Mediaboss Marketing

Apple began discussing integrating health sensors into future sports-oriented headphones in a patent application that was published back in April 2009 and filed in 2008. Apple's engineers noted at the time that "The sensor can also be other than (or in addition to) an activity sensor, such as a psychological or biometric sensors which could measure temperature, heartbeat, etc. of a user of the monitoring system." Fast forwarding to 2018, Apple decided to update their AirPods trademark by adding "wellness sensors" to its description, a telltale sign something was in-the-works. Then a series of patents surfaced in 2020-21 timeline covering health sensor for future AirPods (01,02&03). To top it all off, in June of this year, Apple's VP of Technology talked about health sensors on Apple Watch and possibly AirPods.

The latest development on this front came from Apple's Machine Learning (ML) Research team earlier this month in the form of a research paper. Apple notes, "In this paper, we take the first step towards developing a breathlessness measurement tool by estimating respiratory rate (RR) on exertion in a healthy population using audio from wearable headphones. Given this focus, such a capability also offers a cost-effective method to track cardiorespiratory fitness over time. While sensors such as thermistors, respiratory gauge transducers, and acoustic sensors provide the most accurate estimation of a persons breathing patterns, they are intrusive and may not be comfortable for everyday use. In contrast, wearable headphones are relatively economical, accessible, comfortable, and aesthetically acceptable."

Further into the paper, Apple clarifies: "All data was recorded using microphone-enabled, near-range headphones, specifically Apples AirPods. These particular wearables were selected because they are owned by millions and utilized in a wide array of contexts, from speaking on the phone to listening to music during exercise."

(Click on image to greatly Enlarge)

Below is a full copy of the research paper published by Apple's Machine Learning Research team in the form of a SCRBD document, courtesy of Patently Apple.

Machine Learning Team Paper on Respiratory Rates in Wearable Microphones by Jack Purcher on Scribd

While the paper doesn't discuss when these specialized sensors using machine learning techniques will be implemented in AirPods, it's clearly a positive development that Apple is well into the process of proving the value of adding such sensors to future AirPods.

Read the original post:
Apple's Machine Learning Research Team have Published a Paper on using Specialized Health Sensors in Future AirPods - Patently Apple

Introduction

Hepatocellular carcinoma (HCC), the fourth leading cause of cancer-related death worldwide, typically occurs in patients with chronic liver disease and is an aggressive disease with dismal prognosis.1 Over the past decades, improved surveillance programs and imaging techniques have led to early HCC (EHCC) diagnosis in 4050% of patients, at a stage amenable to potentially curative therapiesresection, transplantation or ablation.2,3 Generally, EHCC is expected to have an excellent outcome after radical therapies. Since total hepatectomy eliminates both the diseased liver and the tumor, liver transplantation (LT) offers the highest chance of cure, with a survival up to 70% at 10 years in selected cases, and remains the best treatment for EHCC.4 Unfortunately, the critical shortage of donor organs represents the main limitation of LT and results in long waiting times.

According to clinical practice guidelines, liver resection (LR) is the recommended first-line option for patients with EHCC and preserved liver function, although ablation is an alternative treatment modality.3,5,6 The prognosis following LR may vary even among patients with EHCC and two competing causes of death (tumor recurrence and liver dysfunction) both influence survival.7 Several HCC staging systems have been proposed to pair prognostic prediction with treatment allocation; however, these proposalssuch as Barcelona Clinic Liver Cancer (BCLC) staging, China Liver Cancer (CNLC) staging, Hong Kong Liver Cancer (HKLC) staging and Cancer of the Liver Italian Program (CLIP) scoreare not derived from surgically managed patients, except for the American Joint Committee on Cancer (AJCC) system and Japan Integrated Staging (JIS) score, and therefore exhibit modest prognostic accuracy for resected cases.69 A few prognostic models have been developed based on readily available patient and tumor characteristics; however, they are by nature outmoded and rigid tools because all determinants were examined by conventional statistical methods (ie, Cox proportional hazard regression) and assigned fixed weights.8,10 Hence, new strategies to improve outcome prediction and treatment selection are warranted for EHCC patients.

Machine learning (ML), a subfield of artificial intelligence, leverages algorithmic methods that enable computers to learn from on large-scale, heterogeneous datasets and execute a specific task without predefined rules.11 ML solutions such as gradient boosting machine (GBM) have outperformed regression modelling in a variety of clinical situations (eg, diagnosis and prognosis).1113 Nevertheless, the benefit of ML in predicting prognosis of patients with resected EHCC has yet to be fully explored. Accordingly, we assembled a large, international cohort of EHCC patients to design and evaluate a ML-based model for survival prediction, and compare its performance with existing prognostic systems.

Patients with EHCC, defined as tumor 5 cm and without evidence of extrahepatic disease or major vascular invasion,14 were retrospectively screened from two sources: (1) Medicare patients treated with surgical therapy (LR+LT) in the Surveillance, Epidemiology, and End Results (SEER) Program, a population-based database in the United States, between 2004 and 2015; (2) consecutive patients treated with LR at two high-volume hepatobiliary centers in China (First Affiliated Hospital of Nanjing Medical University and Wuxi Peoples Hospital) between 2006 and 2016. The inclusion criteria were (1) adult patients aged 20 years; (2) histology-confirmed HCC (International Classification of Diseases for Oncology, Third Edition, histology codes 8170 to 8175 for HCC and site code C22.0 for liver);15 (3) complete survival data and a survival of 1 month. The exclusion criteria were (a) missing information on the type of surgical procedure; (b) another malignant primary tumor prior to HCC diagnosis; (c) unknown cause of death. Patient selection process is summarized in the flow chart of Figure 1. This study protocol was approved by the Institution Review Board of First Affiliated Hospital of Nanjing Medical University and Wuxi Peoples Hospital. Written informed consent was waived because retrospective anonymous data were analyzed. Non-identified information was used in order to protect patient data confidentiality. This study was conducted in accordance with the Declaration of Helsinki.

Figure 1 Analytical framework for survival prediction. (A) Flow diagram of the study cohort details. (B) A machine learning pipeline to train, validate and test the model.

The endpoint selected to develop ML-based model was disease-specific survival (DSS), defined as the time from the date of surgery to the date of death from disease (tumor relapse or liver dysfunction). All deaths from any other cause were counted as non-disease-specific and censored at the date of the last follow-up. Follow-up protocol for Chinese cohort included physical examination, laboratory evaluation and dynamic CT or MRI of the chest and abdomen every 3 months during the first 2 years and every 6 months thereafter. The follow-up was terminated on August 15, 2020.

Electronic and paper medical records were reviewed in detail; all pertinent demographic and clinicopathologic data were abstracted on a standardized template. The following characteristics of interest were ascertained at the time of enrollment: age, gender, race, year of diagnosis, alpha-fetoprotein level, use of neoadjuvant therapy, tumor size, tumor number, vascular invasion, histological grade, liver fibrosis score, and type of surgery.

We deployed GBM, a decision tree-based ML algorithm that has gained popularity because of its performance and interpretability, to aggregate baseline risk factors and predict the likelihood of survival using the R package gbm. GBM algorithm16 assembles multiple base learners, in a step-wise fashion, with each successive learner fitting the residuals left over from previous learners to improve model performance: (1) , where is a base learner, typically a decision tree; (2) , where is optimized parameters in each base learner and is the weight of each base learner in the model. Each base learner may have different variables; variables with higher relative importance are utilized in more decision trees and earlier in the boosting algorithm. The model was trained using stratified 33-fold nested cross-validation (3 outer iterations and 3 inner iterations) on the training/validation cohort; a grid search of optimal hyper-parameter settings was run using the R package mlr. Figure 1 shows the ML workflow schematically.

Model discrimination was quantified using Harrells C-statistic and 95% confidence intervals [CIs] were assessed by bootstrapping. Calibration plots were used to assess the model fit. Decision curve analysis was used to determine the clinical net benefit associated with the adoption of the model.17

Differences between groups were tested using 2 test for categorical variables and MannWhitney U-test for continuous variables. Survival probabilities were assessed using the KaplanMeier method and compared by the Log rank test. The optimal cutoffs of GBM predictions were determined to stratify patients at low, intermediate, or high risk for disease-specific death by using X-tile software version 3.6.1 (Yale University School of Medicine, New Haven, CT).18 Propensity score matching (PSM) was used to balance the LR versus LT for EHCC in SEER cohort using 1:1 nearest neighbor matching with a fixed caliper width of 0.02. Cases (LR) and controls (LT) were matched on all baseline characteristics other than type of surgery using the R package MatchIt. All analyses were conducted using R software version 3.4.4 (www.r-project.org). Statistical significance was set at P<0.05; all tests were two-sided.

A total of 2778 EHCC patients (2082 males and 696 females; median age, 60 years; interquartile range [IQR], 5467 years) treated with LR were identified and divided into 1899 for the training/validation (SEER) cohort and 879 for the test (Chinese) cohort. Patient characteristics of the training/validation and test cohorts are summarized in Table 1. There were 625 disease-related deaths recorded (censored, 67.1%) during a median (IQR) follow-up time of 44.0 (26.074.0) months in the SEER cohort, and 258 deaths were recorded (censored, 70.6%) during a median (IQR) follow-up of 52.5 (35.876.0) months in the Chinese cohort. Baseline characteristics and post-resection survival differed between the cohorts.

Table 1 Baseline Characteristics in the Training/Validation and Test Cohorts

We investigated 12 potential model covariates using GBM algorithm. According to the results of nested cross-validation, we utilized 2000 decision trees sequentially, with at least 5 observations in the terminal nodes of the trees; the decision tree depth was optimized at 3, corresponding to 3-way interactions, and the learning rate was optimized at 0.01. Covariates with a relative influence greater than 5 (age, race, alpha-fetoprotein level, tumor size, multifocality, vascular invasion, histological grade and fibrosis score) were integrated into the final model developed to predict DSS (Figure 2A and B).

Figure 2 Overview of the machine-learning-based model. (A) Relative importance of the variables included in the model. (B) Illustrative example of the gradient boosting machine (GBM). GBM builds the model by combining predictions from stumps of massive decision-tree-base-learners in a step-wise fashion. GBM output is calculated by adding up the predictions attached to the terminal nodes of all 2000 decision trees where the patient traverses. (C) Performance of GBM model as compared with that of American Joint Committee on Cancer (AJCC) staging in the internal validation group. (D) Online model deployment based on GBM output.

The final GBM model demonstrated good discriminatory ability in predicting post-resection survival specific for EHCC, with a C-statistic of 0.738 (95% CI 0.7170.758), and outperformed the 7th and 8th edition of AJCC staging systems (P<0.001) in the training/validation cohort (Table 2). The internal validation group was the 33-fold nested cross-validation of the final model of the training cohort with 211 patients in each fold. For the composite outcome, the GBM model yielded a median C-statistic of 0.727 (95% CI 0.7060.761) and performed better than AJCC staging systems (P<0.05) in the internal validation group (Figure 2C). In the test cohort, the GBM model provided a C-statistic of 0.721 (95% CI, 0.6890.752) in predicting DSS after resection of EHCC and was clearly superior to AJCC, BCLC, CNLC, HKLC, CLIP and JIS systems (P<0.05). Note that prediction scores differed between training/validation and test sets (P<0.001) (Figure S1). The discriminatory performance of ML-based model exceeded those of AJCC staging systems even in sub-cohorts stratified by covariate integrity (complete/missing) (Table S1). Furthermore, the GBM model exhibited greater ability to discriminate survival probabilities than simple prognostic strategies, such as multifocal EHCC with vascular invasion indicating a dismal prognosis following LR, in sub-cohorts with complete strategy-related information (P<0.001) (Table S2).

Table 2 Performance of GBM Model and Staging Systems

Calibration plots presented excellent agreement between model predicted and actual observed survival in both the training/validation and test cohorts (Figure S2A and B). Decision curve analysis demonstrated that the GBM model provided better clinical utility for EHCC in designing clinical trials than the treat all or treat none strategy across the majority of the range of reasonable threshold probabilities (Figure S2C and D). The model is publicly accessible for use on Github (https://github.com/radgrady/EHCC_GBM), with an app (https://mlehcc.shinyapps.io/EHCC_App/) that allows survival estimates at individual scale (Figure 2D).

We utilized X-tile analysis to generate two optimal cut-off values (6.35 and 5.32 in GBM predictions, Figure S3) that separated EHCC patients into 3 strata with a highly different probability of post-resection survival in the training/validation cohort: low risk (760 [40.0%]; 10-year DSS, 75.6%), intermediate risk (948 [49.9%]; 10-year DSS, 41.8%), and high risk (191 [10.1%]; 10-year DSS, 5.7%) (P<0.001). In the test cohort, the aforementioned 3 prognostic strata by using the GBM model were confirmed: low risk (634 [72.1%]; 10-year DSS, 69.0%), intermediate risk (194 [22.1%]; 10-year DSS, 37.9%), and high risk (51 [5.8%]; 10-year DSS, 4.7%) (P<0.001) (Table 3). Visual inspection of the survival curves again revealed that, compared with the 8th edition AJCC criteria, the GBM model provided better prognostic stratification in both the training/validation and test cohorts (Figure 3). Differences in the baseline patient characteristics according to risk groups defined by the GBM model are summarized in Table S3.

Table 3 Disease-Specific Survival According to Risk Stratification

Figure 3 Kaplan-Meier survival plots demonstrating disparities between groups. Disease-specific survival stratified by the 8th edition of the American Joint Committee on Cancer T stage and the machine-learning model in the training/validation (A and C) and the test (B and D) cohort.

We also gathered data of 2124 EHCC patients (1671 males and 453 females; median age, 58 years; IQR, 5362 years) treated with LT from the SEER-Medicare database. SEER data demonstrated that considerable differences existed between LR (n=1899) and LT (n=2124) cohorts in terms of all listed clinical variables except for alpha-fetoprotein level (Table S4). Upon initial analysis, we found a remarkable survival benefit of LT over LR for patients with EHCC (hazard ratio [HR] 0.342, 95% CI 0.3000.389, P<0.001), which was further confirmed in a well-matched cohort of 1892 patients produced by PSM (HR 0.342, 95% CI 0.2850.410, P<0.001). Although a trend for higher survival probability was observed after 5 years in the LT cohort, no statistically significant difference in DSS was observed when compared with low-risk LR cohort (HR 0.850, 95% CI 0.6791.064, P=0.138). After PSM, 420 patients in the LT cohort were matched to 420 patients in the low-risk LR cohort; the trend for improved survival remained after 5 years in the matched LT cohort while the matched comparison also yielded no significant survival difference (HR 0.802, 95% CI 0.5611.145, P=0.226) (Figure 4). By contrast, when compared with intermediate-and high-risk patients treated with LR, remarkable survival benefits were observed in patients treated with LT both before and after PSM (P<0.001) (Table S5).

Figure 4 Comparison of survival after resection versus transplantation before and after propensity score matching in SEER-Medicare database. (A) KaplanMeier curves for different risk groups stratified by the model in the SEER resection cohort (n=1899) and patients in the SEER transplantation cohort (n=2124). (B) KaplanMeier curves for low-risk patients treated with resection and patients treated with transplantation in propensity score-matched cohort (n=840).

In this study involving over 2700 EHCC patients treated with resection, a gradient-boosting ML model was trained, validated and tested to predict post-resection survival. Our results demonstrated that this ML model utilized readily available clinical information, such as age, race, alpha-fetoprotein level, tumor size and number, vascular invasion, histological grade and fibrosis score, and provided real-time, accurate prognosis prediction (C-statistic >0.72) that outperform traditional staging systems. Among the model covariates, tumor-related characteristics, such as size, multifocality and vascular invasion, as well as liver cirrhosis are known risk factors for poor survival following resection of HCC.710 Besides, multiple population-based studies have shown the racial and age differences in survival of HCC.19,20 Therefore, our ML model is a valid and reliable tool to estimate prognosis of EHCC patients. This study represents, to our knowledge, the first application of a state-of-the-art ML survival prediction algorithm in EHCC based on large-scale, heterogeneous datasets.

In SEER cohort, the 10-year survival rate of EHCC after LR was around 50%, which seemed acceptable but was remarkably lower than that after LT (around 80%). No adjuvant therapies are able to prevent tumor relapse and cirrhosis progression; however, patients with dismal prognosis should be considered candidates for clinical trials of adjuvant therapy.7 Salvage LT has also been a highly applicable strategy to alleviate both graft shortage and waitlist dropout with excellent outcomes that are comparable to upfront LT.1,5 Priority policy, defined as enlistment of patients at high mortality risk before disease progression, was then implemented to improve the transplantability rate.21 Promisingly, our ML tool may help clinicians better identify EHCC patients who are at high risk of disease-related death, engage in clinical trials, and meet priority enlistment policy. Specifically, the GBM model identified 10% of EHCC patients who suffered from extremely dismal prognosis following LR in this study. Given its small proportion and survival benefit, we advocate the pre-emptive enlistment of high-risk subset for salvage LT after LR to avoid the later emergence of advanced disease (ie, tumor recurrence and liver decompensation) ultimately leading to death. Moreover, 40% of EHCC patients were at intermediate risk of disease-related death; adjuvant treatments that target HCC and cirrhosis are desirable. In turn, nearly half of EHCC patients were categorized as low risk by using the GBM model. The low-risk subset permits satisfactory long-term survival after LR and may receive no adjuvant therapy. We note that DSS curves are separated after 5 years for low-risk patients treated with LR as compared with patients treated with upfront LT, and thus long-lasting surveillance should be maintained.

Prior efforts to improve prognostic prediction of EHCC have mostly been reliant on tissue-based or imaging-assisted quantification of research biomarkers.9,22 However, a more accurate, yet more complex, prognosis estimate does not necessarily present a better clinical tool. Parametric regression models are ubiquitous in clinical research because of their simplicity and interpretability; however, regression analysis should be performed in complete cases only.23 Moreover, regression modeling strategies assume that relationships among input variables are linear and homogeneous but complicated interactions exist between predictors.24,25 Decision tree-based methods represent a large family of ML algorithms and can reveal complex non-linear relationships between covariates. GBM algorithm has been widely applied in big data analysis and consistently utilized by the top performers of ML predictive modelling competitions.14,26 GBM algorithm utilizes the boosting procedure to combine stumps of massive decision-tree-base-learners, which is similar to the clinical decision-making process for a patient by aggregating consultations from multiple specialists, each which would that look at the case in a slightly different way. Thus, our GBM model directly integrates interpretability in order to mitigate this issue. Compared with other tree-based ensemble methods such as random forest, GBM algorithm also has a built-in functionality to handle missing values that permits utilizing data from, and assigning classification to, all observations in the cohort without the need to impute data. We applied nested cross-validation scheme for hyperparameter tuning in GBM as it prevents information leaking between observations used for training and validating the model, and estimates the external test error of the given algorithm on unseen datasets more accurately by averaging its performance metrics across folds.27 Comparable discriminatory ability in the training/validation cohort, the test cohort as well as sub-cohorts from different clinical scenarios suggested good reproducibility and reliability of the proposed GBM model.

Our study has several limitations that warrant attention. First, all the presented analyses are retrospective; prospective validations of the ML model in different populations are warranted prior to routine use in clinical practice. Second, the study cohort included population-based cancer registries with limited information regarding patient and tumor characteristics; unavailable confounders, such as biochemical parameters, surgical margin status and recurrence treatment modality could not be adjusted for modeling. Third, SEER-Medicare database contains a considerable amount of missing data in several important clinical variables, such as fibrosis score. Indeed, missing data represent an unavoidable feature of all clinical and population-based databases; however, improper management of data resource, such as simply excluding cases with missing data, can introduce considerable bias, as previously noted across numerous cancer types.28 We therefore contend that integrating missingness into our GBM model indicates good transferability in future clinical practice.

In conclusion, ML approach is both feasible and accurate, and a novel way to consider analysis of survival outcomes in clinical scenarios. Our results suggest that a GBM model trained on readily-available clinical data provides good performance that is better than staging systems in predicting prognosis. Although several issues must be addressed, such as prospective validations and ethical challenges, prior to its widespread use, such an automated tool may complement existing prognostic sources and lead to better personalized treatments for patients with resected EHCC.

EHCC, early hepatocellular carcinoma; LT, liver transplantation; LR, liver resection; BCLC, Barcelona Clinic Liver Cancer; China Liver Cancer, CNLC; HKLC, Hong Kong Liver Cancer; CLIP, Cancer of the Liver Italian Program; AJCC, American Joint Committee on Cancer; ML, machine learning; GBM, gradient boosting machine; SEER, Surveillance, Epidemiology, and End Results; DSS, disease-specific survival; PSM, propensity score matching; IQR, interquartile range.

Data for model training and validation as well as R codes are available at Github (https://github.com/radgrady/EHCC_GBM). Test data are available from the corresponding author (Xue-Hao Wang) on reasonable request.

This study protocol was approved by the Institution Review Board of First Affiliated Hospital of Nanjing Medical University and Wuxi Peoples Hospital. Written informed consent was waived because retrospective anonymous data were analyzed. Non-identified information was used in order to protect patient data confidentiality.

This study was supported by the Key Program of the National Natural Science Foundation of China (31930020) and the National Natural Science Foundation of China (81530048, 81470901, 81670570).

The authors declare no potential conflicts of interest.

1. Yang JD, Hainaut P, Gores GJ, Amadou A, Plymoth A, Roberts LR. A global view of hepatocellular carcinoma: trends, risk, prevention and management. Nat Rev Gastroenterol Hepatol. 2019;16(10):589604. doi:10.1038/s41575-019-0186-y

2. Llovet JM, Montal R, Sia D, Finn RS. Molecular therapies and precision medicine for hepatocellular carcinoma. Nat Rev Clin Oncol. 2018;15(10):599616. doi:10.1038/s41571-018-0073-4

3. European Association for the Study of the Liver. EASL clinical practice guidelines: management of hepatocellular carcinoma. J Hepatol. 2018;69(1):182236. doi:10.1016/j.jhep.2018.03.019

4. Pinna AD, Yang T, Mazzaferro V, et al. Liver transplantation and hepatic resection can achieve cure for hepatocellular carcinoma. Ann Surg. 2018;268(5):868875. doi:10.1097/SLA.0000000000002889

5. Marrero JA, Kulik LM, Sirlin CB, et al. Diagnosis, staging, and management of hepatocellular carcinoma: 2018 Practice Guidance by the American Association for the Study of Liver Diseases. Hepatology. 2018;68(2):723750. doi:10.1002/hep.29913

6. Zhou J, Sun H, Wang Z, et al. Guidelines for the diagnosis and treatment of hepatocellular carcinoma (2019 Edition). Liver Cancer. 2020;9(6):682720. doi:10.1159/000509424

7. Villanueva A. Hepatocellular carcinoma. N Engl J Med. 2019;380(15):14501462. doi:10.1056/NEJMra1713263

8. Chan AWH, Zhong J, Berhane S, et al. Development of pre and post-operative models to predict early recurrence of hepatocellular carcinoma after surgical resection. J Hepatol. 2018;69(6):12841293. doi:10.1016/j.jhep.2018.08.027

9. Ji GW, Zhu FP, Xu Q, et al. Radiomic features at contrast-enhanced CT predict recurrence in early stage hepatocellular carcinoma: a Multi-Institutional Study. Radiology. 2020;294(3):568579. doi:10.1148/radiol.2020191470

10. Shim JH, Jun MJ, Han S, et al. Prognostic nomograms for prediction of recurrence and survival after curative liver resection for hepatocellular carcinoma. Ann Surg. 2015;261(5):939946. doi:10.1097/SLA.0000000000000747

11. Deo RC. Machine learning in medicine. Circulation. 2015;132(20):19201930. doi:10.1161/CIRCULATIONAHA.115.001593

12. Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380(14):13471358. doi:10.1056/NEJMra1814259

13. Eaton JE, Vesterhus M, McCauley BM, et al. Primary sclerosing cholangitis risk estimate tool (PREsTo) predicts outcomes of the disease: a derivation and validation study using machine learning. Hepatology. 2020;71(1):214224. doi:10.1002/hep.30085

14. Nathan H, Hyder O, Mayo SC, et al. Surgical therapy for early hepatocellular carcinoma in the modern era: a 10-year SEER-medicare analysis. Ann Surg. 2013;258(6):10221027. doi:10.1097/SLA.0b013e31827da749

15. Fritz AG. International Classification of Diseases for Oncology: ICD-O. 3. Geneva, Switzerland: World Health Organization; 2000.

16. Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001;29(5):11891232. doi:10.1214/aos/1013203451

17. Vickers AJ, Elkin EB. Decision curve analysis: a novel method for evaluating prediction models. Med Decis Making. 2006;26(6):565574. doi:10.1177/0272989X06295361

18. Camp RL, Dolled-Filhart M, Rimm DL. X-tile: a new bio-informatics tool for biomarker assessment and outcome-based cut-point optimization. Clin Cancer Res. 2004;10(21):72527259. doi:10.1158/1078-0432.CCR-04-0713

19. Altekruse SF, Henley SJ, Cucinelli JE, McGlynn KA. Changing hepatocellular carcinoma incidence and liver cancer mortality rates in the United States. Am J Gastroenterol. 2014;109(4):542553. doi:10.1038/ajg.2014.11

20. Dasari BV, Kamarajah SK, Hodson J, et al. Development and validation of a risk score to predict the overall survival following surgical resection of hepatocellular carcinoma in non-cirrhotic liver. HPB (Oxford). 2020;22(3):383390. doi:10.1016/j.hpb.2019.07.007

21. Ferrer-Fbrega J, Forner A, Liccioni A, et al. Prospective validation of ab initio liver transplantation in hepatocellular carcinoma upon detection of risk factors for recurrence after resection. Hepatology. 2016;63(3):839849. doi:10.1002/hep.28339

22. Qiu J, Peng B, Tang Y, et al. CpG methylation signature predicts recurrence in early-stage hepatocellular carcinoma: results from a Multicenter Study. J Clin Oncol. 2017;35(7):734742. doi:10.1200/JCO.2016.68.2153

23. Sterne JA, White IR, Carlin JB, et al. Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls. BMJ. 2009;338:b2393. doi:10.1136/bmj.b2393

24. Loftus TJ, Tighe PJ, Filiberto AC, et al. Artificial intelligence and surgical decision-making. JAMA Surg. 2020;155(2):148158. doi:10.1001/jamasurg.2019.4917

25. Shindoh J, Andreou A, Aloia TA, et al. Microvascular invasion does not predict long-term survival in hepatocellular carcinoma up to 2 cm: reappraisal of the staging system for solitary tumors. Ann Surg Oncol. 2013;20(4):12231229. doi:10.1245/s10434-012-2739-y

26. Bibault JE, Chang DT, Xing L. Development and validation of a model to predict survival in colorectal cancer using a gradient-boosted machine. Gut. 2021;70(5):884889. doi:10.1136/gutjnl-2020-321799

27. Maros ME, Capper D, Jones DTW, et al. Machine learning workflows to estimate class probabilities for precision cancer diagnostics on DNA methylation microarray data. Nat Protoc. 2020;15(2):479512. doi:10.1038/s41596-019-0251-6

28. Jeong CW, Washington SL 3rd, Herlemann A, Gomez SL, Carroll PR, Cooperberg MR. The new surveillance, epidemiology, and end results prostate with watchful waiting database: opportunities and limitations. Eur Urol. 2020;78(3):335344. doi:10.1016/j.eururo.2020.01.009

View post:
Machine learning to improve prognosis prediction of EHCC | JHC - Dove Medical Press

From Friday's decision in Soukaneh v. Andrzejewski, written by Judge Janet Bond Arterton (D. Conn.):

At approximately 8:34 pm on November 12, 2018, Plaintiff was operating a Kia Sorento LX in the vicinity of Hillside Avenue and Pine Street in Waterbury, Connecticut. Plaintiff had stopped his vehicle with the engine running in an attempt to unfreeze his iPhone GPS, which was located in a holder mounted to the dashboard. The dark and high-crime area where Plaintiff stopped his vehicle was well-known for prostitution, drug transactions, and other criminal activity.

As Plaintiff was attempting to fix his phone, Defendant approached his vehicle, knocked on the driver's side window, and requested Plaintiff's license. Plaintiff handed Defendant his license and gun permit, which he removed from the back of his sun visor. At the time Plaintiff handed over his license and gun permit, he told Defendant that he was in possession of a pistol, which was located in the driver's side compartment door. Defendant handcuffed and searched Plaintiff, and Defendant forcibly moved Plaintiff to the back of his police car. While Plaintiff was inside the police car in handcuffs, Defendant ran a check through the Northwest Communication Center to determine whether the pistol permit was valid.

The court held that the initial detention for questioning about why the car was stopped there was constitutional:

Defendant's basis for stopping Plaintiff's vehicle was that the car was stopped at night in the roadway with the engine running in an area known for drugs and prostitution. In Connecticut, a parked car may "not obstruct or impede the normal and reasonable movement of traffic." Thus, Defendant observed Plaintiff committing a traffic offense, giving him reasonable suspicion to stop Plaintiff, check his driver's license, and require him to step out of the car.

But the court held that the handcuffing and detention violated the Fourth Amendment, assuming the facts were as the plaintiff alleged:

Defendant conceded at oral argument that his conduct following the initial stop and check of Plaintiff's driver's license exceeded the bounds of a Terry stop, but that the conduct was still justified because he had probable cause to believe Plaintiff was possessing a firearm without a permit as he had not yet been able to verify the validity of the permit.

The question thus becomes whether Plaintiff's disclosure that he had a pistol in the car coupled with presentation of a facially valid, but not yet verified, permit can "arguably" constitute probable cause to believe that he was unlawfully possessing a weapon in his vehicle. An assessment of arguable probable cause requires consideration of the statute Defendant believed Plaintiff might be violating.

Connecticut General Statutes 29-38(a) makes the absence of a permit while possessing a firearm inside a vehicle an element of the offense, meaning that there needed to have been some evidence indicating the probability that Plaintiff was not licensed to possess a firearm in order to suspect that he had committed the crime of unlawful possession of a firearm in a vehicle. But at no time did Defendant have any reasonable suspicion or actual knowledge of Plaintiff's possession of the firearm without simultaneously knowing that Plaintiff demonstrated that he had an apparently valid firearm permit.

Indeed, it is undisputed that Plaintiff told Defendant that he had a pistol in the driver's side door compartment at the time he handed his driver's license and pistol permit to Defendant. And in his deposition, Plaintiff stated that when he handed his license and permit to Defendant, he said, "That's my license and including [sic] my pistol permit, I have a pistol on me." In the absence of any articulable reason for Defendant to believe the permit was counterfeit or otherwise invalid, there is no indication that Plaintiff was even arguably unlawfully possessing a firearm.

In light of the uncontested fact that Plaintiff presented his pistol permit to Defendant before or at the time he disclosed that he was in possession of a pistol and the absence of any other indicia that Plaintiff was otherwise violating the statute, no reasonable officer could believe probable cause was present. Any contrary holding "would eviscerate Fourth Amendment protections for lawfully armed individuals" by presuming a license expressly permitting possession of a firearm was invalid. To accept Defendant's reasoning would permit police officers to detain any driver because he or she may have a counterfeit or otherwise invalid driver's license which has been rejected by the Supreme Court.

Because, on the record read in the light most favorable to the non-moving party, no reasonable police officer could have believed he or she had probable cause to arrest Plaintiff, the Court denies summary judgment on the lawfulness of the de facto arrest .

The court also held that the law was clear enough that the police officer didn't have qualified immunity from the claim. And it likewise held as to the follow-up search of the car:

"[T]he search of the passenger compartment of an automobile, limited to those areas in which a weapon may be placed or hidden if the police officer possesses a reasonable belief based on 'specific and articulable facts which, taken together with the rational inferences from those facts, reasonably warrant' the officers in believing that the suspect is dangerous and that the suspect may gain immediate control of weapons."

On this record, no reasonable officer could conclude that Plaintiff posed a meaningful threat of being "armed and dangerous" simply because he disclosed that he had a pistol and a license to possess it. Any contrary holding would make it practically impossible for the lawful owner of a firearm to maintain a Fourth Amendment right to privacy in his or her automobile.

More here:
Fourth Amendment Forbids Handcuffing Driver Just Because He Has Gun + Gun Permit - Reason

Aug 15, 20215:00 PMEDT

Many worry that the government will force Apple to grant access to their private photos since they now scan all iCloud uploads for child sexual abuse material.

Cupertino, California - After Apple's recent announcement that it would scan all photos uploaded to iCloud for child sexual abuse material (CSAM), many began to worry that the government could force the company to grant access to their private photos.

Matt Tait, the COO of security company Corellium, reassured users that because the US has the Fourth Amendment in place, the government wouldn't be allowed to use private scanning services to spy on American citizens, according to a summary provided by 9to5Mac.

The Fourth Amendment protects US citizens from unreasonable search and seizure.

Tait is a former analyst for GCHQ, which is the British version of the US' National Security Agency, so he should know what he's talking about.

The new concerns about spying stem from the recent Pegasus software hacking of prominent journalists and leaders who found their phone's information and private photos stolen and leaked.

A fear, according to Johns Hopkins cryptographer Matthew Green, is that the Department of Justice could go to the National Center for Missing & Exploited Children (NCMEC) and ask them to add other photos to the database that teaches Apple's program what to scan for. This could, perhaps, include photos of missing children, wanted criminals, or anyone who is a person of interest to the government.

Given that the NCMEC isn't a wholly government-run organization, there might not be much oversight when this happens.

In this scenario, the photos could then trigger Apple's new system, and if there is enough suspicion, the government could force Apple to turn over customers' information.

Yet, according to Tait, the fact that NCMEC isn't a full government entity is what will keep Americans safe, as they can't easily be forced by the government to do anything.

Apple could also blow the whistle on any requests for information that don't match CSAM parameters, signaling that the government is attempting to circumvent the Fourth Amendment and violate citizens' protection.

Likewise, Apple isn't obligated to work with NCMEC, and the relationship is voluntary.

Additionally, any perceived invasion of privacy would probably be overthrown in court, as it is unlikely the government could supply any proof this doesn't violate the Fourth Amendment.

At least for now, iCloud users can rest a bit easier.

Read the original:
Can the government use Apple's new iCloud scanning program to spy on citizens? - TAG24 NEWS

EFF would like to thank former intern Haley Amster for drafting this post, and former legal fellow Nathan Sobel for his assistance in editing it.

The Fourth Amendment requires authorities to target search warrants at particular places or thingslike a home, a bank deposit box, or a cell phoneand only when there is reason to believe that evidence of a crime will be found there. The Constitutions drafters put in place these essential limits on government power after suffering under British searches called general warrants that gave authorities unlimited discretion to search nearly everyone and everything for evidence of a crime.

Yet today, Google is facilitating the digital equivalent of those colonial-era general warrants. Through the use of geofence warrants (also known as reverse location warrants), federal and state law enforcement officers are routinely requesting that Google search users accounts to determine who was in a certain geographic area at a particular timeand then to track individuals outside of that initially specific area and time period.

These warrants are anathema to the Fourth Amendments core guarantee largely because, by design, they sweep up people wholly unconnected to the crime under investigation.

For example, in 2020 Florida police obtained a geofence warrant in a burglary investigation that led them to suspect a man who frequently rode his bicycle in the area. Google collected the mans location history when he used an app on his smartphone to track his rides, a scenario that ultimately led police to suspect him of the crime even though he was innocent.

Google is the linchpin in this unconstitutional scheme. Authorities send Google geofence warrants precisely because Googles devices, operating system, apps, and other products allow it to collect data from millions of users and to catalog these users locations, movements, associations, and other private details of their lives.

Although Google has sometimes pushed back in court on the breadth of some of these warrants, it has largely acquiesced to law enforcement demandsand the number of geofence warrants law enforcement sends to the company has dramatically increased in recent years. This stands in contrast to documented instances of other companies resisting law enforcement requests for user data on Fourth Amendment grounds.

Its past time for Google to stand up for its users privacy and to resist these unlawful warrants. A growing coalition of civil rights and other organizations, led by the Surveillance Technology and Oversight Project, have previously called on Google to do so. We join that coalitions call for change and further demand that Google:

As explained below, these are the minimum steps Google must take to show that it is committed to its users privacy and the Fourth Amendments protections against general warrants.

EFF calls on Google to stop complying with the geofence warrants it receives. As it stands now, Google appears to have set up an internal system that streamlines, systematizes, and encourages law enforcements use of geofence warrants. Googles practice of complying with geofence warrants despite their unconstitutionality is inconsistent with its stated promise to protect the privacy of its users by keeping your information safe, treating it responsibly, and putting you in control. As recently as October, Googles parent companys CEO, Sundar Pichai, said that [p]rivacy is one of the most important areas we invest in as a company, and in the past, Google has even gone to court to protect its users sensitive data from overreaching government legal process. However, Googles compliance with geofence warrants is incongruent with these platitudes and the companys past actions.

To live up to its promises, Google should commit to either refusing to comply with these unlawful warrants or to challenging them in court. By refusing to comply, Google would put the burden on law enforcement to demonstrate the legality of its warrant in court. Other companies, and even Google itself, have done this in the past. Google should not defer to law enforcements contention that geofence warrants are constitutional, especially given law enforcements well-documented history of trying novel surveillance and legal theories that courts later rule to be unconstitutional. And to the extent Google has refused to comply with geofence warrants, it should say so publicly.

Googles ongoing cooperation is all the more unacceptable given that other companies that collect similar location data from their users, including Microsoft and Garmin, have publicly stated that they would not comply with geofence warrants.

Even if Google were to stop complying with geofence warrants today, it still must be much more transparent about geofence warrants it has received in the past. Google must break out information and provide further details about geofence warrants in its biannual Transparency Reports.

Googles Transparency Reports currently document, among other things, the types and volume of law enforcement requests for user data the company receives, but they do not, as of now, break out information about geofence warrants or provide further details about them. With no detailed reporting from Google about the geofence warrants it has received, the public is left to learn about them via leaks to reporters or by combing through court filings.

Here are a few specific ways Google can be more transparent:

Google should disclose the following information about all geofence warrants it has received over the last five years and commit to continue doing so moving forward:

Google should also resist nondisclosure orders and litigate to ensure, if imposed, that the government has made the appropriate showing required by law. If Google is subject to such an order, or the related docket is sealed (prohibiting the company from disclosing the fact it has received some geofence warrants or from providing other details), Google should move to end those orders and to unseal those dockets so it can make details about them public as early as allowable by law.

Google should also support and seek to provide basic details about court cases and docket numbers for orders authorizing each geofence warrant and docket numbers for any related criminal prosecutions Google is aware of as a result of the geofence warrants. At minimum, Google should disclose details on the agencies seeking geofence warrants, broken down by each federal agency, state-level agencies, and local law enforcement.

Google must start telling its users when their information is caught up in a geofence warranteven if that information is de-identified. This notice to affected users should state explicitly what information Google produced, in what format, which agency requested it, which court authorized the warrant, and whether Google provided identifying information. Notice to users here is critical: if people arent aware of how they are being affected by these warrants, there cant be meaningful public debate about them.

To the extent the law requires Google to delay notice or not disclose the existence of the warrant, Google should challenge such restrictions so as to only comply with valid ones, and it should provide users with notice as soon as possible.

It does not appear that Google gives notice to every user whose data is requested by law enforcement. Some affected users have said that Google notified them that law enforcement accessed their account via a geofence warrant. But in some of the cases EFF has followed, it appears that Google has not always notified affected users who it identifies in response to these warrants, with no public explanation from Google. Googles policies state that it gives notice to users before disclosing information, but more clarity is warranted here. Google should publicly state whether its policy is being applied to all users information subject to geofence warrants, or only those who they identify to law enforcement.

Many people do not know, much less understand, how and when Google collects and stores location data. Google must do a better job of explaining its policies and practices to users, not processing user data absent opt-in consent, minimizing the amount of data it collects, deleting retained data users no longer need, and giving users the ability to easily delete their data.

Well before law enforcement ever comes calling, Google must first ensure it does not collect its users location data before obtaining meaningful consent from them. This consent should establish a fair way for users to opt into data collection, as click-through agreements which apply to dozens of services, data types, or uses at once are insufficient. As one judge in a case involving Facebook put it, the logic that merely clicking I agree indicates true consent requires everyone to pretend that users read every word of these policies before clicking their acceptance, even though we all know that virtually none of them did.

Google should also explain exactly what location data it collects from users, when that collection occurs, what purpose it is used for, and how long Google retains that data. This should be clear and understandable, not buried in dense privacy policies or terms of service.

Google should also only be collecting, retaining, and using its customers location data for a specific purpose, such as to provide directions on Google Maps or to measure road traffic congestion. Data must not be collected or used for a different purpose, such as for targeted advertising, unless users separately opt in to such use. Beyond notice and consent, Google must minimize its processing of user data, that is, only process user data as reasonably necessary to give users what they asked for. For example, user data should be deleted when it is no longer needed for the specific purpose for which it was initially collected, unless the user specifically requests that the data be saved.

Although Google allows users to manually delete their location data and to set automated deletion schedules, Google should confirm that these tools are not illusory. Recent enforcement actions by state attorneys allege that users cannot fully delete their data, much less fully opt out of having their location data collected at all.

* * *

Google holds a tremendous amount of power over law enforcements ability to use geofence warrants. Instead of keeping quiet about them and waiting for defendants in criminal cases to challenge them in court, Google needs to stand up for its users when it comes to revealing their sensitive data to law enforcement.

Continued here:
It's Time for Google to Resist Geofence Warrants and to Stand Up for Its Affected Users - EFF