation skills, knowledge of the patient's context and the doctor-patient relationship seemed to influence how and to what extent these characteristics play a role. Based on the perceptions of the FPs we were able to distinguish five subgroups of patients according to FPs: 1) the anxious MUPS patient, 2) the unhappy MUPS patient, 3) the passive MUPS patient, 4) the distressed MUPS patient, and 5) the puzzled MUPS patient. These subgroups were not mutually exclusive, but were based on how explicit and predominant certain characteristics were perceived by FPs. CONCLUSIONS: FPs believe that they can properly identify MUPS in their patients during consultations and five distinct subgroups of patients could be distinguished. If these subgroups can be confirmed in further research, personalized treatment strategies can be developed and tested for their effectiveness.

Design organization and clinical processes around patient characteristics: Evidence from a multiple case study of Hemophilia.

Background: There is growing evidence of the relevance of designing organization of care around patient characteristics; this is especially true in the case of complex chronic diseases.Purpose: The goal of the paper - that focuses on the analysis of the clinical condition hemophilia in three different centers - is to address two different research questions:1. How can we define, within the same clinical condition, different patient profiles homogeneous in terms of intensity of service required (e.g. number of visits or diagnostics)? 2. What are the conditions to re-organize care around these patient profiles in a multidisciplinary and coordinated manner?Research design: The authors have used a multiple case study approach combining both qualitative and quantitative methodologies; in particularly the semi-structured interviews and the direct observation were aimed to map the process in order to come up with an estimate of the cost of the full cycle of care.Study sample: The research methodology has been applied consistently in three different centers. The selection of the structures has been based on two main different criteria: (i) high standards regarding both organizational and clinical aspects and (ii) willingness from management, nurses and physicians to provide data.Results: The study clearly shows that different patient profiles - within the same clinical condition - trigger a different set of diagnostic and therapeutic activities. It is, thus, important considering patient characteristics in the development and implementation of clinical pathways and this will imply relevant differences in terms of organizational and economic impact.Conclusions: These process-based analyses are very much critical especially if we want to move to a bundled and integrated payment system but, as shown by this study itself, require a lot of time and efforts since our healthcare information systems are still fragmented and vertically designed.

Management of Glucose-Lowering Therapy in Older Adults with Type 2 Diabetes: Challenges and Opportunities.

The population of older adults (≥65 years) with type 2 diabetes mellitus (T2DM) is diverse, encompassing individuals with varying functional capabilities, living arrangements, concomitant medical conditions, and life expectancies. Hence, their categorization into different patient profiles (ie, good health, intermediate health, poor health) may aid in clinical decision-making when establishing glycemic goals and pharmacological treatment strategies. Further granularity in assessing each patient profile through interdisciplinary collaboration may also add precision to therapeutic and monitoring decisions. In this review, we discuss with a multidisciplinary approach how to deliver the best benefit from advanced diabetes therapies and technologies to older adults with T2DM according to each patient profile. There remain however several areas that deserve further research in older adults with T2DM, including the efficacy and safety of continuous glucose monitoring and automated insulin delivery systems, the switch to once-weekly insulin, the effectiveness of multidisciplinary care models, and the use of supported telemedicine and remote blood glucose monitoring in the oldest-old (≥85 years) who particularly require the assistance of others.

Profiling of patients with type 2 diabetes based on medication adherence data.

Introduction: Type 2 diabetes mellitus (T2DM) is a complex, chronic disease affecting multiple organs with varying symptoms and comorbidities. Profiling patients helps identify those with unfavorable disease progression, allowing for tailored therapy and addressing special needs. This study aims to uncover different T2DM profiles based on medication intake records and laboratory measurements, with a focus on how individuals with diabetes move through disease phases. Methods: We use medical records from databases of the last 20 years from the Department of Endocrinology and Diabetology of the University Medical Center in Maribor. Using the standard ATC medication classification system, we created a patient-specific drug profile, created using advanced natural language processing methods combined with data mining and hierarchical clustering. Results: Our results show a well-structured profile distribution characterizing different age groups of individuals with diabetes. Interestingly, only two main profiles characterize the early 40-50 age group, and the same is true for the last 80+ age group. One of these profiles includes individuals with diabetes with very low use of various medications, while the other profile includes individuals with diabetes with much higher use. The number in both groups is reciprocal. Conversely, the middle-aged groups are characterized by several distinct profiles with a wide range of medications that are associated with the distinct concomitant complications of T2DM. It is intuitive that the number of profiles increases in the later age groups, but it is not obvious why it is reduced later in the 80+ age group. In this context, further studies are needed to evaluate the contributions of a range of factors, such as drug development, drug adoption, and the impact of mortality associated with all T2DM-related diseases, which characterize these middle-aged groups, particularly those aged 55-75. Conclusion: Our approach aligns with existing studies and can be widely implemented without complex or expensive analyses. Treatment and drug use data are readily available in healthcare facilities worldwide, allowing for profiling insights into individuals with diabetes. Integrating data from other departments, such as cardiology and renal disease, may provide a more sophisticated understanding of T2DM patient profiles.

Factors Affecting Quality of Life in Zygomatic Fractures: An Original Research.

Introduction: Zygoma is one of the facial bones that are impacted in the accidents. Hence, we aim to evaluate the patient's profiles in the fracture associated with zygomatic bone. Materials and Methods: We conducted a prospective clinical study with 60 subjects who were divided equally into cases (30) and controls (30); controls were general population and the cases underwent surgery of zygomatic complex fracture. Health-related quality of life (HRQoL) was assessed by the means of the questionnaire. The values were compared for the significance keeping P < 0.05 as significant. Results: The preoperative 15D score was lesser for cases than controls. Soon after surgery, it was statistically least and after a month, the mean score surpassed the controls. Infraorbital sensory loss was seen even after 6 months. Conclusions: As expected, the HRQoL decreases only to improve after the surgery. However, the infra-orbital nerve sensory loss may continue for over 6 months after the zygomatic complex fracture.

Validation of Algorithms to Identify Acute Myocardial Infarction, Stroke, and Cardiovascular Death in German Health Insurance Data.

Purpose: Validation of outcomes allows measurement of and correction for potential misclassification and targeted adjustment of algorithms for case definition. The purpose of our study was to validate algorithms for identifying cases of acute myocardial infarction (AMI), stroke, and cardiovascular (CV) death using patient profiles, ie, chronological tabular summaries of relevant available information on a patient, extracted from pseudonymized German claims data. Patients and Methods: Based on the German Pharmacoepidemiological Research Database (GePaRD), 250 cases were randomly selected (50% males) for each outcome between 2016 and 2017 based on the inclusion criteria age ≥50 years and continuous insurance ≥1 year and applying the following algorithms: hospitalization with a main diagnosis of AMI (ICD-10-GM codes I21.- and I22.-) or stroke (I63, I61, I64) or death with a hospitalization in the 60 days before with a main diagnosis of CV disease. Patient profiles were built including (i) age and sex, (ii) hospitalizations incl. diagnoses, procedures, discharge reasons, (iii) outpatient diagnoses incl. diagnostic certainty, physician specialty, (iv) outpatient encounters, and (v) outpatient dispensings. Using adjudication criteria based on clinical guidelines and risk factors, two trained physicians independently classified cases as "certain", "probable", "unlikely" or "not assessable". Positive predictive values (PPVs) were calculated as percentage of confirmed cases among all assessable cases. Results: For AMI, the overall PPV was 97.6% [95% confidence interval 94.8-99.1]. The PPV for any stroke was 94.8% [91.3-97.2] and higher for ischemic (98.3% [95.0-99.6]) than for hemorrhagic stroke (86.5% [76.5-93.3]). The PPV for CV death was 79.9% [74.4-84.4]. It increased to 91.7% [87.2-95.0] after excluding 32 cases with data insufficient for a decision. Conclusion: Algorithms based on hospital diagnoses can identify AMI, stroke, and CV death from German claims data with high PPV. This was the first study to show that German claims data contain information suitable for outcome validation.

Development and Validation of a New Multiparametric Random Survival Forest Predictive Model for Breast Cancer Recurrence with a Potential Benefit to Individual Outcomes.

Purpose: Breast cancer (BC) is a multi-factorial disease. Its individual prognosis varies; thus, individualized patient profiling is instrumental to improving BC management and individual outcomes. An economical, multiparametric, and practical model to predict BC recurrence is needed. Patients and Methods: We retrospectively investigated the clinical data of BC patients treated at the Third Affiliated Hospital of Sun Yat-sen University and Liuzhou Women and Children's Medical Center from January 2013 to December 2020. Random forest-recursive feature elimination (run by R caret package) was used to determine the best variable set, and the random survival forest method was used to develop a predictive model for BC recurrence. Results: The training and validations sets included 623 and 151 patients, respectively. We selected 14 variables, the pathological (TNM) stage, gamma-glutamyl transpeptidase, total cholesterol, Ki-67, lymphocyte count, low-density lipoprotein, age, apolipoprotein B, high-density lipoprotein, globulin, neutrophil count to lymphocyte count ratio, alanine aminotransferase, triglyceride, and albumin to globulin ratio, using random survival forest (RSF)-recursive feature elimination. We developed a recurrence prediction model using RSF. Using area under the receiver operating characteristic curve and Kaplan-Meier survival analyses, the model performance was determined to be accurate. C-indexes were 0.997 and 0.936 for the training and validation sets, respectively. Conclusion: The model could accurately predict BC recurrence. It aids clinicians in identifying high-risk patients and making treatment decisions for Breast cancer patients in China. This new multiparametric RSF model is instrumental for breast cancer recurrence prediction and potentially improves individual outcomes.

Machine Learning for Screening Microvascular Complications in Type 2 Diabetic Patients Using Demographic, Clinical, and Laboratory Profiles.

Microvascular complications are one of the key causes of mortality among type 2 diabetic patients. This study was sought to investigate the use of a novel machine learning approach for predicting these complications using only the patient demographic, clinical, and laboratory profiles. A total of 96 Bangladeshi participants with type 2 diabetes were recruited during their routine hospital visits. All patient profiles were assessed by using a chi-squared (χ2) test to statistically determine the most important markers in predicting three microvascular complications: cardiac autonomic neuropathy (CAN), diabetic peripheral neuropathy (DPN), and diabetic retinopathy (RET). A machine learning approach based on logistic regression, random forest (RF), and support vector machine (SVM) algorithms was then developed to ensure automated clinical testing for microvascular complications in diabetic patients. The highest prediction accuracies were obtained by RF using diastolic blood pressure, albumin-creatinine ratio, and gender for CAN testing (98.67%); microalbuminuria, smoking history, and hemoglobin A1C for DPN testing (67.78%); and hemoglobin A1C, microalbuminuria, and smoking history for RET testing (84.38%). This study suggests machine learning as a promising automated tool for predicting microvascular complications in diabetic patients using their profiles, which could help prevent those patients from further microvascular complications leading to early death.

Clusters of conditions among US service members diagnosed with mild TBI from 2017 through 2019.

Background: Many US Military Service Members (SMs) newly diagnosed with mild Traumatic Brain Injury (mTBI) may exhibit a range of symptoms and comorbidities, making for a complex patient profile that challenges clinicians and healthcare administrators. This study used clustering techniques to determine if conditions co-occurred as clusters among those newly injured with mTBI and up to one year post-injury. Methods: We measured the co-occurrence of 41 conditions among SMs diagnosed with mTBI within the acute phase, one or three months post-mTBI diagnosis, and chronic phase, one year post-mTBI diagnosis. Conditions were identified from the literature, clinical subject matter experts, and mTBI care guidelines. The presence of conditions were based on medical encounters recorded within the military health care data system. Through a two-step approach, we identified clusters. Principal component analysis (PCA) determined the optimal number of clusters, and hierarchical cluster analyses (HCA) identified the composition of clusters. Further, we explored how the composition of these clusters changed over time. Results: Of the 42,018 SMs with mTBI, 23,478 (55.9%) had at least one condition of interest one-month post-injury, 26,831 (63.9%) three months post-injury, and 29,860 (71.1%) one year post injury. Across these three periods, six clusters were identified. One cluster included vision, cognitive, ear, and sleep disorders that occurred one month, three months, and one year post-injury. Another subgroup included psychological conditions such as anxiety, depression, PTSD, and other emotional symptoms that co-occurred in the acute and chronic phases post-injury. Nausea and vomiting symptoms clustered with cervicogenic symptoms one month post-injury, but later shifted to other clusters. Vestibular disorders clustered with sleep disorders and headache disorders one-month post-injury and included numbness and neuropathic pain one year post-injury. Substance abuse symptoms, alcohol disorders, and suicidal attempt clustered one year post-injury in a fifth cluster. Speech disorders co-occurred with headache disorders one month and one year post-injury to form a sixth cluster. Conclusion: PCA and HCA identified six distinct subgroups among newly diagnosed mTBI patients during the acute and chronic phases post-injury. These subgroups may help clinicians better understand the complex profile of SMs newly diagnosed with mTBI.

The Change of Fingolimod Patient Profiles over Time: A Descriptive Analysis of Two Non-Interventional Studies PANGAEA and PANGAEA 2.0.

(1) Background: Fingolimod (Gilenya®) was the first oral treatment for patients with relapsing-remitting multiple sclerosis (RRMS). Since its approval, the treatment landscape has changed enormously. (2) Methods: Data of PANGAEA and PANGAEA 2.0, two German real-world studies, were descriptively analysed for possible evolution of patient profiles and treatment behavior. Both are prospective, multi-center, non-interventional, long-term studies on fingolimod use in RRMS in real life. Data of 4229 PANGAEA patients (recruited 2011-2013) and 2441 PANGAEA 2.0 patients (recruited 2015-2018) were available. Baseline data included demographics, RRMS characteristics and disease severity. (3) Results: The mean age of PANGAEA and PANGAEA 2.0 patients was similar (38.8 vs. 39.2 years). Patients in PANGAEA 2.0 had shorter disease duration (7.1 vs. 8.2 years) and fewer relapses in the year before baseline (1.2 vs. 1.6). Disease severity at baseline estimated by EDSS and SDMT was lower in PANGAEA 2.0 patients compared to PANGAEA (EDSS difference 1.0 points; SDMT difference 3.3 points). (4) Conclusions: The results hint at an influence of changes in the treatment guidelines and the label on fingolimod patients profiles over time. Patients tended to have lower disease activity at fingolimod initiation, suggesting an earlier intervention. This indicates increased experience in using fingolimod for sub-optimally treated RRMS patients and a change in mindset towards an early treatment optimization.